diff options
Diffstat (limited to '')
89 files changed, 25717 insertions, 0 deletions
diff --git a/arch/arm/kernel/.gitignore b/arch/arm/kernel/.gitignore new file mode 100644 index 000000000..bbb90f92d --- /dev/null +++ b/arch/arm/kernel/.gitignore @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +vmlinux.lds diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile new file mode 100644 index 000000000..48737ec80 --- /dev/null +++ b/arch/arm/kernel/Makefile @@ -0,0 +1,111 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the linux kernel. +# + +CPPFLAGS_vmlinux.lds := -DTEXT_OFFSET=$(TEXT_OFFSET) +AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET) + +ifdef CONFIG_FUNCTION_TRACER +CFLAGS_REMOVE_ftrace.o = -pg +CFLAGS_REMOVE_insn.o = -pg +CFLAGS_REMOVE_patch.o = -pg +CFLAGS_REMOVE_unwind.o = -pg +endif + +CFLAGS_REMOVE_return_address.o = -pg + +# Object file lists. + +obj-y := elf.o entry-common.o irq.o opcodes.o \ + process.o ptrace.o reboot.o io.o \ + setup.o signal.o sigreturn_codes.o \ + stacktrace.o sys_arm.o time.o traps.o + +KASAN_SANITIZE_stacktrace.o := n +KASAN_SANITIZE_traps.o := n + +ifneq ($(CONFIG_ARM_UNWIND),y) +obj-$(CONFIG_FRAME_POINTER) += return_address.o +endif + +obj-$(CONFIG_ATAGS) += atags_parse.o +obj-$(CONFIG_ATAGS_PROC) += atags_proc.o +obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o + +ifeq ($(CONFIG_CPU_V7M),y) +obj-y += entry-v7m.o v7m.o +else +obj-y += entry-armv.o +endif + +obj-$(CONFIG_MMU) += bugs.o +obj-$(CONFIG_CPU_IDLE) += cpuidle.o +obj-$(CONFIG_ISA_DMA_API) += dma.o +obj-$(CONFIG_FIQ) += fiq.o fiqasm.o +obj-$(CONFIG_MODULES) += armksyms.o module.o +obj-$(CONFIG_ARM_MODULE_PLTS) += module-plts.o +obj-$(CONFIG_PCI) += bios32.o isa.o +obj-$(CONFIG_ARM_CPU_SUSPEND) += sleep.o suspend.o +obj-$(CONFIG_HIBERNATION) += hibernate.o +obj-$(CONFIG_SMP) += smp.o +ifdef CONFIG_MMU +obj-$(CONFIG_SMP) += smp_tlb.o +endif +obj-$(CONFIG_HAVE_ARM_SCU) += smp_scu.o +obj-$(CONFIG_HAVE_ARM_TWD) += smp_twd.o +obj-$(CONFIG_ARM_ARCH_TIMER) += arch_timer.o +obj-$(CONFIG_FUNCTION_TRACER) += entry-ftrace.o +obj-$(CONFIG_DYNAMIC_FTRACE) += ftrace.o insn.o patch.o +obj-$(CONFIG_FUNCTION_GRAPH_TRACER) += ftrace.o insn.o patch.o +obj-$(CONFIG_JUMP_LABEL) += jump_label.o insn.o patch.o +obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o +# Main staffs in KPROBES are in arch/arm/probes/ . +obj-$(CONFIG_KPROBES) += patch.o insn.o +obj-$(CONFIG_OABI_COMPAT) += sys_oabi-compat.o +obj-$(CONFIG_ARM_THUMBEE) += thumbee.o +obj-$(CONFIG_KGDB) += kgdb.o patch.o +obj-$(CONFIG_ARM_UNWIND) += unwind.o +obj-$(CONFIG_HAVE_TCM) += tcm.o +obj-$(CONFIG_OF) += devtree.o +obj-$(CONFIG_CRASH_DUMP) += crash_dump.o +obj-$(CONFIG_SWP_EMULATE) += swp_emulate.o +CFLAGS_swp_emulate.o := -Wa,-march=armv7-a +obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o + +obj-$(CONFIG_CPU_XSCALE) += xscale-cp0.o +obj-$(CONFIG_CPU_XSC3) += xscale-cp0.o +obj-$(CONFIG_CPU_MOHAWK) += xscale-cp0.o +obj-$(CONFIG_CPU_PJ4) += pj4-cp0.o +obj-$(CONFIG_CPU_PJ4B) += pj4-cp0.o +obj-$(CONFIG_IWMMXT) += iwmmxt.o +obj-$(CONFIG_PERF_EVENTS) += perf_regs.o perf_callchain.o +obj-$(CONFIG_HW_PERF_EVENTS) += perf_event_xscale.o perf_event_v6.o \ + perf_event_v7.o +AFLAGS_iwmmxt.o := -Wa,-mcpu=iwmmxt +obj-$(CONFIG_ARM_CPU_TOPOLOGY) += topology.o +obj-$(CONFIG_VDSO) += vdso.o +obj-$(CONFIG_EFI) += efi.o +obj-$(CONFIG_PARAVIRT) += paravirt.o + +obj-y += head$(MMUEXT).o +obj-$(CONFIG_DEBUG_LL) += debug.o +obj-$(CONFIG_EARLY_PRINTK) += early_printk.o +obj-$(CONFIG_ARM_PATCH_PHYS_VIRT) += phys2virt.o + +# This is executed very early using a temporary stack when no memory allocator +# nor global data is available. Everything has to be allocated on the stack. +CFLAGS_head-inflate-data.o := $(call cc-option,-Wframe-larger-than=10240) +obj-$(CONFIG_XIP_DEFLATED_DATA) += head-inflate-data.o + +obj-$(CONFIG_ARM_VIRT_EXT) += hyp-stub.o +AFLAGS_hyp-stub.o :=-Wa,-march=armv7-a +ifeq ($(CONFIG_ARM_PSCI),y) +obj-$(CONFIG_SMP) += psci_smp.o +endif + +obj-$(CONFIG_HAVE_ARM_SMCCC) += smccc-call.o + +obj-$(CONFIG_GENERIC_CPU_VULNERABILITIES) += spectre.o + +extra-y := vmlinux.lds diff --git a/arch/arm/kernel/arch_timer.c b/arch/arm/kernel/arch_timer.c new file mode 100644 index 000000000..b5e217907 --- /dev/null +++ b/arch/arm/kernel/arch_timer.c @@ -0,0 +1,42 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/arch_timer.c + * + * Copyright (C) 2011 ARM Ltd. + * All Rights Reserved + */ +#include <linux/init.h> +#include <linux/types.h> +#include <linux/errno.h> + +#include <asm/delay.h> +#include <asm/arch_timer.h> + +#include <clocksource/arm_arch_timer.h> + +static unsigned long arch_timer_read_counter_long(void) +{ + return arch_timer_read_counter(); +} + +static struct delay_timer arch_delay_timer; + +static void __init arch_timer_delay_timer_register(void) +{ + /* Use the architected timer for the delay loop. */ + arch_delay_timer.read_current_timer = arch_timer_read_counter_long; + arch_delay_timer.freq = arch_timer_get_rate(); + register_current_timer_delay(&arch_delay_timer); +} + +int __init arch_timer_arch_init(void) +{ + u32 arch_timer_rate = arch_timer_get_rate(); + + if (arch_timer_rate == 0) + return -ENXIO; + + arch_timer_delay_timer_register(); + + return 0; +} diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c new file mode 100644 index 000000000..82e96ac83 --- /dev/null +++ b/arch/arm/kernel/armksyms.c @@ -0,0 +1,177 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/armksyms.c + * + * Copyright (C) 2000 Russell King + */ +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/string.h> +#include <linux/delay.h> +#include <linux/in6.h> +#include <linux/syscalls.h> +#include <linux/uaccess.h> +#include <linux/io.h> +#include <linux/arm-smccc.h> + +#include <asm/checksum.h> +#include <asm/ftrace.h> + +/* + * libgcc functions - functions that are used internally by the + * compiler... (prototypes are not correct though, but that + * doesn't really matter since they're not versioned). + */ +extern void __ashldi3(void); +extern void __ashrdi3(void); +extern void __divsi3(void); +extern void __lshrdi3(void); +extern void __modsi3(void); +extern void __muldi3(void); +extern void __ucmpdi2(void); +extern void __udivsi3(void); +extern void __umodsi3(void); +extern void __do_div64(void); +extern void __bswapsi2(void); +extern void __bswapdi2(void); + +extern void __aeabi_idiv(void); +extern void __aeabi_idivmod(void); +extern void __aeabi_lasr(void); +extern void __aeabi_llsl(void); +extern void __aeabi_llsr(void); +extern void __aeabi_lmul(void); +extern void __aeabi_uidiv(void); +extern void __aeabi_uidivmod(void); +extern void __aeabi_ulcmp(void); + +extern void fpundefinstr(void); + +void mmioset(void *, unsigned int, size_t); +void mmiocpy(void *, const void *, size_t); + + /* platform dependent support */ +EXPORT_SYMBOL(arm_delay_ops); + + /* networking */ +EXPORT_SYMBOL(csum_partial); +EXPORT_SYMBOL(csum_partial_copy_from_user); +EXPORT_SYMBOL(csum_partial_copy_nocheck); +EXPORT_SYMBOL(__csum_ipv6_magic); + + /* io */ +#ifndef __raw_readsb +EXPORT_SYMBOL(__raw_readsb); +#endif +#ifndef __raw_readsw +EXPORT_SYMBOL(__raw_readsw); +#endif +#ifndef __raw_readsl +EXPORT_SYMBOL(__raw_readsl); +#endif +#ifndef __raw_writesb +EXPORT_SYMBOL(__raw_writesb); +#endif +#ifndef __raw_writesw +EXPORT_SYMBOL(__raw_writesw); +#endif +#ifndef __raw_writesl +EXPORT_SYMBOL(__raw_writesl); +#endif + + /* string / mem functions */ +EXPORT_SYMBOL(strchr); +EXPORT_SYMBOL(strrchr); +EXPORT_SYMBOL(memset); +EXPORT_SYMBOL(__memset32); +EXPORT_SYMBOL(__memset64); +EXPORT_SYMBOL(memcpy); +EXPORT_SYMBOL(memmove); +EXPORT_SYMBOL(memchr); + +EXPORT_SYMBOL(mmioset); +EXPORT_SYMBOL(mmiocpy); + +#ifdef CONFIG_MMU +EXPORT_SYMBOL(copy_page); + +EXPORT_SYMBOL(arm_copy_from_user); +EXPORT_SYMBOL(arm_copy_to_user); +EXPORT_SYMBOL(arm_clear_user); + +EXPORT_SYMBOL(__get_user_1); +EXPORT_SYMBOL(__get_user_2); +EXPORT_SYMBOL(__get_user_4); +EXPORT_SYMBOL(__get_user_8); + +#ifdef __ARMEB__ +EXPORT_SYMBOL(__get_user_64t_1); +EXPORT_SYMBOL(__get_user_64t_2); +EXPORT_SYMBOL(__get_user_64t_4); +EXPORT_SYMBOL(__get_user_32t_8); +#endif + +EXPORT_SYMBOL(__put_user_1); +EXPORT_SYMBOL(__put_user_2); +EXPORT_SYMBOL(__put_user_4); +EXPORT_SYMBOL(__put_user_8); +#endif + + /* gcc lib functions */ +EXPORT_SYMBOL(__ashldi3); +EXPORT_SYMBOL(__ashrdi3); +EXPORT_SYMBOL(__divsi3); +EXPORT_SYMBOL(__lshrdi3); +EXPORT_SYMBOL(__modsi3); +EXPORT_SYMBOL(__muldi3); +EXPORT_SYMBOL(__ucmpdi2); +EXPORT_SYMBOL(__udivsi3); +EXPORT_SYMBOL(__umodsi3); +EXPORT_SYMBOL(__do_div64); +EXPORT_SYMBOL(__bswapsi2); +EXPORT_SYMBOL(__bswapdi2); + +#ifdef CONFIG_AEABI +EXPORT_SYMBOL(__aeabi_idiv); +EXPORT_SYMBOL(__aeabi_idivmod); +EXPORT_SYMBOL(__aeabi_lasr); +EXPORT_SYMBOL(__aeabi_llsl); +EXPORT_SYMBOL(__aeabi_llsr); +EXPORT_SYMBOL(__aeabi_lmul); +EXPORT_SYMBOL(__aeabi_uidiv); +EXPORT_SYMBOL(__aeabi_uidivmod); +EXPORT_SYMBOL(__aeabi_ulcmp); +#endif + + /* bitops */ +EXPORT_SYMBOL(_set_bit); +EXPORT_SYMBOL(_test_and_set_bit); +EXPORT_SYMBOL(_clear_bit); +EXPORT_SYMBOL(_test_and_clear_bit); +EXPORT_SYMBOL(_change_bit); +EXPORT_SYMBOL(_test_and_change_bit); +EXPORT_SYMBOL(_find_first_zero_bit_le); +EXPORT_SYMBOL(_find_next_zero_bit_le); +EXPORT_SYMBOL(_find_first_bit_le); +EXPORT_SYMBOL(_find_next_bit_le); + +#ifdef __ARMEB__ +EXPORT_SYMBOL(_find_first_zero_bit_be); +EXPORT_SYMBOL(_find_next_zero_bit_be); +EXPORT_SYMBOL(_find_first_bit_be); +EXPORT_SYMBOL(_find_next_bit_be); +#endif + +#ifdef CONFIG_FUNCTION_TRACER +EXPORT_SYMBOL(__gnu_mcount_nc); +#endif + +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT +EXPORT_SYMBOL(__pv_phys_pfn_offset); +EXPORT_SYMBOL(__pv_offset); +#endif + +#ifdef CONFIG_HAVE_ARM_SMCCC +EXPORT_SYMBOL(__arm_smccc_smc); +EXPORT_SYMBOL(__arm_smccc_hvc); +#endif diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c new file mode 100644 index 000000000..2c8d76fd7 --- /dev/null +++ b/arch/arm/kernel/asm-offsets.c @@ -0,0 +1,173 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 1995-2003 Russell King + * 2001-2002 Keith Owens + * + * Generate definitions needed by assembly language modules. + * This code generates raw asm output which is post-processed to extract + * and format the required data. + */ +#include <linux/compiler.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/dma-mapping.h> +#include <asm/cacheflush.h> +#include <asm/kexec-internal.h> +#include <asm/glue-df.h> +#include <asm/glue-pf.h> +#include <asm/mach/arch.h> +#include <asm/thread_info.h> +#include <asm/memory.h> +#include <asm/mpu.h> +#include <asm/procinfo.h> +#include <asm/suspend.h> +#include <asm/vdso_datapage.h> +#include <asm/hardware/cache-l2x0.h> +#include <linux/kbuild.h> +#include <linux/arm-smccc.h> +#include "signal.h" + +/* + * Make sure that the compiler and target are compatible. + */ +#if defined(__APCS_26__) +#error Sorry, your compiler targets APCS-26 but this kernel requires APCS-32 +#endif + +int main(void) +{ + DEFINE(TSK_ACTIVE_MM, offsetof(struct task_struct, active_mm)); +#ifdef CONFIG_STACKPROTECTOR + DEFINE(TSK_STACK_CANARY, offsetof(struct task_struct, stack_canary)); +#endif + BLANK(); + DEFINE(TI_FLAGS, offsetof(struct thread_info, flags)); + DEFINE(TI_PREEMPT, offsetof(struct thread_info, preempt_count)); + DEFINE(TI_CPU, offsetof(struct thread_info, cpu)); + DEFINE(TI_CPU_DOMAIN, offsetof(struct thread_info, cpu_domain)); + DEFINE(TI_CPU_SAVE, offsetof(struct thread_info, cpu_context)); + DEFINE(TI_ABI_SYSCALL, offsetof(struct thread_info, abi_syscall)); + DEFINE(TI_USED_CP, offsetof(struct thread_info, used_cp)); + DEFINE(TI_TP_VALUE, offsetof(struct thread_info, tp_value)); + DEFINE(TI_FPSTATE, offsetof(struct thread_info, fpstate)); +#ifdef CONFIG_VFP + DEFINE(TI_VFPSTATE, offsetof(struct thread_info, vfpstate)); +#ifdef CONFIG_SMP + DEFINE(VFP_CPU, offsetof(union vfp_state, hard.cpu)); +#endif +#endif +#ifdef CONFIG_ARM_THUMBEE + DEFINE(TI_THUMBEE_STATE, offsetof(struct thread_info, thumbee_state)); +#endif +#ifdef CONFIG_IWMMXT + DEFINE(TI_IWMMXT_STATE, offsetof(struct thread_info, fpstate.iwmmxt)); +#endif + BLANK(); + DEFINE(S_R0, offsetof(struct pt_regs, ARM_r0)); + DEFINE(S_R1, offsetof(struct pt_regs, ARM_r1)); + DEFINE(S_R2, offsetof(struct pt_regs, ARM_r2)); + DEFINE(S_R3, offsetof(struct pt_regs, ARM_r3)); + DEFINE(S_R4, offsetof(struct pt_regs, ARM_r4)); + DEFINE(S_R5, offsetof(struct pt_regs, ARM_r5)); + DEFINE(S_R6, offsetof(struct pt_regs, ARM_r6)); + DEFINE(S_R7, offsetof(struct pt_regs, ARM_r7)); + DEFINE(S_R8, offsetof(struct pt_regs, ARM_r8)); + DEFINE(S_R9, offsetof(struct pt_regs, ARM_r9)); + DEFINE(S_R10, offsetof(struct pt_regs, ARM_r10)); + DEFINE(S_FP, offsetof(struct pt_regs, ARM_fp)); + DEFINE(S_IP, offsetof(struct pt_regs, ARM_ip)); + DEFINE(S_SP, offsetof(struct pt_regs, ARM_sp)); + DEFINE(S_LR, offsetof(struct pt_regs, ARM_lr)); + DEFINE(S_PC, offsetof(struct pt_regs, ARM_pc)); + DEFINE(S_PSR, offsetof(struct pt_regs, ARM_cpsr)); + DEFINE(S_OLD_R0, offsetof(struct pt_regs, ARM_ORIG_r0)); + DEFINE(PT_REGS_SIZE, sizeof(struct pt_regs)); + DEFINE(SVC_DACR, offsetof(struct svc_pt_regs, dacr)); + DEFINE(SVC_REGS_SIZE, sizeof(struct svc_pt_regs)); + BLANK(); + DEFINE(SIGFRAME_RC3_OFFSET, offsetof(struct sigframe, retcode[3])); + DEFINE(RT_SIGFRAME_RC3_OFFSET, offsetof(struct rt_sigframe, sig.retcode[3])); + BLANK(); +#ifdef CONFIG_CACHE_L2X0 + DEFINE(L2X0_R_PHY_BASE, offsetof(struct l2x0_regs, phy_base)); + DEFINE(L2X0_R_AUX_CTRL, offsetof(struct l2x0_regs, aux_ctrl)); + DEFINE(L2X0_R_TAG_LATENCY, offsetof(struct l2x0_regs, tag_latency)); + DEFINE(L2X0_R_DATA_LATENCY, offsetof(struct l2x0_regs, data_latency)); + DEFINE(L2X0_R_FILTER_START, offsetof(struct l2x0_regs, filter_start)); + DEFINE(L2X0_R_FILTER_END, offsetof(struct l2x0_regs, filter_end)); + DEFINE(L2X0_R_PREFETCH_CTRL, offsetof(struct l2x0_regs, prefetch_ctrl)); + DEFINE(L2X0_R_PWR_CTRL, offsetof(struct l2x0_regs, pwr_ctrl)); + BLANK(); +#endif +#ifdef CONFIG_CPU_HAS_ASID + DEFINE(MM_CONTEXT_ID, offsetof(struct mm_struct, context.id.counter)); + BLANK(); +#endif + DEFINE(VMA_VM_MM, offsetof(struct vm_area_struct, vm_mm)); + DEFINE(VMA_VM_FLAGS, offsetof(struct vm_area_struct, vm_flags)); + BLANK(); + DEFINE(VM_EXEC, VM_EXEC); + BLANK(); + DEFINE(PAGE_SZ, PAGE_SIZE); + BLANK(); + DEFINE(SYS_ERROR0, 0x9f0000); + BLANK(); + DEFINE(SIZEOF_MACHINE_DESC, sizeof(struct machine_desc)); + DEFINE(MACHINFO_TYPE, offsetof(struct machine_desc, nr)); + DEFINE(MACHINFO_NAME, offsetof(struct machine_desc, name)); + BLANK(); + DEFINE(PROC_INFO_SZ, sizeof(struct proc_info_list)); + DEFINE(PROCINFO_INITFUNC, offsetof(struct proc_info_list, __cpu_flush)); + DEFINE(PROCINFO_MM_MMUFLAGS, offsetof(struct proc_info_list, __cpu_mm_mmu_flags)); + DEFINE(PROCINFO_IO_MMUFLAGS, offsetof(struct proc_info_list, __cpu_io_mmu_flags)); + BLANK(); +#ifdef MULTI_DABORT + DEFINE(PROCESSOR_DABT_FUNC, offsetof(struct processor, _data_abort)); +#endif +#ifdef MULTI_PABORT + DEFINE(PROCESSOR_PABT_FUNC, offsetof(struct processor, _prefetch_abort)); +#endif +#ifdef MULTI_CPU + DEFINE(CPU_SLEEP_SIZE, offsetof(struct processor, suspend_size)); + DEFINE(CPU_DO_SUSPEND, offsetof(struct processor, do_suspend)); + DEFINE(CPU_DO_RESUME, offsetof(struct processor, do_resume)); +#endif +#ifdef MULTI_CACHE + DEFINE(CACHE_FLUSH_KERN_ALL, offsetof(struct cpu_cache_fns, flush_kern_all)); +#endif +#ifdef CONFIG_ARM_CPU_SUSPEND + DEFINE(SLEEP_SAVE_SP_SZ, sizeof(struct sleep_save_sp)); + DEFINE(SLEEP_SAVE_SP_PHYS, offsetof(struct sleep_save_sp, save_ptr_stash_phys)); + DEFINE(SLEEP_SAVE_SP_VIRT, offsetof(struct sleep_save_sp, save_ptr_stash)); +#endif + DEFINE(ARM_SMCCC_QUIRK_ID_OFFS, offsetof(struct arm_smccc_quirk, id)); + DEFINE(ARM_SMCCC_QUIRK_STATE_OFFS, offsetof(struct arm_smccc_quirk, state)); + BLANK(); + DEFINE(DMA_BIDIRECTIONAL, DMA_BIDIRECTIONAL); + DEFINE(DMA_TO_DEVICE, DMA_TO_DEVICE); + DEFINE(DMA_FROM_DEVICE, DMA_FROM_DEVICE); + BLANK(); + DEFINE(CACHE_WRITEBACK_ORDER, __CACHE_WRITEBACK_ORDER); + DEFINE(CACHE_WRITEBACK_GRANULE, __CACHE_WRITEBACK_GRANULE); + BLANK(); +#ifdef CONFIG_VDSO + DEFINE(VDSO_DATA_SIZE, sizeof(union vdso_data_store)); +#endif + BLANK(); +#ifdef CONFIG_ARM_MPU + DEFINE(MPU_RNG_INFO_RNGS, offsetof(struct mpu_rgn_info, rgns)); + DEFINE(MPU_RNG_INFO_USED, offsetof(struct mpu_rgn_info, used)); + + DEFINE(MPU_RNG_SIZE, sizeof(struct mpu_rgn)); + DEFINE(MPU_RGN_DRBAR, offsetof(struct mpu_rgn, drbar)); + DEFINE(MPU_RGN_DRSR, offsetof(struct mpu_rgn, drsr)); + DEFINE(MPU_RGN_DRACR, offsetof(struct mpu_rgn, dracr)); + DEFINE(MPU_RGN_PRBAR, offsetof(struct mpu_rgn, prbar)); + DEFINE(MPU_RGN_PRLAR, offsetof(struct mpu_rgn, prlar)); +#endif + DEFINE(KEXEC_START_ADDR, offsetof(struct kexec_relocate_data, kexec_start_address)); + DEFINE(KEXEC_INDIR_PAGE, offsetof(struct kexec_relocate_data, kexec_indirection_page)); + DEFINE(KEXEC_MACH_TYPE, offsetof(struct kexec_relocate_data, kexec_mach_type)); + DEFINE(KEXEC_R2, offsetof(struct kexec_relocate_data, kexec_r2)); + return 0; +} diff --git a/arch/arm/kernel/atags.h b/arch/arm/kernel/atags.h new file mode 100644 index 000000000..f2819c25b --- /dev/null +++ b/arch/arm/kernel/atags.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +void convert_to_tag_list(struct tag *tags); + +#ifdef CONFIG_ATAGS +const struct machine_desc *setup_machine_tags(void *__atags_vaddr, + unsigned int machine_nr); +#else +static inline const struct machine_desc * __init __noreturn +setup_machine_tags(void *__atags_vaddr, unsigned int machine_nr) +{ + early_print("no ATAGS support: can't continue\n"); + while (true); + unreachable(); +} +#endif diff --git a/arch/arm/kernel/atags_compat.c b/arch/arm/kernel/atags_compat.c new file mode 100644 index 000000000..10da11c21 --- /dev/null +++ b/arch/arm/kernel/atags_compat.c @@ -0,0 +1,214 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/atags_compat.c + * + * Copyright (C) 2001 Russell King + * + * We keep the old params compatibility cruft in one place (here) + * so we don't end up with lots of mess around other places. + * + * NOTE: + * The old struct param_struct is deprecated, but it will be kept in + * the kernel for 5 years from now (2001). This will allow boot loaders + * to convert to the new struct tag way. + */ +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/init.h> + +#include <asm/setup.h> +#include <asm/mach-types.h> +#include <asm/page.h> + +#include <asm/mach/arch.h> + +#include "atags.h" + +/* + * Usage: + * - do not go blindly adding fields, add them at the end + * - when adding fields, don't rely on the address until + * a patch from me has been released + * - unused fields should be zero (for future expansion) + * - this structure is relatively short-lived - only + * guaranteed to contain useful data in setup_arch() + * + * This is the old deprecated way to pass parameters to the kernel + */ +struct param_struct { + union { + struct { + unsigned long page_size; /* 0 */ + unsigned long nr_pages; /* 4 */ + unsigned long ramdisk_size; /* 8 */ + unsigned long flags; /* 12 */ +#define FLAG_READONLY 1 +#define FLAG_RDLOAD 4 +#define FLAG_RDPROMPT 8 + unsigned long rootdev; /* 16 */ + unsigned long video_num_cols; /* 20 */ + unsigned long video_num_rows; /* 24 */ + unsigned long video_x; /* 28 */ + unsigned long video_y; /* 32 */ + unsigned long memc_control_reg; /* 36 */ + unsigned char sounddefault; /* 40 */ + unsigned char adfsdrives; /* 41 */ + unsigned char bytes_per_char_h; /* 42 */ + unsigned char bytes_per_char_v; /* 43 */ + unsigned long pages_in_bank[4]; /* 44 */ + unsigned long pages_in_vram; /* 60 */ + unsigned long initrd_start; /* 64 */ + unsigned long initrd_size; /* 68 */ + unsigned long rd_start; /* 72 */ + unsigned long system_rev; /* 76 */ + unsigned long system_serial_low; /* 80 */ + unsigned long system_serial_high; /* 84 */ + unsigned long mem_fclk_21285; /* 88 */ + } s; + char unused[256]; + } u1; + union { + char paths[8][128]; + struct { + unsigned long magic; + char n[1024 - sizeof(unsigned long)]; + } s; + } u2; + char commandline[COMMAND_LINE_SIZE]; +}; + +static struct tag * __init memtag(struct tag *tag, unsigned long start, unsigned long size) +{ + tag = tag_next(tag); + tag->hdr.tag = ATAG_MEM; + tag->hdr.size = tag_size(tag_mem32); + tag->u.mem.size = size; + tag->u.mem.start = start; + + return tag; +} + +static void __init build_tag_list(struct param_struct *params, void *taglist) +{ + struct tag *tag = taglist; + + if (params->u1.s.page_size != PAGE_SIZE) { + pr_warn("Warning: bad configuration page, trying to continue\n"); + return; + } + + printk(KERN_DEBUG "Converting old-style param struct to taglist\n"); + +#ifdef CONFIG_ARCH_NETWINDER + if (params->u1.s.nr_pages != 0x02000 && + params->u1.s.nr_pages != 0x04000 && + params->u1.s.nr_pages != 0x08000 && + params->u1.s.nr_pages != 0x10000) { + pr_warn("Warning: bad NeTTrom parameters detected, using defaults\n"); + + params->u1.s.nr_pages = 0x1000; /* 16MB */ + params->u1.s.ramdisk_size = 0; + params->u1.s.flags = FLAG_READONLY; + params->u1.s.initrd_start = 0; + params->u1.s.initrd_size = 0; + params->u1.s.rd_start = 0; + } +#endif + + tag->hdr.tag = ATAG_CORE; + tag->hdr.size = tag_size(tag_core); + tag->u.core.flags = params->u1.s.flags & FLAG_READONLY; + tag->u.core.pagesize = params->u1.s.page_size; + tag->u.core.rootdev = params->u1.s.rootdev; + + tag = tag_next(tag); + tag->hdr.tag = ATAG_RAMDISK; + tag->hdr.size = tag_size(tag_ramdisk); + tag->u.ramdisk.flags = (params->u1.s.flags & FLAG_RDLOAD ? 1 : 0) | + (params->u1.s.flags & FLAG_RDPROMPT ? 2 : 0); + tag->u.ramdisk.size = params->u1.s.ramdisk_size; + tag->u.ramdisk.start = params->u1.s.rd_start; + + tag = tag_next(tag); + tag->hdr.tag = ATAG_INITRD; + tag->hdr.size = tag_size(tag_initrd); + tag->u.initrd.start = params->u1.s.initrd_start; + tag->u.initrd.size = params->u1.s.initrd_size; + + tag = tag_next(tag); + tag->hdr.tag = ATAG_SERIAL; + tag->hdr.size = tag_size(tag_serialnr); + tag->u.serialnr.low = params->u1.s.system_serial_low; + tag->u.serialnr.high = params->u1.s.system_serial_high; + + tag = tag_next(tag); + tag->hdr.tag = ATAG_REVISION; + tag->hdr.size = tag_size(tag_revision); + tag->u.revision.rev = params->u1.s.system_rev; + +#ifdef CONFIG_ARCH_ACORN + if (machine_is_riscpc()) { + int i; + for (i = 0; i < 4; i++) + tag = memtag(tag, PHYS_OFFSET + (i << 26), + params->u1.s.pages_in_bank[i] * PAGE_SIZE); + } else +#endif + tag = memtag(tag, PHYS_OFFSET, params->u1.s.nr_pages * PAGE_SIZE); + +#ifdef CONFIG_FOOTBRIDGE + if (params->u1.s.mem_fclk_21285) { + tag = tag_next(tag); + tag->hdr.tag = ATAG_MEMCLK; + tag->hdr.size = tag_size(tag_memclk); + tag->u.memclk.fmemclk = params->u1.s.mem_fclk_21285; + } +#endif + +#ifdef CONFIG_ARCH_EBSA285 + if (machine_is_ebsa285()) { + tag = tag_next(tag); + tag->hdr.tag = ATAG_VIDEOTEXT; + tag->hdr.size = tag_size(tag_videotext); + tag->u.videotext.x = params->u1.s.video_x; + tag->u.videotext.y = params->u1.s.video_y; + tag->u.videotext.video_page = 0; + tag->u.videotext.video_mode = 0; + tag->u.videotext.video_cols = params->u1.s.video_num_cols; + tag->u.videotext.video_ega_bx = 0; + tag->u.videotext.video_lines = params->u1.s.video_num_rows; + tag->u.videotext.video_isvga = 1; + tag->u.videotext.video_points = 8; + } +#endif + +#ifdef CONFIG_ARCH_ACORN + tag = tag_next(tag); + tag->hdr.tag = ATAG_ACORN; + tag->hdr.size = tag_size(tag_acorn); + tag->u.acorn.memc_control_reg = params->u1.s.memc_control_reg; + tag->u.acorn.vram_pages = params->u1.s.pages_in_vram; + tag->u.acorn.sounddefault = params->u1.s.sounddefault; + tag->u.acorn.adfsdrives = params->u1.s.adfsdrives; +#endif + + tag = tag_next(tag); + tag->hdr.tag = ATAG_CMDLINE; + tag->hdr.size = (strlen(params->commandline) + 3 + + sizeof(struct tag_header)) >> 2; + strcpy(tag->u.cmdline.cmdline, params->commandline); + + tag = tag_next(tag); + tag->hdr.tag = ATAG_NONE; + tag->hdr.size = 0; + + memmove(params, taglist, ((int)tag) - ((int)taglist) + + sizeof(struct tag_header)); +} + +void __init convert_to_tag_list(struct tag *tags) +{ + struct param_struct *params = (struct param_struct *)tags; + build_tag_list(params, ¶ms->u2); +} diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c new file mode 100644 index 000000000..373b61f9a --- /dev/null +++ b/arch/arm/kernel/atags_parse.c @@ -0,0 +1,230 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Tag parsing. + * + * Copyright (C) 1995-2001 Russell King + */ + +/* + * This is the traditional way of passing data to the kernel at boot time. Rather + * than passing a fixed inflexible structure to the kernel, we pass a list + * of variable-sized tags to the kernel. The first tag must be a ATAG_CORE + * tag for the list to be recognised (to distinguish the tagged list from + * a param_struct). The list is terminated with a zero-length tag (this tag + * is not parsed in any way). + */ + +#include <linux/init.h> +#include <linux/initrd.h> +#include <linux/kernel.h> +#include <linux/fs.h> +#include <linux/root_dev.h> +#include <linux/screen_info.h> +#include <linux/memblock.h> +#include <uapi/linux/mount.h> + +#include <asm/setup.h> +#include <asm/system_info.h> +#include <asm/page.h> +#include <asm/mach/arch.h> + +#include "atags.h" + +static char default_command_line[COMMAND_LINE_SIZE] __initdata = CONFIG_CMDLINE; + +#ifndef MEM_SIZE +#define MEM_SIZE (16*1024*1024) +#endif + +static struct { + struct tag_header hdr1; + struct tag_core core; + struct tag_header hdr2; + struct tag_mem32 mem; + struct tag_header hdr3; +} default_tags __initdata = { + { tag_size(tag_core), ATAG_CORE }, + { 1, PAGE_SIZE, 0xff }, + { tag_size(tag_mem32), ATAG_MEM }, + { MEM_SIZE }, + { 0, ATAG_NONE } +}; + +static int __init parse_tag_core(const struct tag *tag) +{ + if (tag->hdr.size > 2) { + if ((tag->u.core.flags & 1) == 0) + root_mountflags &= ~MS_RDONLY; + ROOT_DEV = old_decode_dev(tag->u.core.rootdev); + } + return 0; +} + +__tagtable(ATAG_CORE, parse_tag_core); + +static int __init parse_tag_mem32(const struct tag *tag) +{ + return arm_add_memory(tag->u.mem.start, tag->u.mem.size); +} + +__tagtable(ATAG_MEM, parse_tag_mem32); + +#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE) +static int __init parse_tag_videotext(const struct tag *tag) +{ + screen_info.orig_x = tag->u.videotext.x; + screen_info.orig_y = tag->u.videotext.y; + screen_info.orig_video_page = tag->u.videotext.video_page; + screen_info.orig_video_mode = tag->u.videotext.video_mode; + screen_info.orig_video_cols = tag->u.videotext.video_cols; + screen_info.orig_video_ega_bx = tag->u.videotext.video_ega_bx; + screen_info.orig_video_lines = tag->u.videotext.video_lines; + screen_info.orig_video_isVGA = tag->u.videotext.video_isvga; + screen_info.orig_video_points = tag->u.videotext.video_points; + return 0; +} + +__tagtable(ATAG_VIDEOTEXT, parse_tag_videotext); +#endif + +#ifdef CONFIG_BLK_DEV_RAM +static int __init parse_tag_ramdisk(const struct tag *tag) +{ + rd_image_start = tag->u.ramdisk.start; + + if (tag->u.ramdisk.size) + rd_size = tag->u.ramdisk.size; + + return 0; +} + +__tagtable(ATAG_RAMDISK, parse_tag_ramdisk); +#endif + +static int __init parse_tag_serialnr(const struct tag *tag) +{ + system_serial_low = tag->u.serialnr.low; + system_serial_high = tag->u.serialnr.high; + return 0; +} + +__tagtable(ATAG_SERIAL, parse_tag_serialnr); + +static int __init parse_tag_revision(const struct tag *tag) +{ + system_rev = tag->u.revision.rev; + return 0; +} + +__tagtable(ATAG_REVISION, parse_tag_revision); + +static int __init parse_tag_cmdline(const struct tag *tag) +{ +#if defined(CONFIG_CMDLINE_EXTEND) + strlcat(default_command_line, " ", COMMAND_LINE_SIZE); + strlcat(default_command_line, tag->u.cmdline.cmdline, + COMMAND_LINE_SIZE); +#elif defined(CONFIG_CMDLINE_FORCE) + pr_warn("Ignoring tag cmdline (using the default kernel command line)\n"); +#else + strlcpy(default_command_line, tag->u.cmdline.cmdline, + COMMAND_LINE_SIZE); +#endif + return 0; +} + +__tagtable(ATAG_CMDLINE, parse_tag_cmdline); + +/* + * Scan the tag table for this tag, and call its parse function. + * The tag table is built by the linker from all the __tagtable + * declarations. + */ +static int __init parse_tag(const struct tag *tag) +{ + extern struct tagtable __tagtable_begin, __tagtable_end; + struct tagtable *t; + + for (t = &__tagtable_begin; t < &__tagtable_end; t++) + if (tag->hdr.tag == t->tag) { + t->parse(tag); + break; + } + + return t < &__tagtable_end; +} + +/* + * Parse all tags in the list, checking both the global and architecture + * specific tag tables. + */ +static void __init parse_tags(const struct tag *t) +{ + for (; t->hdr.size; t = tag_next(t)) + if (!parse_tag(t)) + pr_warn("Ignoring unrecognised tag 0x%08x\n", + t->hdr.tag); +} + +static void __init squash_mem_tags(struct tag *tag) +{ + for (; tag->hdr.size; tag = tag_next(tag)) + if (tag->hdr.tag == ATAG_MEM) + tag->hdr.tag = ATAG_NONE; +} + +const struct machine_desc * __init +setup_machine_tags(void *atags_vaddr, unsigned int machine_nr) +{ + struct tag *tags = (struct tag *)&default_tags; + const struct machine_desc *mdesc = NULL, *p; + char *from = default_command_line; + + default_tags.mem.start = PHYS_OFFSET; + + /* + * locate machine in the list of supported machines. + */ + for_each_machine_desc(p) + if (machine_nr == p->nr) { + pr_info("Machine: %s\n", p->name); + mdesc = p; + break; + } + + if (!mdesc) + return NULL; + + if (atags_vaddr) + tags = atags_vaddr; + else if (mdesc->atag_offset) + tags = (void *)(PAGE_OFFSET + mdesc->atag_offset); + +#if defined(CONFIG_DEPRECATED_PARAM_STRUCT) + /* + * If we have the old style parameters, convert them to + * a tag list. + */ + if (tags->hdr.tag != ATAG_CORE) + convert_to_tag_list(tags); +#endif + if (tags->hdr.tag != ATAG_CORE) { + early_print("Warning: Neither atags nor dtb found\n"); + tags = (struct tag *)&default_tags; + } + + if (mdesc->fixup) + mdesc->fixup(tags, &from); + + if (tags->hdr.tag == ATAG_CORE) { + if (memblock_phys_mem_size()) + squash_mem_tags(tags); + save_atags(tags); + parse_tags(tags); + } + + /* parse_early_param needs a boot_command_line */ + strlcpy(boot_command_line, from, COMMAND_LINE_SIZE); + + return mdesc; +} diff --git a/arch/arm/kernel/atags_proc.c b/arch/arm/kernel/atags_proc.c new file mode 100644 index 000000000..3ec2afe78 --- /dev/null +++ b/arch/arm/kernel/atags_proc.c @@ -0,0 +1,76 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/slab.h> +#include <linux/proc_fs.h> +#include <asm/setup.h> +#include <asm/types.h> +#include <asm/page.h> + +struct buffer { + size_t size; + char data[]; +}; + +static ssize_t atags_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct buffer *b = pde_data(file_inode(file)); + return simple_read_from_buffer(buf, count, ppos, b->data, b->size); +} + +static const struct proc_ops atags_proc_ops = { + .proc_read = atags_read, + .proc_lseek = default_llseek, +}; + +#define BOOT_PARAMS_SIZE 1536 +static char __initdata atags_copy[BOOT_PARAMS_SIZE]; + +void __init save_atags(const struct tag *tags) +{ + memcpy(atags_copy, tags, sizeof(atags_copy)); +} + +static int __init init_atags_procfs(void) +{ + /* + * This cannot go into save_atags() because kmalloc and proc don't work + * yet when it is called. + */ + struct proc_dir_entry *tags_entry; + struct tag *tag = (struct tag *)atags_copy; + struct buffer *b; + size_t size; + + if (tag->hdr.tag != ATAG_CORE) { + pr_info("No ATAGs?\n"); + return -EINVAL; + } + + for (; tag->hdr.size; tag = tag_next(tag)) + ; + + /* include the terminating ATAG_NONE */ + size = (char *)tag - atags_copy + sizeof(struct tag_header); + + WARN_ON(tag->hdr.tag != ATAG_NONE); + + b = kmalloc(sizeof(*b) + size, GFP_KERNEL); + if (!b) + goto nomem; + + b->size = size; + memcpy(b->data, atags_copy, size); + + tags_entry = proc_create_data("atags", 0400, NULL, &atags_proc_ops, b); + if (!tags_entry) + goto nomem; + + return 0; + +nomem: + kfree(b); + pr_err("Exporting ATAGs: not enough memory\n"); + + return -ENOMEM; +} +arch_initcall(init_atags_procfs); diff --git a/arch/arm/kernel/bios32.c b/arch/arm/kernel/bios32.c new file mode 100644 index 000000000..e7ef2b5be --- /dev/null +++ b/arch/arm/kernel/bios32.c @@ -0,0 +1,594 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/arch/arm/kernel/bios32.c + * + * PCI bios-type initialisation for PCI machines + * + * Bits taken from various places. + */ +#include <linux/export.h> +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/io.h> + +#include <asm/mach-types.h> +#include <asm/mach/map.h> +#include <asm/mach/pci.h> + +static int debug_pci; + +/* + * We can't use pci_get_device() here since we are + * called from interrupt context. + */ +static void pcibios_bus_report_status(struct pci_bus *bus, u_int status_mask, int warn) +{ + struct pci_dev *dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + u16 status; + + /* + * ignore host bridge - we handle + * that separately + */ + if (dev->bus->number == 0 && dev->devfn == 0) + continue; + + pci_read_config_word(dev, PCI_STATUS, &status); + if (status == 0xffff) + continue; + + if ((status & status_mask) == 0) + continue; + + /* clear the status errors */ + pci_write_config_word(dev, PCI_STATUS, status & status_mask); + + if (warn) + printk("(%s: %04X) ", pci_name(dev), status); + } + + list_for_each_entry(dev, &bus->devices, bus_list) + if (dev->subordinate) + pcibios_bus_report_status(dev->subordinate, status_mask, warn); +} + +void pcibios_report_status(u_int status_mask, int warn) +{ + struct pci_bus *bus; + + list_for_each_entry(bus, &pci_root_buses, node) + pcibios_bus_report_status(bus, status_mask, warn); +} + +/* + * We don't use this to fix the device, but initialisation of it. + * It's not the correct use for this, but it works. + * Note that the arbiter/ISA bridge appears to be buggy, specifically in + * the following area: + * 1. park on CPU + * 2. ISA bridge ping-pong + * 3. ISA bridge master handling of target RETRY + * + * Bug 3 is responsible for the sound DMA grinding to a halt. We now + * live with bug 2. + */ +static void pci_fixup_83c553(struct pci_dev *dev) +{ + /* + * Set memory region to start at address 0, and enable IO + */ + pci_write_config_dword(dev, PCI_BASE_ADDRESS_0, PCI_BASE_ADDRESS_SPACE_MEMORY); + pci_write_config_word(dev, PCI_COMMAND, PCI_COMMAND_IO); + + dev->resource[0].end -= dev->resource[0].start; + dev->resource[0].start = 0; + + /* + * All memory requests from ISA to be channelled to PCI + */ + pci_write_config_byte(dev, 0x48, 0xff); + + /* + * Enable ping-pong on bus master to ISA bridge transactions. + * This improves the sound DMA substantially. The fixed + * priority arbiter also helps (see below). + */ + pci_write_config_byte(dev, 0x42, 0x01); + + /* + * Enable PCI retry + */ + pci_write_config_byte(dev, 0x40, 0x22); + + /* + * We used to set the arbiter to "park on last master" (bit + * 1 set), but unfortunately the CyberPro does not park the + * bus. We must therefore park on CPU. Unfortunately, this + * may trigger yet another bug in the 553. + */ + pci_write_config_byte(dev, 0x83, 0x02); + + /* + * Make the ISA DMA request lowest priority, and disable + * rotating priorities completely. + */ + pci_write_config_byte(dev, 0x80, 0x11); + pci_write_config_byte(dev, 0x81, 0x00); + + /* + * Route INTA input to IRQ 11, and set IRQ11 to be level + * sensitive. + */ + pci_write_config_word(dev, 0x44, 0xb000); + outb(0x08, 0x4d1); +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_WINBOND, PCI_DEVICE_ID_WINBOND_83C553, pci_fixup_83c553); + +static void pci_fixup_unassign(struct pci_dev *dev) +{ + dev->resource[0].end -= dev->resource[0].start; + dev->resource[0].start = 0; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_WINBOND2, PCI_DEVICE_ID_WINBOND2_89C940F, pci_fixup_unassign); + +/* + * Prevent the PCI layer from seeing the resources allocated to this device + * if it is the host bridge by marking it as such. These resources are of + * no consequence to the PCI layer (they are handled elsewhere). + */ +static void pci_fixup_dec21285(struct pci_dev *dev) +{ + int i; + + if (dev->devfn == 0) { + dev->class &= 0xff; + dev->class |= PCI_CLASS_BRIDGE_HOST << 8; + for (i = 0; i < PCI_NUM_RESOURCES; i++) { + dev->resource[i].start = 0; + dev->resource[i].end = 0; + dev->resource[i].flags = 0; + } + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_DEC, PCI_DEVICE_ID_DEC_21285, pci_fixup_dec21285); + +/* + * PCI IDE controllers use non-standard I/O port decoding, respect it. + */ +static void pci_fixup_ide_bases(struct pci_dev *dev) +{ + struct resource *r; + int i; + + if ((dev->class >> 8) != PCI_CLASS_STORAGE_IDE) + return; + + for (i = 0; i < PCI_NUM_RESOURCES; i++) { + r = dev->resource + i; + if ((r->start & ~0x80) == 0x374) { + r->start |= 2; + r->end = r->start; + } + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_ANY_ID, PCI_ANY_ID, pci_fixup_ide_bases); + +/* + * Put the DEC21142 to sleep + */ +static void pci_fixup_dec21142(struct pci_dev *dev) +{ + pci_write_config_dword(dev, 0x40, 0x80000000); +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_DEC, PCI_DEVICE_ID_DEC_21142, pci_fixup_dec21142); + +/* + * The CY82C693 needs some rather major fixups to ensure that it does + * the right thing. Idea from the Alpha people, with a few additions. + * + * We ensure that the IDE base registers are set to 1f0/3f4 for the + * primary bus, and 170/374 for the secondary bus. Also, hide them + * from the PCI subsystem view as well so we won't try to perform + * our own auto-configuration on them. + * + * In addition, we ensure that the PCI IDE interrupts are routed to + * IRQ 14 and IRQ 15 respectively. + * + * The above gets us to a point where the IDE on this device is + * functional. However, The CY82C693U _does not work_ in bus + * master mode without locking the PCI bus solid. + */ +static void pci_fixup_cy82c693(struct pci_dev *dev) +{ + if ((dev->class >> 8) == PCI_CLASS_STORAGE_IDE) { + u32 base0, base1; + + if (dev->class & 0x80) { /* primary */ + base0 = 0x1f0; + base1 = 0x3f4; + } else { /* secondary */ + base0 = 0x170; + base1 = 0x374; + } + + pci_write_config_dword(dev, PCI_BASE_ADDRESS_0, + base0 | PCI_BASE_ADDRESS_SPACE_IO); + pci_write_config_dword(dev, PCI_BASE_ADDRESS_1, + base1 | PCI_BASE_ADDRESS_SPACE_IO); + + dev->resource[0].start = 0; + dev->resource[0].end = 0; + dev->resource[0].flags = 0; + + dev->resource[1].start = 0; + dev->resource[1].end = 0; + dev->resource[1].flags = 0; + } else if (PCI_FUNC(dev->devfn) == 0) { + /* + * Setup IDE IRQ routing. + */ + pci_write_config_byte(dev, 0x4b, 14); + pci_write_config_byte(dev, 0x4c, 15); + + /* + * Disable FREQACK handshake, enable USB. + */ + pci_write_config_byte(dev, 0x4d, 0x41); + + /* + * Enable PCI retry, and PCI post-write buffer. + */ + pci_write_config_byte(dev, 0x44, 0x17); + + /* + * Enable ISA master and DMA post write buffering. + */ + pci_write_config_byte(dev, 0x45, 0x03); + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CONTAQ, PCI_DEVICE_ID_CONTAQ_82C693, pci_fixup_cy82c693); + +/* + * If the bus contains any of these devices, then we must not turn on + * parity checking of any kind. Currently this is CyberPro 20x0 only. + */ +static inline int pdev_bad_for_parity(struct pci_dev *dev) +{ + return ((dev->vendor == PCI_VENDOR_ID_INTERG && + (dev->device == PCI_DEVICE_ID_INTERG_2000 || + dev->device == PCI_DEVICE_ID_INTERG_2010)) || + (dev->vendor == PCI_VENDOR_ID_ITE && + dev->device == PCI_DEVICE_ID_ITE_8152)); + +} + +/* + * pcibios_fixup_bus - Called after each bus is probed, + * but before its children are examined. + */ +void pcibios_fixup_bus(struct pci_bus *bus) +{ + struct pci_dev *dev; + u16 features = PCI_COMMAND_SERR | PCI_COMMAND_PARITY | PCI_COMMAND_FAST_BACK; + + /* + * Walk the devices on this bus, working out what we can + * and can't support. + */ + list_for_each_entry(dev, &bus->devices, bus_list) { + u16 status; + + pci_read_config_word(dev, PCI_STATUS, &status); + + /* + * If any device on this bus does not support fast back + * to back transfers, then the bus as a whole is not able + * to support them. Having fast back to back transfers + * on saves us one PCI cycle per transaction. + */ + if (!(status & PCI_STATUS_FAST_BACK)) + features &= ~PCI_COMMAND_FAST_BACK; + + if (pdev_bad_for_parity(dev)) + features &= ~(PCI_COMMAND_SERR | PCI_COMMAND_PARITY); + + switch (dev->class >> 8) { + case PCI_CLASS_BRIDGE_PCI: + pci_read_config_word(dev, PCI_BRIDGE_CONTROL, &status); + status |= PCI_BRIDGE_CTL_PARITY|PCI_BRIDGE_CTL_MASTER_ABORT; + status &= ~(PCI_BRIDGE_CTL_BUS_RESET|PCI_BRIDGE_CTL_FAST_BACK); + pci_write_config_word(dev, PCI_BRIDGE_CONTROL, status); + break; + + case PCI_CLASS_BRIDGE_CARDBUS: + pci_read_config_word(dev, PCI_CB_BRIDGE_CONTROL, &status); + status |= PCI_CB_BRIDGE_CTL_PARITY|PCI_CB_BRIDGE_CTL_MASTER_ABORT; + pci_write_config_word(dev, PCI_CB_BRIDGE_CONTROL, status); + break; + } + } + + /* + * Now walk the devices again, this time setting them up. + */ + list_for_each_entry(dev, &bus->devices, bus_list) { + u16 cmd; + + pci_read_config_word(dev, PCI_COMMAND, &cmd); + cmd |= features; + pci_write_config_word(dev, PCI_COMMAND, cmd); + + pci_write_config_byte(dev, PCI_CACHE_LINE_SIZE, + L1_CACHE_BYTES >> 2); + } + + /* + * Propagate the flags to the PCI bridge. + */ + if (bus->self && bus->self->hdr_type == PCI_HEADER_TYPE_BRIDGE) { + if (features & PCI_COMMAND_FAST_BACK) + bus->bridge_ctl |= PCI_BRIDGE_CTL_FAST_BACK; + if (features & PCI_COMMAND_PARITY) + bus->bridge_ctl |= PCI_BRIDGE_CTL_PARITY; + } + + /* + * Report what we did for this bus + */ + pr_info("PCI: bus%d: Fast back to back transfers %sabled\n", + bus->number, (features & PCI_COMMAND_FAST_BACK) ? "en" : "dis"); +} +EXPORT_SYMBOL(pcibios_fixup_bus); + +/* + * Swizzle the device pin each time we cross a bridge. If a platform does + * not provide a swizzle function, we perform the standard PCI swizzling. + * + * The default swizzling walks up the bus tree one level at a time, applying + * the standard swizzle function at each step, stopping when it finds the PCI + * root bus. This will return the slot number of the bridge device on the + * root bus and the interrupt pin on that device which should correspond + * with the downstream device interrupt. + * + * Platforms may override this, in which case the slot and pin returned + * depend entirely on the platform code. However, please note that the + * PCI standard swizzle is implemented on plug-in cards and Cardbus based + * PCI extenders, so it can not be ignored. + */ +static u8 pcibios_swizzle(struct pci_dev *dev, u8 *pin) +{ + struct pci_sys_data *sys = dev->sysdata; + int slot, oldpin = *pin; + + if (sys->swizzle) + slot = sys->swizzle(dev, pin); + else + slot = pci_common_swizzle(dev, pin); + + if (debug_pci) + printk("PCI: %s swizzling pin %d => pin %d slot %d\n", + pci_name(dev), oldpin, *pin, slot); + + return slot; +} + +/* + * Map a slot/pin to an IRQ. + */ +static int pcibios_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +{ + struct pci_sys_data *sys = dev->sysdata; + int irq = -1; + + if (sys->map_irq) + irq = sys->map_irq(dev, slot, pin); + + if (debug_pci) + printk("PCI: %s mapping slot %d pin %d => irq %d\n", + pci_name(dev), slot, pin, irq); + + return irq; +} + +static int pcibios_init_resource(int busnr, struct pci_sys_data *sys) +{ + int ret; + struct resource_entry *window; + + if (list_empty(&sys->resources)) { + pci_add_resource_offset(&sys->resources, + &iomem_resource, sys->mem_offset); + } + + resource_list_for_each_entry(window, &sys->resources) + if (resource_type(window->res) == IORESOURCE_IO) + return 0; + + sys->io_res.start = (busnr * SZ_64K) ? : pcibios_min_io; + sys->io_res.end = (busnr + 1) * SZ_64K - 1; + sys->io_res.flags = IORESOURCE_IO; + sys->io_res.name = sys->io_res_name; + sprintf(sys->io_res_name, "PCI%d I/O", busnr); + + ret = request_resource(&ioport_resource, &sys->io_res); + if (ret) { + pr_err("PCI: unable to allocate I/O port region (%d)\n", ret); + return ret; + } + pci_add_resource_offset(&sys->resources, &sys->io_res, + sys->io_offset); + + return 0; +} + +static void pcibios_init_hw(struct device *parent, struct hw_pci *hw, + struct list_head *head) +{ + struct pci_sys_data *sys = NULL; + int ret; + int nr, busnr; + + for (nr = busnr = 0; nr < hw->nr_controllers; nr++) { + struct pci_host_bridge *bridge; + + bridge = pci_alloc_host_bridge(sizeof(struct pci_sys_data)); + if (WARN(!bridge, "PCI: unable to allocate bridge!")) + break; + + sys = pci_host_bridge_priv(bridge); + + sys->busnr = busnr; + sys->swizzle = hw->swizzle; + sys->map_irq = hw->map_irq; + INIT_LIST_HEAD(&sys->resources); + + if (hw->private_data) + sys->private_data = hw->private_data[nr]; + + ret = hw->setup(nr, sys); + + if (ret > 0) { + + ret = pcibios_init_resource(nr, sys); + if (ret) { + pci_free_host_bridge(bridge); + break; + } + + bridge->map_irq = pcibios_map_irq; + bridge->swizzle_irq = pcibios_swizzle; + + if (hw->scan) + ret = hw->scan(nr, bridge); + else { + list_splice_init(&sys->resources, + &bridge->windows); + bridge->dev.parent = parent; + bridge->sysdata = sys; + bridge->busnr = sys->busnr; + bridge->ops = hw->ops; + + ret = pci_scan_root_bus_bridge(bridge); + } + + if (WARN(ret < 0, "PCI: unable to scan bus!")) { + pci_free_host_bridge(bridge); + break; + } + + sys->bus = bridge->bus; + + busnr = sys->bus->busn_res.end + 1; + + list_add(&sys->node, head); + } else { + pci_free_host_bridge(bridge); + if (ret < 0) + break; + } + } +} + +void pci_common_init_dev(struct device *parent, struct hw_pci *hw) +{ + struct pci_sys_data *sys; + LIST_HEAD(head); + + pci_add_flags(PCI_REASSIGN_ALL_BUS); + if (hw->preinit) + hw->preinit(); + pcibios_init_hw(parent, hw, &head); + if (hw->postinit) + hw->postinit(); + + list_for_each_entry(sys, &head, node) { + struct pci_bus *bus = sys->bus; + + /* + * We insert PCI resources into the iomem_resource and + * ioport_resource trees in either pci_bus_claim_resources() + * or pci_bus_assign_resources(). + */ + if (pci_has_flag(PCI_PROBE_ONLY)) { + pci_bus_claim_resources(bus); + } else { + struct pci_bus *child; + + pci_bus_size_bridges(bus); + pci_bus_assign_resources(bus); + + list_for_each_entry(child, &bus->children, node) + pcie_bus_configure_settings(child); + } + + pci_bus_add_devices(bus); + } +} + +#ifndef CONFIG_PCI_HOST_ITE8152 +void pcibios_set_master(struct pci_dev *dev) +{ + /* No special bus mastering setup handling */ +} +#endif + +char * __init pcibios_setup(char *str) +{ + if (!strcmp(str, "debug")) { + debug_pci = 1; + return NULL; + } + return str; +} + +/* + * From arch/i386/kernel/pci-i386.c: + * + * We need to avoid collisions with `mirrored' VGA ports + * and other strange ISA hardware, so we always want the + * addresses to be allocated in the 0x000-0x0ff region + * modulo 0x400. + * + * Why? Because some silly external IO cards only decode + * the low 10 bits of the IO address. The 0x00-0xff region + * is reserved for motherboard devices that decode all 16 + * bits, so it's ok to allocate at, say, 0x2800-0x28ff, + * but we want to try to avoid allocating at 0x2900-0x2bff + * which might be mirrored at 0x0100-0x03ff.. + */ +resource_size_t pcibios_align_resource(void *data, const struct resource *res, + resource_size_t size, resource_size_t align) +{ + struct pci_dev *dev = data; + resource_size_t start = res->start; + struct pci_host_bridge *host_bridge; + + if (res->flags & IORESOURCE_IO && start & 0x300) + start = (start + 0x3ff) & ~0x3ff; + + start = (start + align - 1) & ~(align - 1); + + host_bridge = pci_find_host_bridge(dev->bus); + + if (host_bridge->align_resource) + return host_bridge->align_resource(dev, res, + start, size, align); + + return start; +} + +void __init pci_map_io_early(unsigned long pfn) +{ + struct map_desc pci_io_desc = { + .virtual = PCI_IO_VIRT_BASE, + .type = MT_DEVICE, + .length = SZ_64K, + }; + + pci_io_desc.pfn = pfn; + iotable_init(&pci_io_desc, 1); +} diff --git a/arch/arm/kernel/bugs.c b/arch/arm/kernel/bugs.c new file mode 100644 index 000000000..087bce6ec --- /dev/null +++ b/arch/arm/kernel/bugs.c @@ -0,0 +1,19 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/init.h> +#include <linux/cpu.h> +#include <asm/bugs.h> +#include <asm/proc-fns.h> + +void check_other_bugs(void) +{ +#ifdef MULTI_CPU + if (cpu_check_bugs) + cpu_check_bugs(); +#endif +} + +void __init arch_cpu_finalize_init(void) +{ + check_writebuffer_bugs(); + check_other_bugs(); +} diff --git a/arch/arm/kernel/cpuidle.c b/arch/arm/kernel/cpuidle.c new file mode 100644 index 000000000..e1684623e --- /dev/null +++ b/arch/arm/kernel/cpuidle.c @@ -0,0 +1,149 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * Copyright 2012 Linaro Ltd. + */ + +#include <linux/cpuidle.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <asm/cpuidle.h> + +extern struct of_cpuidle_method __cpuidle_method_of_table[]; + +static const struct of_cpuidle_method __cpuidle_method_of_table_sentinel + __used __section("__cpuidle_method_of_table_end"); + +static struct cpuidle_ops cpuidle_ops[NR_CPUS] __ro_after_init; + +/** + * arm_cpuidle_simple_enter() - a wrapper to cpu_do_idle() + * @dev: not used + * @drv: not used + * @index: not used + * + * A trivial wrapper to allow the cpu_do_idle function to be assigned as a + * cpuidle callback by matching the function signature. + * + * Returns the index passed as parameter + */ +int arm_cpuidle_simple_enter(struct cpuidle_device *dev, + struct cpuidle_driver *drv, int index) +{ + cpu_do_idle(); + + return index; +} + +/** + * arm_cpuidle_suspend() - function to enter low power idle states + * @index: an integer used as an identifier for the low level PM callbacks + * + * This function calls the underlying arch specific low level PM code as + * registered at the init time. + * + * Returns the result of the suspend callback. + */ +int arm_cpuidle_suspend(int index) +{ + int cpu = smp_processor_id(); + + return cpuidle_ops[cpu].suspend(index); +} + +/** + * arm_cpuidle_get_ops() - find a registered cpuidle_ops by name + * @method: the method name + * + * Search in the __cpuidle_method_of_table array the cpuidle ops matching the + * method name. + * + * Returns a struct cpuidle_ops pointer, NULL if not found. + */ +static const struct cpuidle_ops *__init arm_cpuidle_get_ops(const char *method) +{ + struct of_cpuidle_method *m = __cpuidle_method_of_table; + + for (; m->method; m++) + if (!strcmp(m->method, method)) + return m->ops; + + return NULL; +} + +/** + * arm_cpuidle_read_ops() - Initialize the cpuidle ops with the device tree + * @dn: a pointer to a struct device node corresponding to a cpu node + * @cpu: the cpu identifier + * + * Get the method name defined in the 'enable-method' property, retrieve the + * associated cpuidle_ops and do a struct copy. This copy is needed because all + * cpuidle_ops are tagged __initconst and will be unloaded after the init + * process. + * + * Return 0 on sucess, -ENOENT if no 'enable-method' is defined, -EOPNOTSUPP if + * no cpuidle_ops is registered for the 'enable-method', or if either init or + * suspend callback isn't defined. + */ +static int __init arm_cpuidle_read_ops(struct device_node *dn, int cpu) +{ + const char *enable_method; + const struct cpuidle_ops *ops; + + enable_method = of_get_property(dn, "enable-method", NULL); + if (!enable_method) + return -ENOENT; + + ops = arm_cpuidle_get_ops(enable_method); + if (!ops) { + pr_warn("%pOF: unsupported enable-method property: %s\n", + dn, enable_method); + return -EOPNOTSUPP; + } + + if (!ops->init || !ops->suspend) { + pr_warn("cpuidle_ops '%s': no init or suspend callback\n", + enable_method); + return -EOPNOTSUPP; + } + + cpuidle_ops[cpu] = *ops; /* structure copy */ + + pr_notice("cpuidle: enable-method property '%s'" + " found operations\n", enable_method); + + return 0; +} + +/** + * arm_cpuidle_init() - Initialize cpuidle_ops for a specific cpu + * @cpu: the cpu to be initialized + * + * Initialize the cpuidle ops with the device for the cpu and then call + * the cpu's idle initialization callback. This may fail if the underlying HW + * is not operational. + * + * Returns: + * 0 on success, + * -ENODEV if it fails to find the cpu node in the device tree, + * -EOPNOTSUPP if it does not find a registered and valid cpuidle_ops for + * this cpu, + * -ENOENT if it fails to find an 'enable-method' property, + * -ENXIO if the HW reports a failure or a misconfiguration, + * -ENOMEM if the HW report an memory allocation failure + */ +int __init arm_cpuidle_init(int cpu) +{ + struct device_node *cpu_node = of_cpu_device_node_get(cpu); + int ret; + + if (!cpu_node) + return -ENODEV; + + ret = arm_cpuidle_read_ops(cpu_node, cpu); + if (!ret) + ret = cpuidle_ops[cpu].init(cpu_node, cpu); + + of_node_put(cpu_node); + + return ret; +} diff --git a/arch/arm/kernel/crash_dump.c b/arch/arm/kernel/crash_dump.c new file mode 100644 index 000000000..938bd932d --- /dev/null +++ b/arch/arm/kernel/crash_dump.c @@ -0,0 +1,35 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * arch/arm/kernel/crash_dump.c + * + * Copyright (C) 2010 Nokia Corporation. + * Author: Mika Westerberg + * + * This code is taken from arch/x86/kernel/crash_dump_64.c + * Created by: Hariprasad Nellitheertha (hari@in.ibm.com) + * Copyright (C) IBM Corporation, 2004. All rights reserved + */ + +#include <linux/errno.h> +#include <linux/crash_dump.h> +#include <linux/uaccess.h> +#include <linux/io.h> +#include <linux/uio.h> + +ssize_t copy_oldmem_page(struct iov_iter *iter, unsigned long pfn, + size_t csize, unsigned long offset) +{ + void *vaddr; + + if (!csize) + return 0; + + vaddr = ioremap(__pfn_to_phys(pfn), PAGE_SIZE); + if (!vaddr) + return -ENOMEM; + + csize = copy_to_iter(vaddr + offset, csize, iter); + + iounmap(vaddr); + return csize; +} diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S new file mode 100644 index 000000000..d92f44bdf --- /dev/null +++ b/arch/arm/kernel/debug.S @@ -0,0 +1,161 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/arch/arm/kernel/debug.S + * + * Copyright (C) 1994-1999 Russell King + * + * 32-bit debugging code + */ +#include <linux/linkage.h> +#include <asm/assembler.h> + + .text + +/* + * Some debugging routines (useful if you've got MM problems and + * printk isn't working). For DEBUGGING ONLY!!! Do not leave + * references to these in a production kernel! + */ + +#if !defined(CONFIG_DEBUG_SEMIHOSTING) +#include CONFIG_DEBUG_LL_INCLUDE +#endif + +#ifdef CONFIG_MMU + .macro addruart_current, rx, tmp1, tmp2 + addruart \tmp1, \tmp2, \rx + mrc p15, 0, \rx, c1, c0 + tst \rx, #1 + moveq \rx, \tmp1 + movne \rx, \tmp2 + .endm + +#else /* !CONFIG_MMU */ + .macro addruart_current, rx, tmp1, tmp2 + addruart \rx, \tmp1, \tmp2 + .endm + +#endif /* CONFIG_MMU */ + +/* + * Useful debugging routines + */ +ENTRY(printhex8) + mov r1, #8 + b printhex +ENDPROC(printhex8) + +ENTRY(printhex4) + mov r1, #4 + b printhex +ENDPROC(printhex4) + +ENTRY(printhex2) + mov r1, #2 +printhex: adr r2, hexbuf_rel + ldr r3, [r2] + add r2, r2, r3 + add r3, r2, r1 + mov r1, #0 + strb r1, [r3] +1: and r1, r0, #15 + mov r0, r0, lsr #4 + cmp r1, #10 + addlt r1, r1, #'0' + addge r1, r1, #'a' - 10 + strb r1, [r3, #-1]! + teq r3, r2 + bne 1b + mov r0, r2 + b printascii +ENDPROC(printhex2) + + .pushsection .bss +hexbuf_addr: .space 16 + .popsection + .align +hexbuf_rel: .long hexbuf_addr - . + + .ltorg + +#ifndef CONFIG_DEBUG_SEMIHOSTING + +ENTRY(printascii) + addruart_current r3, r1, r2 +1: teq r0, #0 + ldrbne r1, [r0], #1 + teqne r1, #0 + reteq lr +2: teq r1, #'\n' + bne 3f + mov r1, #'\r' +#ifdef CONFIG_DEBUG_UART_FLOW_CONTROL + waituartcts r2, r3 +#endif + waituarttxrdy r2, r3 + senduart r1, r3 + busyuart r2, r3 + mov r1, #'\n' +3: +#ifdef CONFIG_DEBUG_UART_FLOW_CONTROL + waituartcts r2, r3 +#endif + waituarttxrdy r2, r3 + senduart r1, r3 + busyuart r2, r3 + b 1b +ENDPROC(printascii) + +ENTRY(printch) + addruart_current r3, r1, r2 + mov r1, r0 + mov r0, #0 + b 2b +ENDPROC(printch) + +#ifdef CONFIG_MMU +ENTRY(debug_ll_addr) + addruart r2, r3, ip + str r2, [r0] + str r3, [r1] + ret lr +ENDPROC(debug_ll_addr) +#endif + +#else + +ENTRY(printascii) + mov r1, r0 + mov r0, #0x04 @ SYS_WRITE0 + ARM( svc #0x123456 ) +#ifdef CONFIG_CPU_V7M + THUMB( bkpt #0xab ) +#else + THUMB( svc #0xab ) +#endif + ret lr +ENDPROC(printascii) + +ENTRY(printch) + adr r1, hexbuf_rel + ldr r2, [r1] + add r1, r1, r2 + strb r0, [r1] + mov r0, #0x03 @ SYS_WRITEC + ARM( svc #0x123456 ) +#ifdef CONFIG_CPU_V7M + THUMB( bkpt #0xab ) +#else + THUMB( svc #0xab ) +#endif + ret lr +ENDPROC(printch) + +ENTRY(debug_ll_addr) + mov r2, #0 + str r2, [r0] + str r2, [r1] + ret lr +ENDPROC(debug_ll_addr) + +#endif diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c new file mode 100644 index 000000000..264827281 --- /dev/null +++ b/arch/arm/kernel/devtree.c @@ -0,0 +1,239 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/devtree.c + * + * Copyright (C) 2009 Canonical Ltd. <jeremy.kerr@canonical.com> + */ + +#include <linux/init.h> +#include <linux/export.h> +#include <linux/errno.h> +#include <linux/types.h> +#include <linux/memblock.h> +#include <linux/of.h> +#include <linux/of_fdt.h> +#include <linux/of_irq.h> +#include <linux/of_platform.h> +#include <linux/smp.h> + +#include <asm/cputype.h> +#include <asm/setup.h> +#include <asm/page.h> +#include <asm/prom.h> +#include <asm/smp_plat.h> +#include <asm/mach/arch.h> +#include <asm/mach-types.h> + + +#ifdef CONFIG_SMP +extern struct of_cpu_method __cpu_method_of_table[]; + +static const struct of_cpu_method __cpu_method_of_table_sentinel + __used __section("__cpu_method_of_table_end"); + + +static int __init set_smp_ops_by_method(struct device_node *node) +{ + const char *method; + struct of_cpu_method *m = __cpu_method_of_table; + + if (of_property_read_string(node, "enable-method", &method)) + return 0; + + for (; m->method; m++) + if (!strcmp(m->method, method)) { + smp_set_ops(m->ops); + return 1; + } + + return 0; +} +#else +static inline int set_smp_ops_by_method(struct device_node *node) +{ + return 1; +} +#endif + + +/* + * arm_dt_init_cpu_maps - Function retrieves cpu nodes from the device tree + * and builds the cpu logical map array containing MPIDR values related to + * logical cpus + * + * Updates the cpu possible mask with the number of parsed cpu nodes + */ +void __init arm_dt_init_cpu_maps(void) +{ + /* + * Temp logical map is initialized with UINT_MAX values that are + * considered invalid logical map entries since the logical map must + * contain a list of MPIDR[23:0] values where MPIDR[31:24] must + * read as 0. + */ + struct device_node *cpu, *cpus; + int found_method = 0; + u32 i, j, cpuidx = 1; + u32 mpidr = is_smp() ? read_cpuid_mpidr() & MPIDR_HWID_BITMASK : 0; + + u32 tmp_map[NR_CPUS] = { [0 ... NR_CPUS-1] = MPIDR_INVALID }; + bool bootcpu_valid = false; + cpus = of_find_node_by_path("/cpus"); + + if (!cpus) + return; + + for_each_of_cpu_node(cpu) { + u32 hwid = of_get_cpu_hwid(cpu, 0); + + pr_debug(" * %pOF...\n", cpu); + + /* + * Bits n:24 must be set to 0 in the DT since the reg property + * defines the MPIDR[23:0]. + */ + if (hwid & ~MPIDR_HWID_BITMASK) { + of_node_put(cpu); + return; + } + + /* + * Duplicate MPIDRs are a recipe for disaster. + * Scan all initialized entries and check for + * duplicates. If any is found just bail out. + * temp values were initialized to UINT_MAX + * to avoid matching valid MPIDR[23:0] values. + */ + for (j = 0; j < cpuidx; j++) + if (WARN(tmp_map[j] == hwid, + "Duplicate /cpu reg properties in the DT\n")) { + of_node_put(cpu); + return; + } + + /* + * Build a stashed array of MPIDR values. Numbering scheme + * requires that if detected the boot CPU must be assigned + * logical id 0. Other CPUs get sequential indexes starting + * from 1. If a CPU node with a reg property matching the + * boot CPU MPIDR is detected, this is recorded so that the + * logical map built from DT is validated and can be used + * to override the map created in smp_setup_processor_id(). + */ + if (hwid == mpidr) { + i = 0; + bootcpu_valid = true; + } else { + i = cpuidx++; + } + + if (WARN(cpuidx > nr_cpu_ids, "DT /cpu %u nodes greater than " + "max cores %u, capping them\n", + cpuidx, nr_cpu_ids)) { + cpuidx = nr_cpu_ids; + of_node_put(cpu); + break; + } + + tmp_map[i] = hwid; + + if (!found_method) + found_method = set_smp_ops_by_method(cpu); + } + + /* + * Fallback to an enable-method in the cpus node if nothing found in + * a cpu node. + */ + if (!found_method) + set_smp_ops_by_method(cpus); + + if (!bootcpu_valid) { + pr_warn("DT missing boot CPU MPIDR[23:0], fall back to default cpu_logical_map\n"); + return; + } + + /* + * Since the boot CPU node contains proper data, and all nodes have + * a reg property, the DT CPU list can be considered valid and the + * logical map created in smp_setup_processor_id() can be overridden + */ + for (i = 0; i < cpuidx; i++) { + set_cpu_possible(i, true); + cpu_logical_map(i) = tmp_map[i]; + pr_debug("cpu logical map 0x%x\n", cpu_logical_map(i)); + } +} + +bool arch_match_cpu_phys_id(int cpu, u64 phys_id) +{ + return phys_id == cpu_logical_map(cpu); +} + +static const void * __init arch_get_next_mach(const char *const **match) +{ + static const struct machine_desc *mdesc = __arch_info_begin; + const struct machine_desc *m = mdesc; + + if (m >= __arch_info_end) + return NULL; + + mdesc++; + *match = m->dt_compat; + return m; +} + +/** + * setup_machine_fdt - Machine setup when an dtb was passed to the kernel + * @dt_virt: virtual address of dt blob + * + * If a dtb was passed to the kernel in r2, then use it to choose the + * correct machine_desc and to setup the system. + */ +const struct machine_desc * __init setup_machine_fdt(void *dt_virt) +{ + const struct machine_desc *mdesc, *mdesc_best = NULL; + + DT_MACHINE_START(GENERIC_DT, "Generic DT based system") + .l2c_aux_val = 0x0, + .l2c_aux_mask = ~0x0, + MACHINE_END + + mdesc_best = &__mach_desc_GENERIC_DT; + + if (!dt_virt || !early_init_dt_verify(dt_virt)) + return NULL; + + mdesc = of_flat_dt_match_machine(mdesc_best, arch_get_next_mach); + + if (!mdesc) { + const char *prop; + int size; + unsigned long dt_root; + + early_print("\nError: unrecognized/unsupported " + "device tree compatible list:\n[ "); + + dt_root = of_get_flat_dt_root(); + prop = of_get_flat_dt_prop(dt_root, "compatible", &size); + while (size > 0) { + early_print("'%s' ", prop); + size -= strlen(prop) + 1; + prop += strlen(prop) + 1; + } + early_print("]\n\n"); + + dump_machine_table(); /* does not return */ + } + + /* We really don't want to do this, but sometimes firmware provides buggy data */ + if (mdesc->dt_fixup) + mdesc->dt_fixup(); + + early_init_dt_scan_nodes(); + + /* Change machine number to match the mdesc we're using */ + __machine_arch_type = mdesc->nr; + + return mdesc; +} diff --git a/arch/arm/kernel/dma.c b/arch/arm/kernel/dma.c new file mode 100644 index 000000000..ba15b8666 --- /dev/null +++ b/arch/arm/kernel/dma.c @@ -0,0 +1,283 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/dma.c + * + * Copyright (C) 1995-2000 Russell King + * + * Front-end to the DMA handling. This handles the allocation/freeing + * of DMA channels, and provides a unified interface to the machines + * DMA facilities. + */ +#include <linux/module.h> +#include <linux/init.h> +#include <linux/spinlock.h> +#include <linux/errno.h> +#include <linux/scatterlist.h> +#include <linux/seq_file.h> +#include <linux/proc_fs.h> + +#include <asm/dma.h> + +#include <asm/mach/dma.h> + +DEFINE_RAW_SPINLOCK(dma_spin_lock); +EXPORT_SYMBOL(dma_spin_lock); + +static dma_t *dma_chan[MAX_DMA_CHANNELS]; + +static inline dma_t *dma_channel(unsigned int chan) +{ + if (chan >= MAX_DMA_CHANNELS) + return NULL; + + return dma_chan[chan]; +} + +int __init isa_dma_add(unsigned int chan, dma_t *dma) +{ + if (!dma->d_ops) + return -EINVAL; + + sg_init_table(&dma->buf, 1); + + if (dma_chan[chan]) + return -EBUSY; + dma_chan[chan] = dma; + return 0; +} + +/* + * Request DMA channel + * + * On certain platforms, we have to allocate an interrupt as well... + */ +int request_dma(unsigned int chan, const char *device_id) +{ + dma_t *dma = dma_channel(chan); + int ret; + + if (!dma) + goto bad_dma; + + if (xchg(&dma->lock, 1) != 0) + goto busy; + + dma->device_id = device_id; + dma->active = 0; + dma->invalid = 1; + + ret = 0; + if (dma->d_ops->request) + ret = dma->d_ops->request(chan, dma); + + if (ret) + xchg(&dma->lock, 0); + + return ret; + +bad_dma: + pr_err("dma: trying to allocate DMA%d\n", chan); + return -EINVAL; + +busy: + return -EBUSY; +} +EXPORT_SYMBOL(request_dma); + +/* + * Free DMA channel + * + * On certain platforms, we have to free interrupt as well... + */ +void free_dma(unsigned int chan) +{ + dma_t *dma = dma_channel(chan); + + if (!dma) + goto bad_dma; + + if (dma->active) { + pr_err("dma%d: freeing active DMA\n", chan); + dma->d_ops->disable(chan, dma); + dma->active = 0; + } + + if (xchg(&dma->lock, 0) != 0) { + if (dma->d_ops->free) + dma->d_ops->free(chan, dma); + return; + } + + pr_err("dma%d: trying to free free DMA\n", chan); + return; + +bad_dma: + pr_err("dma: trying to free DMA%d\n", chan); +} +EXPORT_SYMBOL(free_dma); + +/* Set DMA Scatter-Gather list + */ +void set_dma_sg (unsigned int chan, struct scatterlist *sg, int nr_sg) +{ + dma_t *dma = dma_channel(chan); + + if (dma->active) + pr_err("dma%d: altering DMA SG while DMA active\n", chan); + + dma->sg = sg; + dma->sgcount = nr_sg; + dma->invalid = 1; +} +EXPORT_SYMBOL(set_dma_sg); + +/* Set DMA address + * + * Copy address to the structure, and set the invalid bit + */ +void __set_dma_addr (unsigned int chan, void *addr) +{ + dma_t *dma = dma_channel(chan); + + if (dma->active) + pr_err("dma%d: altering DMA address while DMA active\n", chan); + + dma->sg = NULL; + dma->addr = addr; + dma->invalid = 1; +} +EXPORT_SYMBOL(__set_dma_addr); + +/* Set DMA byte count + * + * Copy address to the structure, and set the invalid bit + */ +void set_dma_count (unsigned int chan, unsigned long count) +{ + dma_t *dma = dma_channel(chan); + + if (dma->active) + pr_err("dma%d: altering DMA count while DMA active\n", chan); + + dma->sg = NULL; + dma->count = count; + dma->invalid = 1; +} +EXPORT_SYMBOL(set_dma_count); + +/* Set DMA direction mode + */ +void set_dma_mode (unsigned int chan, unsigned int mode) +{ + dma_t *dma = dma_channel(chan); + + if (dma->active) + pr_err("dma%d: altering DMA mode while DMA active\n", chan); + + dma->dma_mode = mode; + dma->invalid = 1; +} +EXPORT_SYMBOL(set_dma_mode); + +/* Enable DMA channel + */ +void enable_dma (unsigned int chan) +{ + dma_t *dma = dma_channel(chan); + + if (!dma->lock) + goto free_dma; + + if (dma->active == 0) { + dma->active = 1; + dma->d_ops->enable(chan, dma); + } + return; + +free_dma: + pr_err("dma%d: trying to enable free DMA\n", chan); + BUG(); +} +EXPORT_SYMBOL(enable_dma); + +/* Disable DMA channel + */ +void disable_dma (unsigned int chan) +{ + dma_t *dma = dma_channel(chan); + + if (!dma->lock) + goto free_dma; + + if (dma->active == 1) { + dma->active = 0; + dma->d_ops->disable(chan, dma); + } + return; + +free_dma: + pr_err("dma%d: trying to disable free DMA\n", chan); + BUG(); +} +EXPORT_SYMBOL(disable_dma); + +/* + * Is the specified DMA channel active? + */ +int dma_channel_active(unsigned int chan) +{ + dma_t *dma = dma_channel(chan); + return dma->active; +} +EXPORT_SYMBOL(dma_channel_active); + +void set_dma_page(unsigned int chan, char pagenr) +{ + pr_err("dma%d: trying to set_dma_page\n", chan); +} +EXPORT_SYMBOL(set_dma_page); + +void set_dma_speed(unsigned int chan, int cycle_ns) +{ + dma_t *dma = dma_channel(chan); + int ret = 0; + + if (dma->d_ops->setspeed) + ret = dma->d_ops->setspeed(chan, dma, cycle_ns); + dma->speed = ret; +} +EXPORT_SYMBOL(set_dma_speed); + +int get_dma_residue(unsigned int chan) +{ + dma_t *dma = dma_channel(chan); + int ret = 0; + + if (dma->d_ops->residue) + ret = dma->d_ops->residue(chan, dma); + + return ret; +} +EXPORT_SYMBOL(get_dma_residue); + +#ifdef CONFIG_PROC_FS +static int proc_dma_show(struct seq_file *m, void *v) +{ + int i; + + for (i = 0 ; i < MAX_DMA_CHANNELS ; i++) { + dma_t *dma = dma_channel(i); + if (dma && dma->lock) + seq_printf(m, "%2d: %s\n", i, dma->device_id); + } + return 0; +} + +static int __init proc_dma_init(void) +{ + proc_create_single("dma", 0, NULL, proc_dma_show); + return 0; +} + +__initcall(proc_dma_init); +#endif diff --git a/arch/arm/kernel/early_printk.c b/arch/arm/kernel/early_printk.c new file mode 100644 index 000000000..03239ca0d --- /dev/null +++ b/arch/arm/kernel/early_printk.c @@ -0,0 +1,47 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/early_printk.c + * + * Copyright (C) 2009 Sascha Hauer <s.hauer@pengutronix.de> + */ + +#include <linux/kernel.h> +#include <linux/console.h> +#include <linux/init.h> +#include <linux/string.h> + +extern void printascii(const char *); + +static void early_write(const char *s, unsigned n) +{ + char buf[128]; + while (n) { + unsigned l = min(n, sizeof(buf)-1); + memcpy(buf, s, l); + buf[l] = 0; + s += l; + n -= l; + printascii(buf); + } +} + +static void early_console_write(struct console *con, const char *s, unsigned n) +{ + early_write(s, n); +} + +static struct console early_console_dev = { + .name = "earlycon", + .write = early_console_write, + .flags = CON_PRINTBUFFER | CON_BOOT, + .index = -1, +}; + +static int __init setup_early_printk(char *buf) +{ + early_console = &early_console_dev; + register_console(&early_console_dev); + return 0; +} + +early_param("earlyprintk", setup_early_printk); diff --git a/arch/arm/kernel/efi.c b/arch/arm/kernel/efi.c new file mode 100644 index 000000000..e50ad7eef --- /dev/null +++ b/arch/arm/kernel/efi.c @@ -0,0 +1,154 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2015 Linaro Ltd <ard.biesheuvel@linaro.org> + */ + +#include <linux/efi.h> +#include <linux/memblock.h> +#include <asm/efi.h> +#include <asm/mach/map.h> +#include <asm/mmu_context.h> + +static int __init set_permissions(pte_t *ptep, unsigned long addr, void *data) +{ + efi_memory_desc_t *md = data; + pte_t pte = *ptep; + + if (md->attribute & EFI_MEMORY_RO) + pte = set_pte_bit(pte, __pgprot(L_PTE_RDONLY)); + if (md->attribute & EFI_MEMORY_XP) + pte = set_pte_bit(pte, __pgprot(L_PTE_XN)); + set_pte_ext(ptep, pte, PTE_EXT_NG); + return 0; +} + +int __init efi_set_mapping_permissions(struct mm_struct *mm, + efi_memory_desc_t *md) +{ + unsigned long base, size; + + base = md->virt_addr; + size = md->num_pages << EFI_PAGE_SHIFT; + + /* + * We can only use apply_to_page_range() if we can guarantee that the + * entire region was mapped using pages. This should be the case if the + * region does not cover any naturally aligned SECTION_SIZE sized + * blocks. + */ + if (round_down(base + size, SECTION_SIZE) < + round_up(base, SECTION_SIZE) + SECTION_SIZE) + return apply_to_page_range(mm, base, size, set_permissions, md); + + return 0; +} + +int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) +{ + struct map_desc desc = { + .virtual = md->virt_addr, + .pfn = __phys_to_pfn(md->phys_addr), + .length = md->num_pages * EFI_PAGE_SIZE, + }; + + /* + * Order is important here: memory regions may have all of the + * bits below set (and usually do), so we check them in order of + * preference. + */ + if (md->attribute & EFI_MEMORY_WB) + desc.type = MT_MEMORY_RWX; + else if (md->attribute & EFI_MEMORY_WT) + desc.type = MT_MEMORY_RWX_NONCACHED; + else if (md->attribute & EFI_MEMORY_WC) + desc.type = MT_DEVICE_WC; + else + desc.type = MT_DEVICE; + + create_mapping_late(mm, &desc, true); + + /* + * If stricter permissions were specified, apply them now. + */ + if (md->attribute & (EFI_MEMORY_RO | EFI_MEMORY_XP)) + return efi_set_mapping_permissions(mm, md); + return 0; +} + +static unsigned long __initdata screen_info_table = EFI_INVALID_TABLE_ADDR; +static unsigned long __initdata cpu_state_table = EFI_INVALID_TABLE_ADDR; + +const efi_config_table_type_t efi_arch_tables[] __initconst = { + {LINUX_EFI_ARM_SCREEN_INFO_TABLE_GUID, &screen_info_table}, + {LINUX_EFI_ARM_CPU_STATE_TABLE_GUID, &cpu_state_table}, + {} +}; + +static void __init load_screen_info_table(void) +{ + struct screen_info *si; + + if (screen_info_table != EFI_INVALID_TABLE_ADDR) { + si = early_memremap_ro(screen_info_table, sizeof(*si)); + if (!si) { + pr_err("Could not map screen_info config table\n"); + return; + } + screen_info = *si; + early_memunmap(si, sizeof(*si)); + + /* dummycon on ARM needs non-zero values for columns/lines */ + screen_info.orig_video_cols = 80; + screen_info.orig_video_lines = 25; + + if (memblock_is_map_memory(screen_info.lfb_base)) + memblock_mark_nomap(screen_info.lfb_base, + screen_info.lfb_size); + } +} + +static void __init load_cpu_state_table(void) +{ + if (cpu_state_table != EFI_INVALID_TABLE_ADDR) { + struct efi_arm_entry_state *state; + bool dump_state = true; + + state = early_memremap_ro(cpu_state_table, + sizeof(struct efi_arm_entry_state)); + if (state == NULL) { + pr_warn("Unable to map CPU entry state table.\n"); + return; + } + + if ((state->sctlr_before_ebs & 1) == 0) + pr_warn(FW_BUG "EFI stub was entered with MMU and Dcache disabled, please fix your firmware!\n"); + else if ((state->sctlr_after_ebs & 1) == 0) + pr_warn(FW_BUG "ExitBootServices() returned with MMU and Dcache disabled, please fix your firmware!\n"); + else + dump_state = false; + + if (dump_state || efi_enabled(EFI_DBG)) { + pr_info("CPSR at EFI stub entry : 0x%08x\n", + state->cpsr_before_ebs); + pr_info("SCTLR at EFI stub entry : 0x%08x\n", + state->sctlr_before_ebs); + pr_info("CPSR after ExitBootServices() : 0x%08x\n", + state->cpsr_after_ebs); + pr_info("SCTLR after ExitBootServices(): 0x%08x\n", + state->sctlr_after_ebs); + } + early_memunmap(state, sizeof(struct efi_arm_entry_state)); + } +} + +void __init arm_efi_init(void) +{ + efi_init(); + + load_screen_info_table(); + + /* ARM does not permit early mappings to persist across paging_init() */ + efi_memmap_unmap(); + + load_cpu_state_table(); +} diff --git a/arch/arm/kernel/elf.c b/arch/arm/kernel/elf.c new file mode 100644 index 000000000..254ab7138 --- /dev/null +++ b/arch/arm/kernel/elf.c @@ -0,0 +1,133 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/personality.h> +#include <linux/binfmts.h> +#include <linux/elf.h> +#include <linux/elf-fdpic.h> +#include <asm/system_info.h> + +int elf_check_arch(const struct elf32_hdr *x) +{ + unsigned int eflags; + + /* Make sure it's an ARM executable */ + if (x->e_machine != EM_ARM) + return 0; + + /* Make sure the entry address is reasonable */ + if (x->e_entry & 1) { + if (!(elf_hwcap & HWCAP_THUMB)) + return 0; + } else if (x->e_entry & 3) + return 0; + + eflags = x->e_flags; + if ((eflags & EF_ARM_EABI_MASK) == EF_ARM_EABI_UNKNOWN) { + unsigned int flt_fmt; + + /* APCS26 is only allowed if the CPU supports it */ + if ((eflags & EF_ARM_APCS_26) && !(elf_hwcap & HWCAP_26BIT)) + return 0; + + flt_fmt = eflags & (EF_ARM_VFP_FLOAT | EF_ARM_SOFT_FLOAT); + + /* VFP requires the supporting code */ + if (flt_fmt == EF_ARM_VFP_FLOAT && !(elf_hwcap & HWCAP_VFP)) + return 0; + } + return 1; +} +EXPORT_SYMBOL(elf_check_arch); + +void elf_set_personality(const struct elf32_hdr *x) +{ + unsigned int eflags = x->e_flags; + unsigned int personality = current->personality & ~PER_MASK; + + /* + * We only support Linux ELF executables, so always set the + * personality to LINUX. + */ + personality |= PER_LINUX; + + /* + * APCS-26 is only valid for OABI executables + */ + if ((eflags & EF_ARM_EABI_MASK) == EF_ARM_EABI_UNKNOWN && + (eflags & EF_ARM_APCS_26)) + personality &= ~ADDR_LIMIT_32BIT; + else + personality |= ADDR_LIMIT_32BIT; + + set_personality(personality); + + /* + * Since the FPA coprocessor uses CP1 and CP2, and iWMMXt uses CP0 + * and CP1, we only enable access to the iWMMXt coprocessor if the + * binary is EABI or softfloat (and thus, guaranteed not to use + * FPA instructions.) + */ + if (elf_hwcap & HWCAP_IWMMXT && + eflags & (EF_ARM_EABI_MASK | EF_ARM_SOFT_FLOAT)) { + set_thread_flag(TIF_USING_IWMMXT); + } else { + clear_thread_flag(TIF_USING_IWMMXT); + } +} +EXPORT_SYMBOL(elf_set_personality); + +/* + * An executable for which elf_read_implies_exec() returns TRUE will + * have the READ_IMPLIES_EXEC personality flag set automatically. + * + * The decision process for determining the results are: + * + *        CPU: | lacks NX*  | has NX | + * ELF:        |       |      | + * ---------------------|------------|------------| + * missing PT_GNU_STACK | exec-all  | exec-all  | + * PT_GNU_STACK == RWX  | exec-all  | exec-stack | + * PT_GNU_STACK == RW  | exec-all  | exec-none | + * + * exec-all : all PROT_READ user mappings are executable, except when + * backed by files on a noexec-filesystem. + * exec-none : only PROT_EXEC user mappings are executable. + * exec-stack: only the stack and PROT_EXEC user mappings are executable. + * + * *this column has no architectural effect: NX markings are ignored by + * hardware, but may have behavioral effects when "wants X" collides with + * "cannot be X" constraints in memory permission flags, as in + * https://lkml.kernel.org/r/20190418055759.GA3155@mellanox.com + * + */ +int arm_elf_read_implies_exec(int executable_stack) +{ + if (executable_stack == EXSTACK_DEFAULT) + return 1; + if (cpu_architecture() < CPU_ARCH_ARMv6) + return 1; + return 0; +} +EXPORT_SYMBOL(arm_elf_read_implies_exec); + +#if defined(CONFIG_MMU) && defined(CONFIG_BINFMT_ELF_FDPIC) + +void elf_fdpic_arch_lay_out_mm(struct elf_fdpic_params *exec_params, + struct elf_fdpic_params *interp_params, + unsigned long *start_stack, + unsigned long *start_brk) +{ + elf_set_personality(&exec_params->hdr); + + exec_params->load_addr = 0x8000; + interp_params->load_addr = ELF_ET_DYN_BASE; + *start_stack = TASK_SIZE - SZ_16M; + + if ((exec_params->flags & ELF_FDPIC_FLAG_ARRANGEMENT) == ELF_FDPIC_FLAG_INDEPENDENT) { + exec_params->flags &= ~ELF_FDPIC_FLAG_ARRANGEMENT; + exec_params->flags |= ELF_FDPIC_FLAG_CONSTDISP; + } +} + +#endif diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S new file mode 100644 index 000000000..c39303e5c --- /dev/null +++ b/arch/arm/kernel/entry-armv.S @@ -0,0 +1,1342 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/arch/arm/kernel/entry-armv.S + * + * Copyright (C) 1996,1997,1998 Russell King. + * ARM700 fix by Matthew Godbolt (linux-user@willothewisp.demon.co.uk) + * nommu support by Hyok S. Choi (hyok.choi@samsung.com) + * + * Low-level vector interface routines + * + * Note: there is a StrongARM bug in the STMIA rn, {regs}^ instruction + * that causes it to save wrong values... Be aware! + */ + +#include <linux/init.h> + +#include <asm/assembler.h> +#include <asm/memory.h> +#include <asm/glue-df.h> +#include <asm/glue-pf.h> +#include <asm/vfpmacros.h> +#include <asm/thread_notify.h> +#include <asm/unwind.h> +#include <asm/unistd.h> +#include <asm/tls.h> +#include <asm/system_info.h> +#include <asm/uaccess-asm.h> + +#include "entry-header.S" +#include <asm/probes.h> + +/* + * Interrupt handling. + */ + .macro irq_handler, from_user:req + mov r1, sp + ldr_this_cpu r2, irq_stack_ptr, r2, r3 + .if \from_user == 0 + @ + @ If we took the interrupt while running in the kernel, we may already + @ be using the IRQ stack, so revert to the original value in that case. + @ + subs r3, r2, r1 @ SP above bottom of IRQ stack? + rsbscs r3, r3, #THREAD_SIZE @ ... and below the top? +#ifdef CONFIG_VMAP_STACK + ldr_va r3, high_memory, cc @ End of the linear region + cmpcc r3, r1 @ Stack pointer was below it? +#endif + bcc 0f @ If not, switch to the IRQ stack + mov r0, r1 + bl generic_handle_arch_irq + b 1f +0: + .endif + + mov_l r0, generic_handle_arch_irq + bl call_with_stack +1: + .endm + + .macro pabt_helper + @ PABORT handler takes pt_regs in r2, fault address in r4 and psr in r5 +#ifdef MULTI_PABORT + ldr_va ip, processor, offset=PROCESSOR_PABT_FUNC + bl_r ip +#else + bl CPU_PABORT_HANDLER +#endif + .endm + + .macro dabt_helper + + @ + @ Call the processor-specific abort handler: + @ + @ r2 - pt_regs + @ r4 - aborted context pc + @ r5 - aborted context psr + @ + @ The abort handler must return the aborted address in r0, and + @ the fault status register in r1. r9 must be preserved. + @ +#ifdef MULTI_DABORT + ldr_va ip, processor, offset=PROCESSOR_DABT_FUNC + bl_r ip +#else + bl CPU_DABORT_HANDLER +#endif + .endm + + .section .entry.text,"ax",%progbits + +/* + * Invalid mode handlers + */ + .macro inv_entry, reason + sub sp, sp, #PT_REGS_SIZE + ARM( stmib sp, {r1 - lr} ) + THUMB( stmia sp, {r0 - r12} ) + THUMB( str sp, [sp, #S_SP] ) + THUMB( str lr, [sp, #S_LR] ) + mov r1, #\reason + .endm + +__pabt_invalid: + inv_entry BAD_PREFETCH + b common_invalid +ENDPROC(__pabt_invalid) + +__dabt_invalid: + inv_entry BAD_DATA + b common_invalid +ENDPROC(__dabt_invalid) + +__irq_invalid: + inv_entry BAD_IRQ + b common_invalid +ENDPROC(__irq_invalid) + +__und_invalid: + inv_entry BAD_UNDEFINSTR + + @ + @ XXX fall through to common_invalid + @ + +@ +@ common_invalid - generic code for failed exception (re-entrant version of handlers) +@ +common_invalid: + zero_fp + + ldmia r0, {r4 - r6} + add r0, sp, #S_PC @ here for interlock avoidance + mov r7, #-1 @ "" "" "" "" + str r4, [sp] @ save preserved r0 + stmia r0, {r5 - r7} @ lr_<exception>, + @ cpsr_<exception>, "old_r0" + + mov r0, sp + b bad_mode +ENDPROC(__und_invalid) + +/* + * SVC mode handlers + */ + +#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5) +#define SPFIX(code...) code +#else +#define SPFIX(code...) +#endif + + .macro svc_entry, stack_hole=0, trace=1, uaccess=1, overflow_check=1 + UNWIND(.fnstart ) + sub sp, sp, #(SVC_REGS_SIZE + \stack_hole) + THUMB( add sp, r1 ) @ get SP in a GPR without + THUMB( sub r1, sp, r1 ) @ using a temp register + + .if \overflow_check + UNWIND(.save {r0 - pc} ) + do_overflow_check (SVC_REGS_SIZE + \stack_hole) + .endif + +#ifdef CONFIG_THUMB2_KERNEL + tst r1, #4 @ test stack pointer alignment + sub r1, sp, r1 @ restore original R1 + sub sp, r1 @ restore original SP +#else + SPFIX( tst sp, #4 ) +#endif + SPFIX( subne sp, sp, #4 ) + + ARM( stmib sp, {r1 - r12} ) + THUMB( stmia sp, {r0 - r12} ) @ No STMIB in Thumb-2 + + ldmia r0, {r3 - r5} + add r7, sp, #S_SP @ here for interlock avoidance + mov r6, #-1 @ "" "" "" "" + add r2, sp, #(SVC_REGS_SIZE + \stack_hole) + SPFIX( addne r2, r2, #4 ) + str r3, [sp] @ save the "real" r0 copied + @ from the exception stack + + mov r3, lr + + @ + @ We are now ready to fill in the remaining blanks on the stack: + @ + @ r2 - sp_svc + @ r3 - lr_svc + @ r4 - lr_<exception>, already fixed up for correct return/restart + @ r5 - spsr_<exception> + @ r6 - orig_r0 (see pt_regs definition in ptrace.h) + @ + stmia r7, {r2 - r6} + + get_thread_info tsk + uaccess_entry tsk, r0, r1, r2, \uaccess + + .if \trace +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off +#endif + .endif + .endm + + .align 5 +__dabt_svc: + svc_entry uaccess=0 + mov r2, sp + dabt_helper + THUMB( ldr r5, [sp, #S_PSR] ) @ potentially updated CPSR + svc_exit r5 @ return from exception + UNWIND(.fnend ) +ENDPROC(__dabt_svc) + + .align 5 +__irq_svc: + svc_entry + irq_handler from_user=0 + +#ifdef CONFIG_PREEMPTION + ldr r8, [tsk, #TI_PREEMPT] @ get preempt count + ldr r0, [tsk, #TI_FLAGS] @ get flags + teq r8, #0 @ if preempt count != 0 + movne r0, #0 @ force flags to 0 + tst r0, #_TIF_NEED_RESCHED + blne svc_preempt +#endif + + svc_exit r5, irq = 1 @ return from exception + UNWIND(.fnend ) +ENDPROC(__irq_svc) + + .ltorg + +#ifdef CONFIG_PREEMPTION +svc_preempt: + mov r8, lr +1: bl preempt_schedule_irq @ irq en/disable is done inside + ldr r0, [tsk, #TI_FLAGS] @ get new tasks TI_FLAGS + tst r0, #_TIF_NEED_RESCHED + reteq r8 @ go again + b 1b +#endif + +__und_fault: + @ Correct the PC such that it is pointing at the instruction + @ which caused the fault. If the faulting instruction was ARM + @ the PC will be pointing at the next instruction, and have to + @ subtract 4. Otherwise, it is Thumb, and the PC will be + @ pointing at the second half of the Thumb instruction. We + @ have to subtract 2. + ldr r2, [r0, #S_PC] + sub r2, r2, r1 + str r2, [r0, #S_PC] + b do_undefinstr +ENDPROC(__und_fault) + + .align 5 +__und_svc: +#ifdef CONFIG_KPROBES + @ If a kprobe is about to simulate a "stmdb sp..." instruction, + @ it obviously needs free stack space which then will belong to + @ the saved context. + svc_entry MAX_STACK_SIZE +#else + svc_entry +#endif + + mov r1, #4 @ PC correction to apply + THUMB( tst r5, #PSR_T_BIT ) @ exception taken in Thumb mode? + THUMB( movne r1, #2 ) @ if so, fix up PC correction + mov r0, sp @ struct pt_regs *regs + bl __und_fault + +__und_svc_finish: + get_thread_info tsk + ldr r5, [sp, #S_PSR] @ Get SVC cpsr + svc_exit r5 @ return from exception + UNWIND(.fnend ) +ENDPROC(__und_svc) + + .align 5 +__pabt_svc: + svc_entry + mov r2, sp @ regs + pabt_helper + svc_exit r5 @ return from exception + UNWIND(.fnend ) +ENDPROC(__pabt_svc) + + .align 5 +__fiq_svc: + svc_entry trace=0 + mov r0, sp @ struct pt_regs *regs + bl handle_fiq_as_nmi + svc_exit_via_fiq + UNWIND(.fnend ) +ENDPROC(__fiq_svc) + +/* + * Abort mode handlers + */ + +@ +@ Taking a FIQ in abort mode is similar to taking a FIQ in SVC mode +@ and reuses the same macros. However in abort mode we must also +@ save/restore lr_abt and spsr_abt to make nested aborts safe. +@ + .align 5 +__fiq_abt: + svc_entry trace=0 + + ARM( msr cpsr_c, #ABT_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( mov r0, #ABT_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( msr cpsr_c, r0 ) + mov r1, lr @ Save lr_abt + mrs r2, spsr @ Save spsr_abt, abort is now safe + ARM( msr cpsr_c, #SVC_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( mov r0, #SVC_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( msr cpsr_c, r0 ) + stmfd sp!, {r1 - r2} + + add r0, sp, #8 @ struct pt_regs *regs + bl handle_fiq_as_nmi + + ldmfd sp!, {r1 - r2} + ARM( msr cpsr_c, #ABT_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( mov r0, #ABT_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( msr cpsr_c, r0 ) + mov lr, r1 @ Restore lr_abt, abort is unsafe + msr spsr_cxsf, r2 @ Restore spsr_abt + ARM( msr cpsr_c, #SVC_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( mov r0, #SVC_MODE | PSR_I_BIT | PSR_F_BIT ) + THUMB( msr cpsr_c, r0 ) + + svc_exit_via_fiq + UNWIND(.fnend ) +ENDPROC(__fiq_abt) + +/* + * User mode handlers + * + * EABI note: sp_svc is always 64-bit aligned here, so should PT_REGS_SIZE + */ + +#if defined(CONFIG_AEABI) && (__LINUX_ARM_ARCH__ >= 5) && (PT_REGS_SIZE & 7) +#error "sizeof(struct pt_regs) must be a multiple of 8" +#endif + + .macro usr_entry, trace=1, uaccess=1 + UNWIND(.fnstart ) + UNWIND(.cantunwind ) @ don't unwind the user space + sub sp, sp, #PT_REGS_SIZE + ARM( stmib sp, {r1 - r12} ) + THUMB( stmia sp, {r0 - r12} ) + + ATRAP( mrc p15, 0, r7, c1, c0, 0) + ATRAP( ldr_va r8, cr_alignment) + + ldmia r0, {r3 - r5} + add r0, sp, #S_PC @ here for interlock avoidance + mov r6, #-1 @ "" "" "" "" + + str r3, [sp] @ save the "real" r0 copied + @ from the exception stack + + @ + @ We are now ready to fill in the remaining blanks on the stack: + @ + @ r4 - lr_<exception>, already fixed up for correct return/restart + @ r5 - spsr_<exception> + @ r6 - orig_r0 (see pt_regs definition in ptrace.h) + @ + @ Also, separately save sp_usr and lr_usr + @ + stmia r0, {r4 - r6} + ARM( stmdb r0, {sp, lr}^ ) + THUMB( store_user_sp_lr r0, r1, S_SP - S_PC ) + + .if \uaccess + uaccess_disable ip + .endif + + @ Enable the alignment trap while in kernel mode + ATRAP( teq r8, r7) + ATRAP( mcrne p15, 0, r8, c1, c0, 0) + + reload_current r7, r8 + + @ + @ Clear FP to mark the first stack frame + @ + zero_fp + + .if \trace +#ifdef CONFIG_TRACE_IRQFLAGS + bl trace_hardirqs_off +#endif + ct_user_exit save = 0 + .endif + .endm + + .macro kuser_cmpxchg_check +#if !defined(CONFIG_CPU_32v6K) && defined(CONFIG_KUSER_HELPERS) +#ifndef CONFIG_MMU +#warning "NPTL on non MMU needs fixing" +#else + @ Make sure our user space atomic helper is restarted + @ if it was interrupted in a critical region. Here we + @ perform a quick test inline since it should be false + @ 99.9999% of the time. The rest is done out of line. + ldr r0, =TASK_SIZE + cmp r4, r0 + blhs kuser_cmpxchg64_fixup +#endif +#endif + .endm + + .align 5 +__dabt_usr: + usr_entry uaccess=0 + kuser_cmpxchg_check + mov r2, sp + dabt_helper + b ret_from_exception + UNWIND(.fnend ) +ENDPROC(__dabt_usr) + + .align 5 +__irq_usr: + usr_entry + kuser_cmpxchg_check + irq_handler from_user=1 + get_thread_info tsk + mov why, #0 + b ret_to_user_from_irq + UNWIND(.fnend ) +ENDPROC(__irq_usr) + + .ltorg + + .align 5 +__und_usr: + usr_entry uaccess=0 + + mov r2, r4 + mov r3, r5 + + @ r2 = regs->ARM_pc, which is either 2 or 4 bytes ahead of the + @ faulting instruction depending on Thumb mode. + @ r3 = regs->ARM_cpsr + @ + @ The emulation code returns using r9 if it has emulated the + @ instruction, or the more conventional lr if we are to treat + @ this as a real undefined instruction + @ + badr r9, ret_from_exception + + @ IRQs must be enabled before attempting to read the instruction from + @ user space since that could cause a page/translation fault if the + @ page table was modified by another CPU. + enable_irq + + tst r3, #PSR_T_BIT @ Thumb mode? + bne __und_usr_thumb + sub r4, r2, #4 @ ARM instr at LR - 4 +1: ldrt r0, [r4] + ARM_BE8(rev r0, r0) @ little endian instruction + + uaccess_disable ip + + @ r0 = 32-bit ARM instruction which caused the exception + @ r2 = PC value for the following instruction (:= regs->ARM_pc) + @ r4 = PC value for the faulting instruction + @ lr = 32-bit undefined instruction function + badr lr, __und_usr_fault_32 + b call_fpe + +__und_usr_thumb: + @ Thumb instruction + sub r4, r2, #2 @ First half of thumb instr at LR - 2 +#if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7 +/* + * Thumb-2 instruction handling. Note that because pre-v6 and >= v6 platforms + * can never be supported in a single kernel, this code is not applicable at + * all when __LINUX_ARM_ARCH__ < 6. This allows simplifying assumptions to be + * made about .arch directives. + */ +#if __LINUX_ARM_ARCH__ < 7 +/* If the target CPU may not be Thumb-2-capable, a run-time check is needed: */ + ldr_va r5, cpu_architecture + cmp r5, #CPU_ARCH_ARMv7 + blo __und_usr_fault_16 @ 16bit undefined instruction +/* + * The following code won't get run unless the running CPU really is v7, so + * coding round the lack of ldrht on older arches is pointless. Temporarily + * override the assembler target arch with the minimum required instead: + */ + .arch armv6t2 +#endif +2: ldrht r5, [r4] +ARM_BE8(rev16 r5, r5) @ little endian instruction + cmp r5, #0xe800 @ 32bit instruction if xx != 0 + blo __und_usr_fault_16_pan @ 16bit undefined instruction +3: ldrht r0, [r2] +ARM_BE8(rev16 r0, r0) @ little endian instruction + uaccess_disable ip + add r2, r2, #2 @ r2 is PC + 2, make it PC + 4 + str r2, [sp, #S_PC] @ it's a 2x16bit instr, update + orr r0, r0, r5, lsl #16 + badr lr, __und_usr_fault_32 + @ r0 = the two 16-bit Thumb instructions which caused the exception + @ r2 = PC value for the following Thumb instruction (:= regs->ARM_pc) + @ r4 = PC value for the first 16-bit Thumb instruction + @ lr = 32bit undefined instruction function + +#if __LINUX_ARM_ARCH__ < 7 +/* If the target arch was overridden, change it back: */ +#ifdef CONFIG_CPU_32v6K + .arch armv6k +#else + .arch armv6 +#endif +#endif /* __LINUX_ARM_ARCH__ < 7 */ +#else /* !(CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7) */ + b __und_usr_fault_16 +#endif + UNWIND(.fnend) +ENDPROC(__und_usr) + +/* + * The out of line fixup for the ldrt instructions above. + */ + .pushsection .text.fixup, "ax" + .align 2 +4: str r4, [sp, #S_PC] @ retry current instruction + ret r9 + .popsection + .pushsection __ex_table,"a" + .long 1b, 4b +#if CONFIG_ARM_THUMB && __LINUX_ARM_ARCH__ >= 6 && CONFIG_CPU_V7 + .long 2b, 4b + .long 3b, 4b +#endif + .popsection + +/* + * Check whether the instruction is a co-processor instruction. + * If yes, we need to call the relevant co-processor handler. + * + * Note that we don't do a full check here for the co-processor + * instructions; all instructions with bit 27 set are well + * defined. The only instructions that should fault are the + * co-processor instructions. However, we have to watch out + * for the ARM6/ARM7 SWI bug. + * + * NEON is a special case that has to be handled here. Not all + * NEON instructions are co-processor instructions, so we have + * to make a special case of checking for them. Plus, there's + * five groups of them, so we have a table of mask/opcode pairs + * to check against, and if any match then we branch off into the + * NEON handler code. + * + * Emulators may wish to make use of the following registers: + * r0 = instruction opcode (32-bit ARM or two 16-bit Thumb) + * r2 = PC value to resume execution after successful emulation + * r9 = normal "successful" return address + * r10 = this threads thread_info structure + * lr = unrecognised instruction return address + * IRQs enabled, FIQs enabled. + */ + @ + @ Fall-through from Thumb-2 __und_usr + @ +#ifdef CONFIG_NEON + get_thread_info r10 @ get current thread + adr r6, .LCneon_thumb_opcodes + b 2f +#endif +call_fpe: + get_thread_info r10 @ get current thread +#ifdef CONFIG_NEON + adr r6, .LCneon_arm_opcodes +2: ldr r5, [r6], #4 @ mask value + ldr r7, [r6], #4 @ opcode bits matching in mask + cmp r5, #0 @ end mask? + beq 1f + and r8, r0, r5 + cmp r8, r7 @ NEON instruction? + bne 2b + mov r7, #1 + strb r7, [r10, #TI_USED_CP + 10] @ mark CP#10 as used + strb r7, [r10, #TI_USED_CP + 11] @ mark CP#11 as used + b do_vfp @ let VFP handler handle this +1: +#endif + tst r0, #0x08000000 @ only CDP/CPRT/LDC/STC have bit 27 + tstne r0, #0x04000000 @ bit 26 set on both ARM and Thumb-2 + reteq lr + and r8, r0, #0x00000f00 @ mask out CP number + mov r7, #1 + add r6, r10, r8, lsr #8 @ add used_cp[] array offset first + strb r7, [r6, #TI_USED_CP] @ set appropriate used_cp[] +#ifdef CONFIG_IWMMXT + @ Test if we need to give access to iWMMXt coprocessors + ldr r5, [r10, #TI_FLAGS] + rsbs r7, r8, #(1 << 8) @ CP 0 or 1 only + movscs r7, r5, lsr #(TIF_USING_IWMMXT + 1) + bcs iwmmxt_task_enable +#endif + ARM( add pc, pc, r8, lsr #6 ) + THUMB( lsr r8, r8, #6 ) + THUMB( add pc, r8 ) + nop + + ret.w lr @ CP#0 + W(b) do_fpe @ CP#1 (FPE) + W(b) do_fpe @ CP#2 (FPE) + ret.w lr @ CP#3 + ret.w lr @ CP#4 + ret.w lr @ CP#5 + ret.w lr @ CP#6 + ret.w lr @ CP#7 + ret.w lr @ CP#8 + ret.w lr @ CP#9 +#ifdef CONFIG_VFP + W(b) do_vfp @ CP#10 (VFP) + W(b) do_vfp @ CP#11 (VFP) +#else + ret.w lr @ CP#10 (VFP) + ret.w lr @ CP#11 (VFP) +#endif + ret.w lr @ CP#12 + ret.w lr @ CP#13 + ret.w lr @ CP#14 (Debug) + ret.w lr @ CP#15 (Control) + +#ifdef CONFIG_NEON + .align 6 + +.LCneon_arm_opcodes: + .word 0xfe000000 @ mask + .word 0xf2000000 @ opcode + + .word 0xff100000 @ mask + .word 0xf4000000 @ opcode + + .word 0x00000000 @ mask + .word 0x00000000 @ opcode + +.LCneon_thumb_opcodes: + .word 0xef000000 @ mask + .word 0xef000000 @ opcode + + .word 0xff100000 @ mask + .word 0xf9000000 @ opcode + + .word 0x00000000 @ mask + .word 0x00000000 @ opcode +#endif + +do_fpe: + add r10, r10, #TI_FPSTATE @ r10 = workspace + ldr_va pc, fp_enter, tmp=r4 @ Call FP module USR entry point + +/* + * The FP module is called with these registers set: + * r0 = instruction + * r2 = PC+4 + * r9 = normal "successful" return address + * r10 = FP workspace + * lr = unrecognised FP instruction return address + */ + + .pushsection .data + .align 2 +ENTRY(fp_enter) + .word no_fp + .popsection + +ENTRY(no_fp) + ret lr +ENDPROC(no_fp) + +__und_usr_fault_32: + mov r1, #4 + b 1f +__und_usr_fault_16_pan: + uaccess_disable ip +__und_usr_fault_16: + mov r1, #2 +1: mov r0, sp + badr lr, ret_from_exception + b __und_fault +ENDPROC(__und_usr_fault_32) +ENDPROC(__und_usr_fault_16) + + .align 5 +__pabt_usr: + usr_entry + mov r2, sp @ regs + pabt_helper + UNWIND(.fnend ) + /* fall through */ +/* + * This is the return code to user mode for abort handlers + */ +ENTRY(ret_from_exception) + UNWIND(.fnstart ) + UNWIND(.cantunwind ) + get_thread_info tsk + mov why, #0 + b ret_to_user + UNWIND(.fnend ) +ENDPROC(__pabt_usr) +ENDPROC(ret_from_exception) + + .align 5 +__fiq_usr: + usr_entry trace=0 + kuser_cmpxchg_check + mov r0, sp @ struct pt_regs *regs + bl handle_fiq_as_nmi + get_thread_info tsk + restore_user_regs fast = 0, offset = 0 + UNWIND(.fnend ) +ENDPROC(__fiq_usr) + +/* + * Register switch for ARMv3 and ARMv4 processors + * r0 = previous task_struct, r1 = previous thread_info, r2 = next thread_info + * previous and next are guaranteed not to be the same. + */ +ENTRY(__switch_to) + UNWIND(.fnstart ) + UNWIND(.cantunwind ) + add ip, r1, #TI_CPU_SAVE + ARM( stmia ip!, {r4 - sl, fp, sp, lr} ) @ Store most regs on stack + THUMB( stmia ip!, {r4 - sl, fp} ) @ Store most regs on stack + THUMB( str sp, [ip], #4 ) + THUMB( str lr, [ip], #4 ) + ldr r4, [r2, #TI_TP_VALUE] + ldr r5, [r2, #TI_TP_VALUE + 4] +#ifdef CONFIG_CPU_USE_DOMAINS + mrc p15, 0, r6, c3, c0, 0 @ Get domain register + str r6, [r1, #TI_CPU_DOMAIN] @ Save old domain register + ldr r6, [r2, #TI_CPU_DOMAIN] +#endif + switch_tls r1, r4, r5, r3, r7 +#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_SMP) && \ + !defined(CONFIG_STACKPROTECTOR_PER_TASK) + ldr r8, =__stack_chk_guard + .if (TSK_STACK_CANARY > IMM12_MASK) + add r9, r2, #TSK_STACK_CANARY & ~IMM12_MASK + ldr r9, [r9, #TSK_STACK_CANARY & IMM12_MASK] + .else + ldr r9, [r2, #TSK_STACK_CANARY & IMM12_MASK] + .endif +#endif + mov r7, r2 @ Preserve 'next' +#ifdef CONFIG_CPU_USE_DOMAINS + mcr p15, 0, r6, c3, c0, 0 @ Set domain register +#endif + mov r5, r0 + add r4, r2, #TI_CPU_SAVE + ldr r0, =thread_notify_head + mov r1, #THREAD_NOTIFY_SWITCH + bl atomic_notifier_call_chain +#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_SMP) && \ + !defined(CONFIG_STACKPROTECTOR_PER_TASK) + str r9, [r8] +#endif + mov r0, r5 +#if !defined(CONFIG_THUMB2_KERNEL) && !defined(CONFIG_VMAP_STACK) + set_current r7, r8 + ldmia r4, {r4 - sl, fp, sp, pc} @ Load all regs saved previously +#else + mov r1, r7 + ldmia r4, {r4 - sl, fp, ip, lr} @ Load all regs saved previously +#ifdef CONFIG_VMAP_STACK + @ + @ Do a dummy read from the new stack while running from the old one so + @ that we can rely on do_translation_fault() to fix up any stale PMD + @ entries covering the vmalloc region. + @ + ldr r2, [ip] +#endif + + @ When CONFIG_THREAD_INFO_IN_TASK=n, the update of SP itself is what + @ effectuates the task switch, as that is what causes the observable + @ values of current and current_thread_info to change. When + @ CONFIG_THREAD_INFO_IN_TASK=y, setting current (and therefore + @ current_thread_info) is done explicitly, and the update of SP just + @ switches us to another stack, with few other side effects. In order + @ to prevent this distinction from causing any inconsistencies, let's + @ keep the 'set_current' call as close as we can to the update of SP. + set_current r1, r2 + mov sp, ip + ret lr +#endif + UNWIND(.fnend ) +ENDPROC(__switch_to) + +#ifdef CONFIG_VMAP_STACK + .text + .align 2 +__bad_stack: + @ + @ We've just detected an overflow. We need to load the address of this + @ CPU's overflow stack into the stack pointer register. We have only one + @ scratch register so let's use a sequence of ADDs including one + @ involving the PC, and decorate them with PC-relative group + @ relocations. As these are ARM only, switch to ARM mode first. + @ + @ We enter here with IP clobbered and its value stashed on the mode + @ stack. + @ +THUMB( bx pc ) +THUMB( nop ) +THUMB( .arm ) + ldr_this_cpu_armv6 ip, overflow_stack_ptr + + str sp, [ip, #-4]! @ Preserve original SP value + mov sp, ip @ Switch to overflow stack + pop {ip} @ Original SP in IP + +#if defined(CONFIG_UNWINDER_FRAME_POINTER) && defined(CONFIG_CC_IS_GCC) + mov ip, ip @ mov expected by unwinder + push {fp, ip, lr, pc} @ GCC flavor frame record +#else + str ip, [sp, #-8]! @ store original SP + push {fpreg, lr} @ Clang flavor frame record +#endif +UNWIND( ldr ip, [r0, #4] ) @ load exception LR +UNWIND( str ip, [sp, #12] ) @ store in the frame record + ldr ip, [r0, #12] @ reload IP + + @ Store the original GPRs to the new stack. + svc_entry uaccess=0, overflow_check=0 + +UNWIND( .save {sp, pc} ) +UNWIND( .save {fpreg, lr} ) +UNWIND( .setfp fpreg, sp ) + + ldr fpreg, [sp, #S_SP] @ Add our frame record + @ to the linked list +#if defined(CONFIG_UNWINDER_FRAME_POINTER) && defined(CONFIG_CC_IS_GCC) + ldr r1, [fp, #4] @ reload SP at entry + add fp, fp, #12 +#else + ldr r1, [fpreg, #8] +#endif + str r1, [sp, #S_SP] @ store in pt_regs + + @ Stash the regs for handle_bad_stack + mov r0, sp + + @ Time to die + bl handle_bad_stack + nop +UNWIND( .fnend ) +ENDPROC(__bad_stack) +#endif + + __INIT + +/* + * User helpers. + * + * Each segment is 32-byte aligned and will be moved to the top of the high + * vector page. New segments (if ever needed) must be added in front of + * existing ones. This mechanism should be used only for things that are + * really small and justified, and not be abused freely. + * + * See Documentation/arm/kernel_user_helpers.rst for formal definitions. + */ + THUMB( .arm ) + + .macro usr_ret, reg +#ifdef CONFIG_ARM_THUMB + bx \reg +#else + ret \reg +#endif + .endm + + .macro kuser_pad, sym, size + .if (. - \sym) & 3 + .rept 4 - (. - \sym) & 3 + .byte 0 + .endr + .endif + .rept (\size - (. - \sym)) / 4 + .word 0xe7fddef1 + .endr + .endm + +#ifdef CONFIG_KUSER_HELPERS + .align 5 + .globl __kuser_helper_start +__kuser_helper_start: + +/* + * Due to the length of some sequences, __kuser_cmpxchg64 spans 2 regular + * kuser "slots", therefore 0xffff0f80 is not used as a valid entry point. + */ + +__kuser_cmpxchg64: @ 0xffff0f60 + +#if defined(CONFIG_CPU_32v6K) + + stmfd sp!, {r4, r5, r6, r7} + ldrd r4, r5, [r0] @ load old val + ldrd r6, r7, [r1] @ load new val + smp_dmb arm +1: ldrexd r0, r1, [r2] @ load current val + eors r3, r0, r4 @ compare with oldval (1) + eorseq r3, r1, r5 @ compare with oldval (2) + strexdeq r3, r6, r7, [r2] @ store newval if eq + teqeq r3, #1 @ success? + beq 1b @ if no then retry + smp_dmb arm + rsbs r0, r3, #0 @ set returned val and C flag + ldmfd sp!, {r4, r5, r6, r7} + usr_ret lr + +#elif !defined(CONFIG_SMP) + +#ifdef CONFIG_MMU + + /* + * The only thing that can break atomicity in this cmpxchg64 + * implementation is either an IRQ or a data abort exception + * causing another process/thread to be scheduled in the middle of + * the critical sequence. The same strategy as for cmpxchg is used. + */ + stmfd sp!, {r4, r5, r6, lr} + ldmia r0, {r4, r5} @ load old val + ldmia r1, {r6, lr} @ load new val +1: ldmia r2, {r0, r1} @ load current val + eors r3, r0, r4 @ compare with oldval (1) + eorseq r3, r1, r5 @ compare with oldval (2) +2: stmiaeq r2, {r6, lr} @ store newval if eq + rsbs r0, r3, #0 @ set return val and C flag + ldmfd sp!, {r4, r5, r6, pc} + + .text +kuser_cmpxchg64_fixup: + @ Called from kuser_cmpxchg_fixup. + @ r4 = address of interrupted insn (must be preserved). + @ sp = saved regs. r7 and r8 are clobbered. + @ 1b = first critical insn, 2b = last critical insn. + @ If r4 >= 1b and r4 <= 2b then saved pc_usr is set to 1b. + mov r7, #0xffff0fff + sub r7, r7, #(0xffff0fff - (0xffff0f60 + (1b - __kuser_cmpxchg64))) + subs r8, r4, r7 + rsbscs r8, r8, #(2b - 1b) + strcs r7, [sp, #S_PC] +#if __LINUX_ARM_ARCH__ < 6 + bcc kuser_cmpxchg32_fixup +#endif + ret lr + .previous + +#else +#warning "NPTL on non MMU needs fixing" + mov r0, #-1 + adds r0, r0, #0 + usr_ret lr +#endif + +#else +#error "incoherent kernel configuration" +#endif + + kuser_pad __kuser_cmpxchg64, 64 + +__kuser_memory_barrier: @ 0xffff0fa0 + smp_dmb arm + usr_ret lr + + kuser_pad __kuser_memory_barrier, 32 + +__kuser_cmpxchg: @ 0xffff0fc0 + +#if __LINUX_ARM_ARCH__ < 6 + +#ifdef CONFIG_MMU + + /* + * The only thing that can break atomicity in this cmpxchg + * implementation is either an IRQ or a data abort exception + * causing another process/thread to be scheduled in the middle + * of the critical sequence. To prevent this, code is added to + * the IRQ and data abort exception handlers to set the pc back + * to the beginning of the critical section if it is found to be + * within that critical section (see kuser_cmpxchg_fixup). + */ +1: ldr r3, [r2] @ load current val + subs r3, r3, r0 @ compare with oldval +2: streq r1, [r2] @ store newval if eq + rsbs r0, r3, #0 @ set return val and C flag + usr_ret lr + + .text +kuser_cmpxchg32_fixup: + @ Called from kuser_cmpxchg_check macro. + @ r4 = address of interrupted insn (must be preserved). + @ sp = saved regs. r7 and r8 are clobbered. + @ 1b = first critical insn, 2b = last critical insn. + @ If r4 >= 1b and r4 <= 2b then saved pc_usr is set to 1b. + mov r7, #0xffff0fff + sub r7, r7, #(0xffff0fff - (0xffff0fc0 + (1b - __kuser_cmpxchg))) + subs r8, r4, r7 + rsbscs r8, r8, #(2b - 1b) + strcs r7, [sp, #S_PC] + ret lr + .previous + +#else +#warning "NPTL on non MMU needs fixing" + mov r0, #-1 + adds r0, r0, #0 + usr_ret lr +#endif + +#else + + smp_dmb arm +1: ldrex r3, [r2] + subs r3, r3, r0 + strexeq r3, r1, [r2] + teqeq r3, #1 + beq 1b + rsbs r0, r3, #0 + /* beware -- each __kuser slot must be 8 instructions max */ + ALT_SMP(b __kuser_memory_barrier) + ALT_UP(usr_ret lr) + +#endif + + kuser_pad __kuser_cmpxchg, 32 + +__kuser_get_tls: @ 0xffff0fe0 + ldr r0, [pc, #(16 - 8)] @ read TLS, set in kuser_get_tls_init + usr_ret lr + mrc p15, 0, r0, c13, c0, 3 @ 0xffff0fe8 hardware TLS code + kuser_pad __kuser_get_tls, 16 + .rep 3 + .word 0 @ 0xffff0ff0 software TLS value, then + .endr @ pad up to __kuser_helper_version + +__kuser_helper_version: @ 0xffff0ffc + .word ((__kuser_helper_end - __kuser_helper_start) >> 5) + + .globl __kuser_helper_end +__kuser_helper_end: + +#endif + + THUMB( .thumb ) + +/* + * Vector stubs. + * + * This code is copied to 0xffff1000 so we can use branches in the + * vectors, rather than ldr's. Note that this code must not exceed + * a page size. + * + * Common stub entry macro: + * Enter in IRQ mode, spsr = SVC/USR CPSR, lr = SVC/USR PC + * + * SP points to a minimal amount of processor-private memory, the address + * of which is copied into r0 for the mode specific abort handler. + */ + .macro vector_stub, name, mode, correction=0 + .align 5 +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +vector_bhb_bpiall_\name: + mcr p15, 0, r0, c7, c5, 6 @ BPIALL + @ isb not needed due to "movs pc, lr" in the vector stub + @ which gives a "context synchronisation". +#endif + +vector_\name: + .if \correction + sub lr, lr, #\correction + .endif + + @ Save r0, lr_<exception> (parent PC) + stmia sp, {r0, lr} @ save r0, lr + + @ Save spsr_<exception> (parent CPSR) +.Lvec_\name: + mrs lr, spsr + str lr, [sp, #8] @ save spsr + + @ + @ Prepare for SVC32 mode. IRQs remain disabled. + @ + mrs r0, cpsr + eor r0, r0, #(\mode ^ SVC_MODE | PSR_ISETSTATE) + msr spsr_cxsf, r0 + + @ + @ the branch table must immediately follow this code + @ + and lr, lr, #0x0f + THUMB( adr r0, 1f ) + THUMB( ldr lr, [r0, lr, lsl #2] ) + mov r0, sp + ARM( ldr lr, [pc, lr, lsl #2] ) + movs pc, lr @ branch to handler in SVC mode +ENDPROC(vector_\name) + +#ifdef CONFIG_HARDEN_BRANCH_HISTORY + .subsection 1 + .align 5 +vector_bhb_loop8_\name: + .if \correction + sub lr, lr, #\correction + .endif + + @ Save r0, lr_<exception> (parent PC) + stmia sp, {r0, lr} + + @ bhb workaround + mov r0, #8 +3: W(b) . + 4 + subs r0, r0, #1 + bne 3b + dsb nsh + @ isb not needed due to "movs pc, lr" in the vector stub + @ which gives a "context synchronisation". + b .Lvec_\name +ENDPROC(vector_bhb_loop8_\name) + .previous +#endif + + .align 2 + @ handler addresses follow this label +1: + .endm + + .section .stubs, "ax", %progbits + @ These need to remain at the start of the section so that + @ they are in range of the 'SWI' entries in the vector tables + @ located 4k down. +.L__vector_swi: + .word vector_swi +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +.L__vector_bhb_loop8_swi: + .word vector_bhb_loop8_swi +.L__vector_bhb_bpiall_swi: + .word vector_bhb_bpiall_swi +#endif + +vector_rst: + ARM( swi SYS_ERROR0 ) + THUMB( svc #0 ) + THUMB( nop ) + b vector_und + +/* + * Interrupt dispatcher + */ + vector_stub irq, IRQ_MODE, 4 + + .long __irq_usr @ 0 (USR_26 / USR_32) + .long __irq_invalid @ 1 (FIQ_26 / FIQ_32) + .long __irq_invalid @ 2 (IRQ_26 / IRQ_32) + .long __irq_svc @ 3 (SVC_26 / SVC_32) + .long __irq_invalid @ 4 + .long __irq_invalid @ 5 + .long __irq_invalid @ 6 + .long __irq_invalid @ 7 + .long __irq_invalid @ 8 + .long __irq_invalid @ 9 + .long __irq_invalid @ a + .long __irq_invalid @ b + .long __irq_invalid @ c + .long __irq_invalid @ d + .long __irq_invalid @ e + .long __irq_invalid @ f + +/* + * Data abort dispatcher + * Enter in ABT mode, spsr = USR CPSR, lr = USR PC + */ + vector_stub dabt, ABT_MODE, 8 + + .long __dabt_usr @ 0 (USR_26 / USR_32) + .long __dabt_invalid @ 1 (FIQ_26 / FIQ_32) + .long __dabt_invalid @ 2 (IRQ_26 / IRQ_32) + .long __dabt_svc @ 3 (SVC_26 / SVC_32) + .long __dabt_invalid @ 4 + .long __dabt_invalid @ 5 + .long __dabt_invalid @ 6 + .long __dabt_invalid @ 7 + .long __dabt_invalid @ 8 + .long __dabt_invalid @ 9 + .long __dabt_invalid @ a + .long __dabt_invalid @ b + .long __dabt_invalid @ c + .long __dabt_invalid @ d + .long __dabt_invalid @ e + .long __dabt_invalid @ f + +/* + * Prefetch abort dispatcher + * Enter in ABT mode, spsr = USR CPSR, lr = USR PC + */ + vector_stub pabt, ABT_MODE, 4 + + .long __pabt_usr @ 0 (USR_26 / USR_32) + .long __pabt_invalid @ 1 (FIQ_26 / FIQ_32) + .long __pabt_invalid @ 2 (IRQ_26 / IRQ_32) + .long __pabt_svc @ 3 (SVC_26 / SVC_32) + .long __pabt_invalid @ 4 + .long __pabt_invalid @ 5 + .long __pabt_invalid @ 6 + .long __pabt_invalid @ 7 + .long __pabt_invalid @ 8 + .long __pabt_invalid @ 9 + .long __pabt_invalid @ a + .long __pabt_invalid @ b + .long __pabt_invalid @ c + .long __pabt_invalid @ d + .long __pabt_invalid @ e + .long __pabt_invalid @ f + +/* + * Undef instr entry dispatcher + * Enter in UND mode, spsr = SVC/USR CPSR, lr = SVC/USR PC + */ + vector_stub und, UND_MODE + + .long __und_usr @ 0 (USR_26 / USR_32) + .long __und_invalid @ 1 (FIQ_26 / FIQ_32) + .long __und_invalid @ 2 (IRQ_26 / IRQ_32) + .long __und_svc @ 3 (SVC_26 / SVC_32) + .long __und_invalid @ 4 + .long __und_invalid @ 5 + .long __und_invalid @ 6 + .long __und_invalid @ 7 + .long __und_invalid @ 8 + .long __und_invalid @ 9 + .long __und_invalid @ a + .long __und_invalid @ b + .long __und_invalid @ c + .long __und_invalid @ d + .long __und_invalid @ e + .long __und_invalid @ f + + .align 5 + +/*============================================================================= + * Address exception handler + *----------------------------------------------------------------------------- + * These aren't too critical. + * (they're not supposed to happen, and won't happen in 32-bit data mode). + */ + +vector_addrexcptn: + b vector_addrexcptn + +/*============================================================================= + * FIQ "NMI" handler + *----------------------------------------------------------------------------- + * Handle a FIQ using the SVC stack allowing FIQ act like NMI on x86 + * systems. This must be the last vector stub, so lets place it in its own + * subsection. + */ + .subsection 2 + vector_stub fiq, FIQ_MODE, 4 + + .long __fiq_usr @ 0 (USR_26 / USR_32) + .long __fiq_svc @ 1 (FIQ_26 / FIQ_32) + .long __fiq_svc @ 2 (IRQ_26 / IRQ_32) + .long __fiq_svc @ 3 (SVC_26 / SVC_32) + .long __fiq_svc @ 4 + .long __fiq_svc @ 5 + .long __fiq_svc @ 6 + .long __fiq_abt @ 7 + .long __fiq_svc @ 8 + .long __fiq_svc @ 9 + .long __fiq_svc @ a + .long __fiq_svc @ b + .long __fiq_svc @ c + .long __fiq_svc @ d + .long __fiq_svc @ e + .long __fiq_svc @ f + + .globl vector_fiq + + .section .vectors, "ax", %progbits + W(b) vector_rst + W(b) vector_und +ARM( .reloc ., R_ARM_LDR_PC_G0, .L__vector_swi ) +THUMB( .reloc ., R_ARM_THM_PC12, .L__vector_swi ) + W(ldr) pc, . + W(b) vector_pabt + W(b) vector_dabt + W(b) vector_addrexcptn + W(b) vector_irq + W(b) vector_fiq + +#ifdef CONFIG_HARDEN_BRANCH_HISTORY + .section .vectors.bhb.loop8, "ax", %progbits + W(b) vector_rst + W(b) vector_bhb_loop8_und +ARM( .reloc ., R_ARM_LDR_PC_G0, .L__vector_bhb_loop8_swi ) +THUMB( .reloc ., R_ARM_THM_PC12, .L__vector_bhb_loop8_swi ) + W(ldr) pc, . + W(b) vector_bhb_loop8_pabt + W(b) vector_bhb_loop8_dabt + W(b) vector_addrexcptn + W(b) vector_bhb_loop8_irq + W(b) vector_bhb_loop8_fiq + + .section .vectors.bhb.bpiall, "ax", %progbits + W(b) vector_rst + W(b) vector_bhb_bpiall_und +ARM( .reloc ., R_ARM_LDR_PC_G0, .L__vector_bhb_bpiall_swi ) +THUMB( .reloc ., R_ARM_THM_PC12, .L__vector_bhb_bpiall_swi ) + W(ldr) pc, . + W(b) vector_bhb_bpiall_pabt + W(b) vector_bhb_bpiall_dabt + W(b) vector_addrexcptn + W(b) vector_bhb_bpiall_irq + W(b) vector_bhb_bpiall_fiq +#endif + + .data + .align 2 + + .globl cr_alignment +cr_alignment: + .space 4 diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S new file mode 100644 index 000000000..b413b541c --- /dev/null +++ b/arch/arm/kernel/entry-common.S @@ -0,0 +1,476 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/arch/arm/kernel/entry-common.S + * + * Copyright (C) 2000 Russell King + */ + +#include <asm/assembler.h> +#include <asm/unistd.h> +#include <asm/ftrace.h> +#include <asm/unwind.h> +#include <asm/memory.h> +#ifdef CONFIG_AEABI +#include <asm/unistd-oabi.h> +#endif + + .equ NR_syscalls, __NR_syscalls + + .macro arch_ret_to_user, tmp +#ifdef CONFIG_ARCH_IOP32X + mrc p15, 0, \tmp, c15, c1, 0 + tst \tmp, #(1 << 6) + bicne \tmp, \tmp, #(1 << 6) + mcrne p15, 0, \tmp, c15, c1, 0 @ Disable cp6 access +#endif + .endm + +#include "entry-header.S" + +saved_psr .req r8 +#if defined(CONFIG_TRACE_IRQFLAGS) || defined(CONFIG_CONTEXT_TRACKING_USER) +saved_pc .req r9 +#define TRACE(x...) x +#else +saved_pc .req lr +#define TRACE(x...) +#endif + + .section .entry.text,"ax",%progbits + .align 5 +#if !(IS_ENABLED(CONFIG_TRACE_IRQFLAGS) || IS_ENABLED(CONFIG_CONTEXT_TRACKING_USER) || \ + IS_ENABLED(CONFIG_DEBUG_RSEQ)) +/* + * This is the fast syscall return path. We do as little as possible here, + * such as avoiding writing r0 to the stack. We only use this path if we + * have tracing, context tracking and rseq debug disabled - the overheads + * from those features make this path too inefficient. + */ +ret_fast_syscall: +__ret_fast_syscall: + UNWIND(.fnstart ) + UNWIND(.cantunwind ) + disable_irq_notrace @ disable interrupts + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing + movs r1, r1, lsl #16 + bne fast_work_pending + + + /* perform architecture specific actions before user return */ + arch_ret_to_user r1 + + restore_user_regs fast = 1, offset = S_OFF + UNWIND(.fnend ) +ENDPROC(ret_fast_syscall) + + /* Ok, we need to do extra processing, enter the slow path. */ +fast_work_pending: + str r0, [sp, #S_R0+S_OFF]! @ returned r0 + /* fall through to work_pending */ +#else +/* + * The "replacement" ret_fast_syscall for when tracing, context tracking, + * or rseq debug is enabled. As we will need to call out to some C functions, + * we save r0 first to avoid needing to save registers around each C function + * call. + */ +ret_fast_syscall: +__ret_fast_syscall: + UNWIND(.fnstart ) + UNWIND(.cantunwind ) + str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 +#if IS_ENABLED(CONFIG_DEBUG_RSEQ) + /* do_rseq_syscall needs interrupts enabled. */ + mov r0, sp @ 'regs' + bl do_rseq_syscall +#endif + disable_irq_notrace @ disable interrupts + ldr r1, [tsk, #TI_FLAGS] @ re-check for syscall tracing + movs r1, r1, lsl #16 + beq no_work_pending + UNWIND(.fnend ) +ENDPROC(ret_fast_syscall) + + /* Slower path - fall through to work_pending */ +#endif + + tst r1, #_TIF_SYSCALL_WORK + bne __sys_trace_return_nosave +slow_work_pending: + mov r0, sp @ 'regs' + mov r2, why @ 'syscall' + bl do_work_pending + cmp r0, #0 + beq no_work_pending + movlt scno, #(__NR_restart_syscall - __NR_SYSCALL_BASE) + str scno, [tsk, #TI_ABI_SYSCALL] @ make sure tracers see update + ldmia sp, {r0 - r6} @ have to reload r0 - r6 + b local_restart @ ... and off we go +ENDPROC(ret_fast_syscall) + +/* + * "slow" syscall return path. "why" tells us if this was a real syscall. + * IRQs may be enabled here, so always disable them. Note that we use the + * "notrace" version to avoid calling into the tracing code unnecessarily. + * do_work_pending() will update this state if necessary. + */ +ENTRY(ret_to_user) +ret_slow_syscall: +#if IS_ENABLED(CONFIG_DEBUG_RSEQ) + /* do_rseq_syscall needs interrupts enabled. */ + enable_irq_notrace @ enable interrupts + mov r0, sp @ 'regs' + bl do_rseq_syscall +#endif + disable_irq_notrace @ disable interrupts +ENTRY(ret_to_user_from_irq) + ldr r1, [tsk, #TI_FLAGS] + movs r1, r1, lsl #16 + bne slow_work_pending +no_work_pending: + asm_trace_hardirqs_on save = 0 + + /* perform architecture specific actions before user return */ + arch_ret_to_user r1 + ct_user_enter save = 0 + + restore_user_regs fast = 0, offset = 0 +ENDPROC(ret_to_user_from_irq) +ENDPROC(ret_to_user) + +/* + * This is how we return from a fork. + */ +ENTRY(ret_from_fork) + bl schedule_tail + cmp r5, #0 + movne r0, r4 + badrne lr, 1f + retne r5 +1: get_thread_info tsk + b ret_slow_syscall +ENDPROC(ret_from_fork) + +/*============================================================================= + * SWI handler + *----------------------------------------------------------------------------- + */ + + .align 5 +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +ENTRY(vector_bhb_loop8_swi) + sub sp, sp, #PT_REGS_SIZE + stmia sp, {r0 - r12} + mov r8, #8 +1: b 2f +2: subs r8, r8, #1 + bne 1b + dsb nsh + isb + b 3f +ENDPROC(vector_bhb_loop8_swi) + + .align 5 +ENTRY(vector_bhb_bpiall_swi) + sub sp, sp, #PT_REGS_SIZE + stmia sp, {r0 - r12} + mcr p15, 0, r8, c7, c5, 6 @ BPIALL + isb + b 3f +ENDPROC(vector_bhb_bpiall_swi) +#endif + .align 5 +ENTRY(vector_swi) +#ifdef CONFIG_CPU_V7M + v7m_exception_entry +#else + sub sp, sp, #PT_REGS_SIZE + stmia sp, {r0 - r12} @ Calling r0 - r12 +3: + ARM( add r8, sp, #S_PC ) + ARM( stmdb r8, {sp, lr}^ ) @ Calling sp, lr + THUMB( mov r8, sp ) + THUMB( store_user_sp_lr r8, r10, S_SP ) @ calling sp, lr + mrs saved_psr, spsr @ called from non-FIQ mode, so ok. + TRACE( mov saved_pc, lr ) + str saved_pc, [sp, #S_PC] @ Save calling PC + str saved_psr, [sp, #S_PSR] @ Save CPSR + str r0, [sp, #S_OLD_R0] @ Save OLD_R0 +#endif + reload_current r10, ip + zero_fp + alignment_trap r10, ip, cr_alignment + asm_trace_hardirqs_on save=0 + enable_irq_notrace + ct_user_exit save=0 + + /* + * Get the system call number. + */ + +#if defined(CONFIG_OABI_COMPAT) + + /* + * If we have CONFIG_OABI_COMPAT then we need to look at the swi + * value to determine if it is an EABI or an old ABI call. + */ +#ifdef CONFIG_ARM_THUMB + tst saved_psr, #PSR_T_BIT + movne r10, #0 @ no thumb OABI emulation + USER( ldreq r10, [saved_pc, #-4] ) @ get SWI instruction +#else + USER( ldr r10, [saved_pc, #-4] ) @ get SWI instruction +#endif + ARM_BE8(rev r10, r10) @ little endian instruction + +#elif defined(CONFIG_AEABI) + + /* + * Pure EABI user space always put syscall number into scno (r7). + */ +#elif defined(CONFIG_ARM_THUMB) + /* Legacy ABI only, possibly thumb mode. */ + tst saved_psr, #PSR_T_BIT @ this is SPSR from save_user_regs + addne scno, r7, #__NR_SYSCALL_BASE @ put OS number in + USER( ldreq scno, [saved_pc, #-4] ) + +#else + /* Legacy ABI only. */ + USER( ldr scno, [saved_pc, #-4] ) @ get SWI instruction +#endif + + /* saved_psr and saved_pc are now dead */ + + uaccess_disable tbl + get_thread_info tsk + + adr tbl, sys_call_table @ load syscall table pointer + +#if defined(CONFIG_OABI_COMPAT) + /* + * If the swi argument is zero, this is an EABI call and we do nothing. + * + * If this is an old ABI call, get the syscall number into scno and + * get the old ABI syscall table address. + */ + bics r10, r10, #0xff000000 + strne r10, [tsk, #TI_ABI_SYSCALL] + streq scno, [tsk, #TI_ABI_SYSCALL] + eorne scno, r10, #__NR_OABI_SYSCALL_BASE + ldrne tbl, =sys_oabi_call_table +#elif !defined(CONFIG_AEABI) + bic scno, scno, #0xff000000 @ mask off SWI op-code + str scno, [tsk, #TI_ABI_SYSCALL] + eor scno, scno, #__NR_SYSCALL_BASE @ check OS number +#else + str scno, [tsk, #TI_ABI_SYSCALL] +#endif + /* + * Reload the registers that may have been corrupted on entry to + * the syscall assembly (by tracing or context tracking.) + */ + TRACE( ldmia sp, {r0 - r3} ) + +local_restart: + ldr r10, [tsk, #TI_FLAGS] @ check for syscall tracing + stmdb sp!, {r4, r5} @ push fifth and sixth args + + tst r10, #_TIF_SYSCALL_WORK @ are we tracing syscalls? + bne __sys_trace + + invoke_syscall tbl, scno, r10, __ret_fast_syscall + + add r1, sp, #S_OFF +2: cmp scno, #(__ARM_NR_BASE - __NR_SYSCALL_BASE) + eor r0, scno, #__NR_SYSCALL_BASE @ put OS number back + bcs arm_syscall + mov why, #0 @ no longer a real syscall + b sys_ni_syscall @ not private func + +#if defined(CONFIG_OABI_COMPAT) || !defined(CONFIG_AEABI) + /* + * We failed to handle a fault trying to access the page + * containing the swi instruction, but we're not really in a + * position to return -EFAULT. Instead, return back to the + * instruction and re-enter the user fault handling path trying + * to page it in. This will likely result in sending SEGV to the + * current task. + */ +9001: + sub lr, saved_pc, #4 + str lr, [sp, #S_PC] + get_thread_info tsk + b ret_fast_syscall +#endif +ENDPROC(vector_swi) + .ltorg + + /* + * This is the really slow path. We're going to be doing + * context switches, and waiting for our parent to respond. + */ +__sys_trace: + add r0, sp, #S_OFF + bl syscall_trace_enter + mov scno, r0 + invoke_syscall tbl, scno, r10, __sys_trace_return, reload=1 + cmp scno, #-1 @ skip the syscall? + bne 2b + add sp, sp, #S_OFF @ restore stack + +__sys_trace_return_nosave: + enable_irq_notrace + mov r0, sp + bl syscall_trace_exit + b ret_slow_syscall + +__sys_trace_return: + str r0, [sp, #S_R0 + S_OFF]! @ save returned r0 + mov r0, sp + bl syscall_trace_exit + b ret_slow_syscall + + .macro syscall_table_start, sym + .equ __sys_nr, 0 + .type \sym, #object +ENTRY(\sym) + .endm + + .macro syscall, nr, func + .ifgt __sys_nr - \nr + .error "Duplicated/unorded system call entry" + .endif + .rept \nr - __sys_nr + .long sys_ni_syscall + .endr + .long \func + .equ __sys_nr, \nr + 1 + .endm + + .macro syscall_table_end, sym + .ifgt __sys_nr - __NR_syscalls + .error "System call table too big" + .endif + .rept __NR_syscalls - __sys_nr + .long sys_ni_syscall + .endr + .size \sym, . - \sym + .endm + +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native) +#define __SYSCALL(nr, func) syscall nr, func + +/* + * This is the syscall table declaration for native ABI syscalls. + * With EABI a couple syscalls are obsolete and defined as sys_ni_syscall. + */ + syscall_table_start sys_call_table +#ifdef CONFIG_AEABI +#include <calls-eabi.S> +#else +#include <calls-oabi.S> +#endif + syscall_table_end sys_call_table + +/*============================================================================ + * Special system call wrappers + */ +@ r0 = syscall number +@ r8 = syscall table +sys_syscall: + bic scno, r0, #__NR_OABI_SYSCALL_BASE + cmp scno, #__NR_syscall - __NR_SYSCALL_BASE + cmpne scno, #NR_syscalls @ check range +#ifdef CONFIG_CPU_SPECTRE + movhs scno, #0 + csdb +#endif + stmialo sp, {r5, r6} @ shuffle args + movlo r0, r1 + movlo r1, r2 + movlo r2, r3 + movlo r3, r4 + ldrlo pc, [tbl, scno, lsl #2] + b sys_ni_syscall +ENDPROC(sys_syscall) + +sys_sigreturn_wrapper: + add r0, sp, #S_OFF + mov why, #0 @ prevent syscall restart handling + b sys_sigreturn +ENDPROC(sys_sigreturn_wrapper) + +sys_rt_sigreturn_wrapper: + add r0, sp, #S_OFF + mov why, #0 @ prevent syscall restart handling + b sys_rt_sigreturn +ENDPROC(sys_rt_sigreturn_wrapper) + +sys_statfs64_wrapper: + teq r1, #88 + moveq r1, #84 + b sys_statfs64 +ENDPROC(sys_statfs64_wrapper) + +sys_fstatfs64_wrapper: + teq r1, #88 + moveq r1, #84 + b sys_fstatfs64 +ENDPROC(sys_fstatfs64_wrapper) + +/* + * Note: off_4k (r5) is always units of 4K. If we can't do the requested + * offset, we return EINVAL. + */ +sys_mmap2: + str r5, [sp, #4] + b sys_mmap_pgoff +ENDPROC(sys_mmap2) + +#ifdef CONFIG_OABI_COMPAT + +/* + * These are syscalls with argument register differences + */ + +sys_oabi_pread64: + stmia sp, {r3, r4} + b sys_pread64 +ENDPROC(sys_oabi_pread64) + +sys_oabi_pwrite64: + stmia sp, {r3, r4} + b sys_pwrite64 +ENDPROC(sys_oabi_pwrite64) + +sys_oabi_truncate64: + mov r3, r2 + mov r2, r1 + b sys_truncate64 +ENDPROC(sys_oabi_truncate64) + +sys_oabi_ftruncate64: + mov r3, r2 + mov r2, r1 + b sys_ftruncate64 +ENDPROC(sys_oabi_ftruncate64) + +sys_oabi_readahead: + str r3, [sp] + mov r3, r2 + mov r2, r1 + b sys_readahead +ENDPROC(sys_oabi_readahead) + +/* + * Let's declare a second syscall table for old ABI binaries + * using the compatibility syscall entries. + */ + syscall_table_start sys_oabi_call_table +#undef __SYSCALL_WITH_COMPAT +#define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, compat) +#include <calls-oabi.S> + syscall_table_end sys_oabi_call_table + +#endif + diff --git a/arch/arm/kernel/entry-ftrace.S b/arch/arm/kernel/entry-ftrace.S new file mode 100644 index 000000000..3e7bcaca5 --- /dev/null +++ b/arch/arm/kernel/entry-ftrace.S @@ -0,0 +1,288 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#include <asm/assembler.h> +#include <asm/ftrace.h> +#include <asm/unwind.h> + +#include "entry-header.S" + +/* + * When compiling with -pg, gcc inserts a call to the mcount routine at the + * start of every function. In mcount, apart from the function's address (in + * lr), we need to get hold of the function's caller's address. + * + * Newer GCCs (4.4+) solve this problem by using a version of mcount with call + * sites like: + * + * push {lr} + * bl __gnu_mcount_nc + * + * With these compilers, frame pointers are not necessary. + * + * mcount can be thought of as a function called in the middle of a subroutine + * call. As such, it needs to be transparent for both the caller and the + * callee: the original lr needs to be restored when leaving mcount, and no + * registers should be clobbered. + * + * When using dynamic ftrace, we patch out the mcount call by a "add sp, #4" + * instead of the __gnu_mcount_nc call (see arch/arm/kernel/ftrace.c). + */ + +.macro mcount_adjust_addr rd, rn + bic \rd, \rn, #1 @ clear the Thumb bit if present + sub \rd, \rd, #MCOUNT_INSN_SIZE +.endm + +.macro __mcount suffix + mcount_enter + ldr_va r2, ftrace_trace_function + badr r0, .Lftrace_stub + cmp r0, r2 + bne 1f + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + ldr_va r2, ftrace_graph_return + cmp r0, r2 + bne ftrace_graph_caller\suffix + + ldr_va r2, ftrace_graph_entry + mov_l r0, ftrace_graph_entry_stub + cmp r0, r2 + bne ftrace_graph_caller\suffix +#endif + + mcount_exit + +1: mcount_get_lr r1 @ lr of instrumented func + mcount_adjust_addr r0, lr @ instrumented function + badr lr, 2f + mov pc, r2 +2: mcount_exit +.endm + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + +.macro __ftrace_regs_caller + + str lr, [sp, #-8]! @ store LR as PC and make space for CPSR/OLD_R0, + @ OLD_R0 will overwrite previous LR + + ldr lr, [sp, #8] @ get previous LR + + str r0, [sp, #8] @ write r0 as OLD_R0 over previous LR + + str lr, [sp, #-4]! @ store previous LR as LR + + add lr, sp, #16 @ move in LR the value of SP as it was + @ before the push {lr} of the mcount mechanism + + push {r0-r11, ip, lr} + + @ stack content at this point: + @ 0 4 48 52 56 60 64 68 72 + @ R0 | R1 | ... | IP | SP + 4 | previous LR | LR | PSR | OLD_R0 | + + mov r3, sp @ struct pt_regs* + + ldr_va r2, function_trace_op @ pointer to the current + @ function tracing op + + ldr r1, [sp, #S_LR] @ lr of instrumented func + + ldr lr, [sp, #S_PC] @ get LR + + mcount_adjust_addr r0, lr @ instrumented function + + .globl ftrace_regs_call +ftrace_regs_call: + bl ftrace_stub + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + .globl ftrace_graph_regs_call +ftrace_graph_regs_call: +ARM( mov r0, r0 ) +THUMB( nop.w ) +#endif + + @ pop saved regs + pop {r0-r11, ip, lr} @ restore r0 through r12 + ldr lr, [sp], #4 @ restore LR + ldr pc, [sp], #12 +.endm + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +.macro __ftrace_graph_regs_caller + +#ifdef CONFIG_UNWINDER_FRAME_POINTER + sub r0, fp, #4 @ lr of instrumented routine (parent) +#else + add r0, sp, #S_LR +#endif + + @ called from __ftrace_regs_caller + ldr r1, [sp, #S_PC] @ instrumented routine (func) + mcount_adjust_addr r1, r1 + + mov r2, fpreg @ frame pointer + add r3, sp, #PT_REGS_SIZE + bl prepare_ftrace_return + + @ pop registers saved in ftrace_regs_caller + pop {r0-r11, ip, lr} @ restore r0 through r12 + ldr lr, [sp], #4 @ restore LR + ldr pc, [sp], #12 + +.endm +#endif +#endif + +.macro __ftrace_caller suffix + mcount_enter + + mcount_get_lr r1 @ lr of instrumented func + mcount_adjust_addr r0, lr @ instrumented function + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + ldr_va r2, function_trace_op @ pointer to the current + @ function tracing op + mov r3, #0 @ regs is NULL +#endif + + .globl ftrace_call\suffix +ftrace_call\suffix: + bl ftrace_stub + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER + .globl ftrace_graph_call\suffix +ftrace_graph_call\suffix: +ARM( mov r0, r0 ) +THUMB( nop.w ) +#endif + + mcount_exit +.endm + +.macro __ftrace_graph_caller +#ifdef CONFIG_UNWINDER_FRAME_POINTER + sub r0, fp, #4 @ &lr of instrumented routine (&parent) +#else + add r0, sp, #20 +#endif +#ifdef CONFIG_DYNAMIC_FTRACE + @ called from __ftrace_caller, saved in mcount_enter + ldr r1, [sp, #16] @ instrumented routine (func) + mcount_adjust_addr r1, r1 +#else + @ called from __mcount, untouched in lr + mcount_adjust_addr r1, lr @ instrumented routine (func) +#endif + mov r2, fpreg @ frame pointer + add r3, sp, #24 + bl prepare_ftrace_return + mcount_exit +.endm + +/* + * __gnu_mcount_nc + */ + +.macro mcount_enter +/* + * This pad compensates for the push {lr} at the call site. Note that we are + * unable to unwind through a function which does not otherwise save its lr. + */ + UNWIND(.pad #4) + stmdb sp!, {r0-r3, lr} + UNWIND(.save {r0-r3, lr}) +.endm + +.macro mcount_get_lr reg + ldr \reg, [sp, #20] +.endm + +.macro mcount_exit + ldmia sp!, {r0-r3} + ldr lr, [sp, #4] + ldr pc, [sp], #8 +.endm + +ENTRY(__gnu_mcount_nc) +UNWIND(.fnstart) +#ifdef CONFIG_DYNAMIC_FTRACE + push {lr} + ldr lr, [sp, #4] + ldr pc, [sp], #8 +#else + __mcount +#endif +UNWIND(.fnend) +ENDPROC(__gnu_mcount_nc) + +#ifdef CONFIG_DYNAMIC_FTRACE +ENTRY(ftrace_caller) +UNWIND(.fnstart) + __ftrace_caller +UNWIND(.fnend) +ENDPROC(ftrace_caller) + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +ENTRY(ftrace_regs_caller) +UNWIND(.fnstart) + __ftrace_regs_caller +UNWIND(.fnend) +ENDPROC(ftrace_regs_caller) +#endif + +#endif + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(ftrace_graph_caller) +UNWIND(.fnstart) + __ftrace_graph_caller +UNWIND(.fnend) +ENDPROC(ftrace_graph_caller) + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS +ENTRY(ftrace_graph_regs_caller) +UNWIND(.fnstart) + __ftrace_graph_regs_caller +UNWIND(.fnend) +ENDPROC(ftrace_graph_regs_caller) +#endif +#endif + +.purgem mcount_enter +.purgem mcount_get_lr +.purgem mcount_exit + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +ENTRY(return_to_handler) + stmdb sp!, {r0-r3} + add r0, sp, #16 @ sp at exit of instrumented routine + bl ftrace_return_to_handler + mov lr, r0 @ r0 has real ret addr + ldmia sp!, {r0-r3} + ret lr +ENDPROC(return_to_handler) +#endif + +ENTRY(ftrace_stub) +.Lftrace_stub: + ret lr +ENDPROC(ftrace_stub) + +#ifdef CONFIG_DYNAMIC_FTRACE + + __INIT + + .macro init_tramp, dst:req +ENTRY(\dst\()_from_init) + ldr pc, =\dst +ENDPROC(\dst\()_from_init) + .endm + + init_tramp ftrace_caller +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + init_tramp ftrace_regs_caller +#endif +#endif diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S new file mode 100644 index 000000000..99411fa91 --- /dev/null +++ b/arch/arm/kernel/entry-header.S @@ -0,0 +1,467 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/init.h> +#include <linux/linkage.h> + +#include <asm/assembler.h> +#include <asm/asm-offsets.h> +#include <asm/errno.h> +#include <asm/thread_info.h> +#include <asm/uaccess-asm.h> +#include <asm/v7m.h> + +@ Bad Abort numbers +@ ----------------- +@ +#define BAD_PREFETCH 0 +#define BAD_DATA 1 +#define BAD_ADDREXCPTN 2 +#define BAD_IRQ 3 +#define BAD_UNDEFINSTR 4 + +@ +@ Most of the stack format comes from struct pt_regs, but with +@ the addition of 8 bytes for storing syscall args 5 and 6. +@ This _must_ remain a multiple of 8 for EABI. +@ +#define S_OFF 8 + +/* + * The SWI code relies on the fact that R0 is at the bottom of the stack + * (due to slow/fast restore user regs). + */ +#if S_R0 != 0 +#error "Please fix" +#endif + + .macro zero_fp +#ifdef CONFIG_FRAME_POINTER + mov fp, #0 +#endif + .endm + +#ifdef CONFIG_ALIGNMENT_TRAP +#define ATRAP(x...) x +#else +#define ATRAP(x...) +#endif + + .macro alignment_trap, rtmp1, rtmp2, label +#ifdef CONFIG_ALIGNMENT_TRAP + mrc p15, 0, \rtmp2, c1, c0, 0 + ldr_va \rtmp1, \label + teq \rtmp1, \rtmp2 + mcrne p15, 0, \rtmp1, c1, c0, 0 +#endif + .endm + +#ifdef CONFIG_CPU_V7M +/* + * ARMv7-M exception entry/exit macros. + * + * xPSR, ReturnAddress(), LR (R14), R12, R3, R2, R1, and R0 are + * automatically saved on the current stack (32 words) before + * switching to the exception stack (SP_main). + * + * If exception is taken while in user mode, SP_main is + * empty. Otherwise, SP_main is aligned to 64 bit automatically + * (CCR.STKALIGN set). + * + * Linux assumes that the interrupts are disabled when entering an + * exception handler and it may BUG if this is not the case. Interrupts + * are disabled during entry and reenabled in the exit macro. + * + * v7m_exception_slow_exit is used when returning from SVC or PendSV. + * When returning to kernel mode, we don't return from exception. + */ + .macro v7m_exception_entry + @ determine the location of the registers saved by the core during + @ exception entry. Depending on the mode the cpu was in when the + @ exception happend that is either on the main or the process stack. + @ Bit 2 of EXC_RETURN stored in the lr register specifies which stack + @ was used. + tst lr, #EXC_RET_STACK_MASK + mrsne r12, psp + moveq r12, sp + + @ we cannot rely on r0-r3 and r12 matching the value saved in the + @ exception frame because of tail-chaining. So these have to be + @ reloaded. + ldmia r12!, {r0-r3} + + @ Linux expects to have irqs off. Do it here before taking stack space + cpsid i + + sub sp, #PT_REGS_SIZE-S_IP + stmdb sp!, {r0-r11} + + @ load saved r12, lr, return address and xPSR. + @ r0-r7 are used for signals and never touched from now on. Clobbering + @ r8-r12 is OK. + mov r9, r12 + ldmia r9!, {r8, r10-r12} + + @ calculate the original stack pointer value. + @ r9 currently points to the memory location just above the auto saved + @ xPSR. + @ The cpu might automatically 8-byte align the stack. Bit 9 + @ of the saved xPSR specifies if stack aligning took place. In this case + @ another 32-bit value is included in the stack. + + tst r12, V7M_xPSR_FRAMEPTRALIGN + addne r9, r9, #4 + + @ store saved r12 using str to have a register to hold the base for stm + str r8, [sp, #S_IP] + add r8, sp, #S_SP + @ store r13-r15, xPSR + stmia r8!, {r9-r12} + @ store old_r0 + str r0, [r8] + .endm + + /* + * PENDSV and SVCALL are configured to have the same exception + * priorities. As a kernel thread runs at SVCALL execution priority it + * can never be preempted and so we will never have to return to a + * kernel thread here. + */ + .macro v7m_exception_slow_exit ret_r0 + cpsid i + ldr lr, =exc_ret + ldr lr, [lr] + + @ read original r12, sp, lr, pc and xPSR + add r12, sp, #S_IP + ldmia r12, {r1-r5} + + @ an exception frame is always 8-byte aligned. To tell the hardware if + @ the sp to be restored is aligned or not set bit 9 of the saved xPSR + @ accordingly. + tst r2, #4 + subne r2, r2, #4 + orrne r5, V7M_xPSR_FRAMEPTRALIGN + biceq r5, V7M_xPSR_FRAMEPTRALIGN + + @ ensure bit 0 is cleared in the PC, otherwise behaviour is + @ unpredictable + bic r4, #1 + + @ write basic exception frame + stmdb r2!, {r1, r3-r5} + ldmia sp, {r1, r3-r5} + .if \ret_r0 + stmdb r2!, {r0, r3-r5} + .else + stmdb r2!, {r1, r3-r5} + .endif + + @ restore process sp + msr psp, r2 + + @ restore original r4-r11 + ldmia sp!, {r0-r11} + + @ restore main sp + add sp, sp, #PT_REGS_SIZE-S_IP + + cpsie i + bx lr + .endm +#endif /* CONFIG_CPU_V7M */ + + @ + @ Store/load the USER SP and LR registers by switching to the SYS + @ mode. Useful in Thumb-2 mode where "stm/ldm rd, {sp, lr}^" is not + @ available. Should only be called from SVC mode + @ + .macro store_user_sp_lr, rd, rtemp, offset = 0 + mrs \rtemp, cpsr + eor \rtemp, \rtemp, #(SVC_MODE ^ SYSTEM_MODE) + msr cpsr_c, \rtemp @ switch to the SYS mode + + str sp, [\rd, #\offset] @ save sp_usr + str lr, [\rd, #\offset + 4] @ save lr_usr + + eor \rtemp, \rtemp, #(SVC_MODE ^ SYSTEM_MODE) + msr cpsr_c, \rtemp @ switch back to the SVC mode + .endm + + .macro load_user_sp_lr, rd, rtemp, offset = 0 + mrs \rtemp, cpsr + eor \rtemp, \rtemp, #(SVC_MODE ^ SYSTEM_MODE) + msr cpsr_c, \rtemp @ switch to the SYS mode + + ldr sp, [\rd, #\offset] @ load sp_usr + ldr lr, [\rd, #\offset + 4] @ load lr_usr + + eor \rtemp, \rtemp, #(SVC_MODE ^ SYSTEM_MODE) + msr cpsr_c, \rtemp @ switch back to the SVC mode + .endm + + + .macro svc_exit, rpsr, irq = 0 + .if \irq != 0 + @ IRQs already off +#ifdef CONFIG_TRACE_IRQFLAGS + @ The parent context IRQs must have been enabled to get here in + @ the first place, so there's no point checking the PSR I bit. + bl trace_hardirqs_on +#endif + .else + @ IRQs off again before pulling preserved data off the stack + disable_irq_notrace +#ifdef CONFIG_TRACE_IRQFLAGS + tst \rpsr, #PSR_I_BIT + bleq trace_hardirqs_on + tst \rpsr, #PSR_I_BIT + blne trace_hardirqs_off +#endif + .endif + uaccess_exit tsk, r0, r1 + +#ifndef CONFIG_THUMB2_KERNEL + @ ARM mode SVC restore + msr spsr_cxsf, \rpsr +#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K) + @ We must avoid clrex due to Cortex-A15 erratum #830321 + sub r0, sp, #4 @ uninhabited address + strex r1, r2, [r0] @ clear the exclusive monitor +#endif + ldmia sp, {r0 - pc}^ @ load r0 - pc, cpsr +#else + @ Thumb mode SVC restore + ldr lr, [sp, #S_SP] @ top of the stack + ldrd r0, r1, [sp, #S_LR] @ calling lr and pc + + @ We must avoid clrex due to Cortex-A15 erratum #830321 + strex r2, r1, [sp, #S_LR] @ clear the exclusive monitor + + stmdb lr!, {r0, r1, \rpsr} @ calling lr and rfe context + ldmia sp, {r0 - r12} + mov sp, lr + ldr lr, [sp], #4 + rfeia sp! +#endif + .endm + + @ + @ svc_exit_via_fiq - like svc_exit but switches to FIQ mode before exit + @ + @ This macro acts in a similar manner to svc_exit but switches to FIQ + @ mode to restore the final part of the register state. + @ + @ We cannot use the normal svc_exit procedure because that would + @ clobber spsr_svc (FIQ could be delivered during the first few + @ instructions of vector_swi meaning its contents have not been + @ saved anywhere). + @ + @ Note that, unlike svc_exit, this macro also does not allow a caller + @ supplied rpsr. This is because the FIQ exceptions are not re-entrant + @ and the handlers cannot call into the scheduler (meaning the value + @ on the stack remains correct). + @ + .macro svc_exit_via_fiq + uaccess_exit tsk, r0, r1 +#ifndef CONFIG_THUMB2_KERNEL + @ ARM mode restore + mov r0, sp + ldmib r0, {r1 - r14} @ abort is deadly from here onward (it will + @ clobber state restored below) + msr cpsr_c, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT + add r8, r0, #S_PC + ldr r9, [r0, #S_PSR] + msr spsr_cxsf, r9 + ldr r0, [r0, #S_R0] + ldmia r8, {pc}^ +#else + @ Thumb mode restore + add r0, sp, #S_R2 + ldr lr, [sp, #S_LR] + ldr sp, [sp, #S_SP] @ abort is deadly from here onward (it will + @ clobber state restored below) + ldmia r0, {r2 - r12} + mov r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT + msr cpsr_c, r1 + sub r0, #S_R2 + add r8, r0, #S_PC + ldmia r0, {r0 - r1} + rfeia r8 +#endif + .endm + + + .macro restore_user_regs, fast = 0, offset = 0 +#if defined(CONFIG_CPU_32v6K) && \ + (!defined(CONFIG_CPU_V6) || defined(CONFIG_SMP)) +#ifdef CONFIG_CPU_V6 +ALT_SMP(nop) +ALT_UP_B(.L1_\@) +#endif + @ The TLS register update is deferred until return to user space so we + @ can use it for other things while running in the kernel + mrc p15, 0, r1, c13, c0, 3 @ get current_thread_info pointer + ldr r1, [r1, #TI_TP_VALUE] + mcr p15, 0, r1, c13, c0, 3 @ set TLS register +.L1_\@: +#endif + + uaccess_enable r1, isb=0 +#ifndef CONFIG_THUMB2_KERNEL + @ ARM mode restore + mov r2, sp + ldr r1, [r2, #\offset + S_PSR] @ get calling cpsr + ldr lr, [r2, #\offset + S_PC]! @ get pc + tst r1, #PSR_I_BIT | 0x0f + bne 1f + msr spsr_cxsf, r1 @ save in spsr_svc +#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K) + @ We must avoid clrex due to Cortex-A15 erratum #830321 + strex r1, r2, [r2] @ clear the exclusive monitor +#endif + .if \fast + ldmdb r2, {r1 - lr}^ @ get calling r1 - lr + .else + ldmdb r2, {r0 - lr}^ @ get calling r0 - lr + .endif + mov r0, r0 @ ARMv5T and earlier require a nop + @ after ldm {}^ + add sp, sp, #\offset + PT_REGS_SIZE + movs pc, lr @ return & move spsr_svc into cpsr +1: bug "Returning to usermode but unexpected PSR bits set?", \@ +#elif defined(CONFIG_CPU_V7M) + @ V7M restore. + @ Note that we don't need to do clrex here as clearing the local + @ monitor is part of the exception entry and exit sequence. + .if \offset + add sp, #\offset + .endif + v7m_exception_slow_exit ret_r0 = \fast +#else + @ Thumb mode restore + mov r2, sp + load_user_sp_lr r2, r3, \offset + S_SP @ calling sp, lr + ldr r1, [sp, #\offset + S_PSR] @ get calling cpsr + ldr lr, [sp, #\offset + S_PC] @ get pc + add sp, sp, #\offset + S_SP + tst r1, #PSR_I_BIT | 0x0f + bne 1f + msr spsr_cxsf, r1 @ save in spsr_svc + + @ We must avoid clrex due to Cortex-A15 erratum #830321 + strex r1, r2, [sp] @ clear the exclusive monitor + + .if \fast + ldmdb sp, {r1 - r12} @ get calling r1 - r12 + .else + ldmdb sp, {r0 - r12} @ get calling r0 - r12 + .endif + add sp, sp, #PT_REGS_SIZE - S_SP + movs pc, lr @ return & move spsr_svc into cpsr +1: bug "Returning to usermode but unexpected PSR bits set?", \@ +#endif /* !CONFIG_THUMB2_KERNEL */ + .endm + +/* + * Context tracking subsystem. Used to instrument transitions + * between user and kernel mode. + */ + .macro ct_user_exit, save = 1 +#ifdef CONFIG_CONTEXT_TRACKING_USER + .if \save + stmdb sp!, {r0-r3, ip, lr} + bl user_exit_callable + ldmia sp!, {r0-r3, ip, lr} + .else + bl user_exit_callable + .endif +#endif + .endm + + .macro ct_user_enter, save = 1 +#ifdef CONFIG_CONTEXT_TRACKING_USER + .if \save + stmdb sp!, {r0-r3, ip, lr} + bl user_enter_callable + ldmia sp!, {r0-r3, ip, lr} + .else + bl user_enter_callable + .endif +#endif + .endm + + .macro invoke_syscall, table, nr, tmp, ret, reload=0 +#ifdef CONFIG_CPU_SPECTRE + mov \tmp, \nr + cmp \tmp, #NR_syscalls @ check upper syscall limit + movcs \tmp, #0 + csdb + badr lr, \ret @ return address + .if \reload + add r1, sp, #S_R0 + S_OFF @ pointer to regs + ldmiacc r1, {r0 - r6} @ reload r0-r6 + stmiacc sp, {r4, r5} @ update stack arguments + .endif + ldrcc pc, [\table, \tmp, lsl #2] @ call sys_* routine +#else + cmp \nr, #NR_syscalls @ check upper syscall limit + badr lr, \ret @ return address + .if \reload + add r1, sp, #S_R0 + S_OFF @ pointer to regs + ldmiacc r1, {r0 - r6} @ reload r0-r6 + stmiacc sp, {r4, r5} @ update stack arguments + .endif + ldrcc pc, [\table, \nr, lsl #2] @ call sys_* routine +#endif + .endm + +/* + * These are the registers used in the syscall handler, and allow us to + * have in theory up to 7 arguments to a function - r0 to r6. + * + * r7 is reserved for the system call number for thumb mode. + * + * Note that tbl == why is intentional. + * + * We must set at least "tsk" and "why" when calling ret_with_reschedule. + */ +scno .req r7 @ syscall number +tbl .req r8 @ syscall table pointer +why .req r8 @ Linux syscall (!= 0) +tsk .req r9 @ current thread_info + + .macro do_overflow_check, frame_size:req +#ifdef CONFIG_VMAP_STACK + @ + @ Test whether the SP has overflowed. Task and IRQ stacks are aligned + @ so that SP & BIT(THREAD_SIZE_ORDER + PAGE_SHIFT) should always be + @ zero. + @ +ARM( tst sp, #1 << (THREAD_SIZE_ORDER + PAGE_SHIFT) ) +THUMB( tst r1, #1 << (THREAD_SIZE_ORDER + PAGE_SHIFT) ) +THUMB( it ne ) + bne .Lstack_overflow_check\@ + + .pushsection .text +.Lstack_overflow_check\@: + @ + @ The stack pointer is not pointing to a valid vmap'ed stack, but it + @ may be pointing into the linear map instead, which may happen if we + @ are already running from the overflow stack. We cannot detect overflow + @ in such cases so just carry on. + @ + str ip, [r0, #12] @ Stash IP on the mode stack + ldr_va ip, high_memory @ Start of VMALLOC space +ARM( cmp sp, ip ) @ SP in vmalloc space? +THUMB( cmp r1, ip ) +THUMB( itt lo ) + ldrlo ip, [r0, #12] @ Restore IP + blo .Lout\@ @ Carry on + +THUMB( sub r1, sp, r1 ) @ Restore original R1 +THUMB( sub sp, r1 ) @ Restore original SP + add sp, sp, #\frame_size @ Undo svc_entry's SP change + b __bad_stack @ Handle VMAP stack overflow + .popsection +.Lout\@: +#endif + .endm diff --git a/arch/arm/kernel/entry-v7m.S b/arch/arm/kernel/entry-v7m.S new file mode 100644 index 000000000..de8a60363 --- /dev/null +++ b/arch/arm/kernel/entry-v7m.S @@ -0,0 +1,160 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/arch/arm/kernel/entry-v7m.S + * + * Copyright (C) 2008 ARM Ltd. + * + * Low-level vector interface routines for the ARMv7-M architecture + */ +#include <asm/memory.h> +#include <asm/glue.h> +#include <asm/thread_notify.h> +#include <asm/v7m.h> + +#include "entry-header.S" + +#ifdef CONFIG_TRACE_IRQFLAGS +#error "CONFIG_TRACE_IRQFLAGS not supported on the current ARMv7M implementation" +#endif + +__invalid_entry: + v7m_exception_entry +#ifdef CONFIG_PRINTK + adr r0, strerr + mrs r1, ipsr + mov r2, lr + bl _printk +#endif + mov r0, sp + bl show_regs +1: b 1b +ENDPROC(__invalid_entry) + +strerr: .asciz "\nUnhandled exception: IPSR = %08lx LR = %08lx\n" + + .align 2 +__irq_entry: + v7m_exception_entry + + @ + @ Invoke the IRQ handler + @ + mov r0, sp + ldr_this_cpu sp, irq_stack_ptr, r1, r2 + + @ + @ If we took the interrupt while running in the kernel, we may already + @ be using the IRQ stack, so revert to the original value in that case. + @ + subs r2, sp, r0 @ SP above bottom of IRQ stack? + rsbscs r2, r2, #THREAD_SIZE @ ... and below the top? + movcs sp, r0 + + push {r0, lr} @ preserve LR and original SP + + @ routine called with r0 = struct pt_regs * + bl generic_handle_arch_irq + + pop {r0, lr} + mov sp, r0 + + @ + @ Check for any pending work if returning to user + @ + ldr r1, =BASEADDR_V7M_SCB + ldr r0, [r1, V7M_SCB_ICSR] + tst r0, V7M_SCB_ICSR_RETTOBASE + beq 2f + + get_thread_info tsk + ldr r2, [tsk, #TI_FLAGS] + movs r2, r2, lsl #16 + beq 2f @ no work pending + mov r0, #V7M_SCB_ICSR_PENDSVSET + str r0, [r1, V7M_SCB_ICSR] @ raise PendSV + +2: + @ registers r0-r3 and r12 are automatically restored on exception + @ return. r4-r7 were not clobbered in v7m_exception_entry so for + @ correctness they don't need to be restored. So only r8-r11 must be + @ restored here. The easiest way to do so is to restore r0-r7, too. + ldmia sp!, {r0-r11} + add sp, #PT_REGS_SIZE-S_IP + cpsie i + bx lr +ENDPROC(__irq_entry) + +__pendsv_entry: + v7m_exception_entry + + ldr r1, =BASEADDR_V7M_SCB + mov r0, #V7M_SCB_ICSR_PENDSVCLR + str r0, [r1, V7M_SCB_ICSR] @ clear PendSV + + @ execute the pending work, including reschedule + get_thread_info tsk + mov why, #0 + b ret_to_user_from_irq +ENDPROC(__pendsv_entry) + +/* + * Register switch for ARMv7-M processors. + * r0 = previous task_struct, r1 = previous thread_info, r2 = next thread_info + * previous and next are guaranteed not to be the same. + */ +ENTRY(__switch_to) + .fnstart + .cantunwind + add ip, r1, #TI_CPU_SAVE + stmia ip!, {r4 - r11} @ Store most regs on stack + str sp, [ip], #4 + str lr, [ip], #4 + mov r5, r0 + mov r6, r2 @ Preserve 'next' + add r4, r2, #TI_CPU_SAVE + ldr r0, =thread_notify_head + mov r1, #THREAD_NOTIFY_SWITCH + bl atomic_notifier_call_chain + mov r0, r5 + mov r1, r6 + ldmia r4, {r4 - r12, lr} @ Load all regs saved previously + set_current r1, r2 + mov sp, ip + bx lr + .fnend +ENDPROC(__switch_to) + + .data +#if CONFIG_CPU_V7M_NUM_IRQ <= 112 + .align 9 +#else + .align 10 +#endif + +/* + * Vector table (Natural alignment need to be ensured) + */ +ENTRY(vector_table) + .long 0 @ 0 - Reset stack pointer + .long __invalid_entry @ 1 - Reset + .long __invalid_entry @ 2 - NMI + .long __invalid_entry @ 3 - HardFault + .long __invalid_entry @ 4 - MemManage + .long __invalid_entry @ 5 - BusFault + .long __invalid_entry @ 6 - UsageFault + .long __invalid_entry @ 7 - Reserved + .long __invalid_entry @ 8 - Reserved + .long __invalid_entry @ 9 - Reserved + .long __invalid_entry @ 10 - Reserved + .long vector_swi @ 11 - SVCall + .long __invalid_entry @ 12 - Debug Monitor + .long __invalid_entry @ 13 - Reserved + .long __pendsv_entry @ 14 - PendSV + .long __invalid_entry @ 15 - SysTick + .rept CONFIG_CPU_V7M_NUM_IRQ + .long __irq_entry @ External Interrupts + .endr + .align 2 + .globl exc_ret +exc_ret: + .space 4 diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c new file mode 100644 index 000000000..98ca3e3fa --- /dev/null +++ b/arch/arm/kernel/fiq.c @@ -0,0 +1,165 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * linux/arch/arm/kernel/fiq.c + * + * Copyright (C) 1998 Russell King + * Copyright (C) 1998, 1999 Phil Blundell + * + * FIQ support written by Philip Blundell <philb@gnu.org>, 1998. + * + * FIQ support re-written by Russell King to be more generic + * + * We now properly support a method by which the FIQ handlers can + * be stacked onto the vector. We still do not support sharing + * the FIQ vector itself. + * + * Operation is as follows: + * 1. Owner A claims FIQ: + * - default_fiq relinquishes control. + * 2. Owner A: + * - inserts code. + * - sets any registers, + * - enables FIQ. + * 3. Owner B claims FIQ: + * - if owner A has a relinquish function. + * - disable FIQs. + * - saves any registers. + * - returns zero. + * 4. Owner B: + * - inserts code. + * - sets any registers, + * - enables FIQ. + * 5. Owner B releases FIQ: + * - Owner A is asked to reacquire FIQ: + * - inserts code. + * - restores saved registers. + * - enables FIQ. + * 6. Goto 3 + */ +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/seq_file.h> + +#include <asm/cacheflush.h> +#include <asm/cp15.h> +#include <asm/fiq.h> +#include <asm/irq.h> +#include <asm/traps.h> + +#define FIQ_OFFSET ({ \ + extern void *vector_fiq_offset; \ + (unsigned)&vector_fiq_offset; \ + }) + +static unsigned long dfl_fiq_insn; +static struct pt_regs dfl_fiq_regs; + +/* Default reacquire function + * - we always relinquish FIQ control + * - we always reacquire FIQ control + */ +static int fiq_def_op(void *ref, int relinquish) +{ + if (!relinquish) { + /* Restore default handler and registers */ + local_fiq_disable(); + set_fiq_regs(&dfl_fiq_regs); + set_fiq_handler(&dfl_fiq_insn, sizeof(dfl_fiq_insn)); + local_fiq_enable(); + + /* FIXME: notify irq controller to standard enable FIQs */ + } + + return 0; +} + +static struct fiq_handler default_owner = { + .name = "default", + .fiq_op = fiq_def_op, +}; + +static struct fiq_handler *current_fiq = &default_owner; + +int show_fiq_list(struct seq_file *p, int prec) +{ + if (current_fiq != &default_owner) + seq_printf(p, "%*s: %s\n", prec, "FIQ", + current_fiq->name); + + return 0; +} + +void set_fiq_handler(void *start, unsigned int length) +{ + void *base = vectors_page; + unsigned offset = FIQ_OFFSET; + + memcpy(base + offset, start, length); + if (!cache_is_vipt_nonaliasing()) + flush_icache_range((unsigned long)base + offset, + (unsigned long)base + offset + length); + flush_icache_range(0xffff0000 + offset, 0xffff0000 + offset + length); +} + +int claim_fiq(struct fiq_handler *f) +{ + int ret = 0; + + if (current_fiq) { + ret = -EBUSY; + + if (current_fiq->fiq_op != NULL) + ret = current_fiq->fiq_op(current_fiq->dev_id, 1); + } + + if (!ret) { + f->next = current_fiq; + current_fiq = f; + } + + return ret; +} + +void release_fiq(struct fiq_handler *f) +{ + if (current_fiq != f) { + pr_err("%s FIQ trying to release %s FIQ\n", + f->name, current_fiq->name); + dump_stack(); + return; + } + + do + current_fiq = current_fiq->next; + while (current_fiq->fiq_op(current_fiq->dev_id, 0)); +} + +static int fiq_start; + +void enable_fiq(int fiq) +{ + enable_irq(fiq + fiq_start); +} + +void disable_fiq(int fiq) +{ + disable_irq(fiq + fiq_start); +} + +EXPORT_SYMBOL(set_fiq_handler); +EXPORT_SYMBOL(__set_fiq_regs); /* defined in fiqasm.S */ +EXPORT_SYMBOL(__get_fiq_regs); /* defined in fiqasm.S */ +EXPORT_SYMBOL(claim_fiq); +EXPORT_SYMBOL(release_fiq); +EXPORT_SYMBOL(enable_fiq); +EXPORT_SYMBOL(disable_fiq); + +void __init init_FIQ(int start) +{ + unsigned offset = FIQ_OFFSET; + dfl_fiq_insn = *(unsigned long *)(0xffff0000 + offset); + get_fiq_regs(&dfl_fiq_regs); + fiq_start = start; +} diff --git a/arch/arm/kernel/fiqasm.S b/arch/arm/kernel/fiqasm.S new file mode 100644 index 000000000..8dd26e1a9 --- /dev/null +++ b/arch/arm/kernel/fiqasm.S @@ -0,0 +1,49 @@ +/* + * linux/arch/arm/kernel/fiqasm.S + * + * Derived from code originally in linux/arch/arm/kernel/fiq.c: + * + * Copyright (C) 1998 Russell King + * Copyright (C) 1998, 1999 Phil Blundell + * Copyright (C) 2011, Linaro Limited + * + * FIQ support written by Philip Blundell <philb@gnu.org>, 1998. + * + * FIQ support re-written by Russell King to be more generic + * + * v7/Thumb-2 compatibility modifications by Linaro Limited, 2011. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> + +/* + * Taking an interrupt in FIQ mode is death, so both these functions + * disable irqs for the duration. + */ + +ENTRY(__set_fiq_regs) + mov r2, #PSR_I_BIT | PSR_F_BIT | FIQ_MODE + mrs r1, cpsr + msr cpsr_c, r2 @ select FIQ mode + mov r0, r0 @ avoid hazard prior to ARMv4 + ldmia r0!, {r8 - r12} + ldr sp, [r0], #4 + ldr lr, [r0] + msr cpsr_c, r1 @ return to SVC mode + mov r0, r0 @ avoid hazard prior to ARMv4 + ret lr +ENDPROC(__set_fiq_regs) + +ENTRY(__get_fiq_regs) + mov r2, #PSR_I_BIT | PSR_F_BIT | FIQ_MODE + mrs r1, cpsr + msr cpsr_c, r2 @ select FIQ mode + mov r0, r0 @ avoid hazard prior to ARMv4 + stmia r0!, {r8 - r12} + str sp, [r0], #4 + str lr, [r0] + msr cpsr_c, r1 @ return to SVC mode + mov r0, r0 @ avoid hazard prior to ARMv4 + ret lr +ENDPROC(__get_fiq_regs) diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c new file mode 100644 index 000000000..a0b6d1e38 --- /dev/null +++ b/arch/arm/kernel/ftrace.c @@ -0,0 +1,310 @@ +/* + * Dynamic function tracing support. + * + * Copyright (C) 2008 Abhishek Sagar <sagar.abhishek@gmail.com> + * Copyright (C) 2010 Rabin Vincent <rabin@rab.in> + * + * For licencing details, see COPYING. + * + * Defines low-level handling of mcount calls when the kernel + * is compiled with the -pg flag. When using dynamic ftrace, the + * mcount call-sites get patched with NOP till they are enabled. + * All code mutation routines here are called under stop_machine(). + */ + +#include <linux/ftrace.h> +#include <linux/uaccess.h> +#include <linux/module.h> +#include <linux/stop_machine.h> + +#include <asm/cacheflush.h> +#include <asm/opcodes.h> +#include <asm/ftrace.h> +#include <asm/insn.h> +#include <asm/set_memory.h> +#include <asm/stacktrace.h> +#include <asm/patch.h> + +/* + * The compiler emitted profiling hook consists of + * + * PUSH {LR} + * BL __gnu_mcount_nc + * + * To turn this combined sequence into a NOP, we need to restore the value of + * SP before the PUSH. Let's use an ADD rather than a POP into LR, as LR is not + * modified anyway, and reloading LR from memory is highly likely to be less + * efficient. + */ +#ifdef CONFIG_THUMB2_KERNEL +#define NOP 0xf10d0d04 /* add.w sp, sp, #4 */ +#else +#define NOP 0xe28dd004 /* add sp, sp, #4 */ +#endif + +#ifdef CONFIG_DYNAMIC_FTRACE + +static int __ftrace_modify_code(void *data) +{ + int *command = data; + + ftrace_modify_all_code(*command); + + return 0; +} + +void arch_ftrace_update_code(int command) +{ + stop_machine(__ftrace_modify_code, &command, NULL); +} + +static unsigned long ftrace_nop_replace(struct dyn_ftrace *rec) +{ + return NOP; +} + +void ftrace_caller_from_init(void); +void ftrace_regs_caller_from_init(void); + +static unsigned long __ref adjust_address(struct dyn_ftrace *rec, + unsigned long addr) +{ + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE) || + system_state >= SYSTEM_FREEING_INITMEM || + likely(!is_kernel_inittext(rec->ip))) + return addr; + if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) || + addr == (unsigned long)&ftrace_caller) + return (unsigned long)&ftrace_caller_from_init; + return (unsigned long)&ftrace_regs_caller_from_init; +} + +void ftrace_arch_code_modify_prepare(void) +{ +} + +void ftrace_arch_code_modify_post_process(void) +{ + /* Make sure any TLB misses during machine stop are cleared. */ + flush_tlb_all(); +} + +static unsigned long ftrace_call_replace(unsigned long pc, unsigned long addr, + bool warn) +{ + return arm_gen_branch_link(pc, addr, warn); +} + +static int ftrace_modify_code(unsigned long pc, unsigned long old, + unsigned long new, bool validate) +{ + unsigned long replaced; + + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) + old = __opcode_to_mem_thumb32(old); + else + old = __opcode_to_mem_arm(old); + + if (validate) { + if (copy_from_kernel_nofault(&replaced, (void *)pc, + MCOUNT_INSN_SIZE)) + return -EFAULT; + + if (replaced != old) + return -EINVAL; + } + + __patch_text((void *)pc, new); + + return 0; +} + +int ftrace_update_ftrace_func(ftrace_func_t func) +{ + unsigned long pc; + unsigned long new; + int ret; + + pc = (unsigned long)&ftrace_call; + new = ftrace_call_replace(pc, (unsigned long)func, true); + + ret = ftrace_modify_code(pc, 0, new, false); + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + if (!ret) { + pc = (unsigned long)&ftrace_regs_call; + new = ftrace_call_replace(pc, (unsigned long)func, true); + + ret = ftrace_modify_code(pc, 0, new, false); + } +#endif + + return ret; +} + +int ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long new, old; + unsigned long ip = rec->ip; + unsigned long aaddr = adjust_address(rec, addr); + struct module *mod = NULL; + +#ifdef CONFIG_ARM_MODULE_PLTS + mod = rec->arch.mod; +#endif + + old = ftrace_nop_replace(rec); + + new = ftrace_call_replace(ip, aaddr, !mod); +#ifdef CONFIG_ARM_MODULE_PLTS + if (!new && mod) { + aaddr = get_module_plt(mod, ip, aaddr); + new = ftrace_call_replace(ip, aaddr, true); + } +#endif + + return ftrace_modify_code(rec->ip, old, new, true); +} + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + +int ftrace_modify_call(struct dyn_ftrace *rec, unsigned long old_addr, + unsigned long addr) +{ + unsigned long new, old; + unsigned long ip = rec->ip; + + old = ftrace_call_replace(ip, adjust_address(rec, old_addr), true); + + new = ftrace_call_replace(ip, adjust_address(rec, addr), true); + + return ftrace_modify_code(rec->ip, old, new, true); +} + +#endif + +int ftrace_make_nop(struct module *mod, + struct dyn_ftrace *rec, unsigned long addr) +{ + unsigned long aaddr = adjust_address(rec, addr); + unsigned long ip = rec->ip; + unsigned long old; + unsigned long new; + int ret; + +#ifdef CONFIG_ARM_MODULE_PLTS + /* mod is only supplied during module loading */ + if (!mod) + mod = rec->arch.mod; + else + rec->arch.mod = mod; +#endif + + old = ftrace_call_replace(ip, aaddr, + !IS_ENABLED(CONFIG_ARM_MODULE_PLTS) || !mod); +#ifdef CONFIG_ARM_MODULE_PLTS + if (!old && mod) { + aaddr = get_module_plt(mod, ip, aaddr); + old = ftrace_call_replace(ip, aaddr, true); + } +#endif + + new = ftrace_nop_replace(rec); + /* + * Locations in .init.text may call __gnu_mcount_mc via a linker + * emitted veneer if they are too far away from its implementation, and + * so validation may fail spuriously in such cases. Let's work around + * this by omitting those from validation. + */ + ret = ftrace_modify_code(ip, old, new, !is_kernel_inittext(ip)); + + return ret; +} +#endif /* CONFIG_DYNAMIC_FTRACE */ + +#ifdef CONFIG_FUNCTION_GRAPH_TRACER +asmlinkage +void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr, + unsigned long frame_pointer, + unsigned long stack_pointer) +{ + unsigned long return_hooker = (unsigned long) &return_to_handler; + unsigned long old; + + if (unlikely(atomic_read(¤t->tracing_graph_pause))) + return; + + if (IS_ENABLED(CONFIG_UNWINDER_FRAME_POINTER)) { + /* FP points one word below parent's top of stack */ + frame_pointer += 4; + } else { + struct stackframe frame = { + .fp = frame_pointer, + .sp = stack_pointer, + .lr = self_addr, + .pc = self_addr, + }; + if (unwind_frame(&frame) < 0) + return; + if (frame.lr != self_addr) + parent = frame.lr_addr; + frame_pointer = frame.sp; + } + + old = *parent; + *parent = return_hooker; + + if (function_graph_enter(old, self_addr, frame_pointer, NULL)) + *parent = old; +} + +#ifdef CONFIG_DYNAMIC_FTRACE +extern unsigned long ftrace_graph_call; +extern unsigned long ftrace_graph_call_old; +extern void ftrace_graph_caller_old(void); +extern unsigned long ftrace_graph_regs_call; +extern void ftrace_graph_regs_caller(void); + +static int __ftrace_modify_caller(unsigned long *callsite, + void (*func) (void), bool enable) +{ + unsigned long caller_fn = (unsigned long) func; + unsigned long pc = (unsigned long) callsite; + unsigned long branch = arm_gen_branch(pc, caller_fn); + unsigned long nop = arm_gen_nop(); + unsigned long old = enable ? nop : branch; + unsigned long new = enable ? branch : nop; + + return ftrace_modify_code(pc, old, new, true); +} + +static int ftrace_modify_graph_caller(bool enable) +{ + int ret; + + ret = __ftrace_modify_caller(&ftrace_graph_call, + ftrace_graph_caller, + enable); + +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS + if (!ret) + ret = __ftrace_modify_caller(&ftrace_graph_regs_call, + ftrace_graph_regs_caller, + enable); +#endif + + + return ret; +} + +int ftrace_enable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(true); +} + +int ftrace_disable_ftrace_graph_caller(void) +{ + return ftrace_modify_graph_caller(false); +} +#endif /* CONFIG_DYNAMIC_FTRACE */ +#endif /* CONFIG_FUNCTION_GRAPH_TRACER */ diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S new file mode 100644 index 000000000..42cae73fc --- /dev/null +++ b/arch/arm/kernel/head-common.S @@ -0,0 +1,239 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/arch/arm/kernel/head-common.S + * + * Copyright (C) 1994-2002 Russell King + * Copyright (c) 2003 ARM Limited + * All Rights Reserved + */ +#include <asm/assembler.h> + +#define ATAG_CORE 0x54410001 +#define ATAG_CORE_SIZE ((2*4 + 3*4) >> 2) +#define ATAG_CORE_SIZE_EMPTY ((2*4) >> 2) + +#ifdef CONFIG_CPU_BIG_ENDIAN +#define OF_DT_MAGIC 0xd00dfeed +#else +#define OF_DT_MAGIC 0xedfe0dd0 /* 0xd00dfeed in big-endian */ +#endif + +/* + * Exception handling. Something went wrong and we can't proceed. We + * ought to tell the user, but since we don't have any guarantee that + * we're even running on the right architecture, we do virtually nothing. + * + * If CONFIG_DEBUG_LL is set we try to print out something about the error + * and hope for the best (useful if bootloader fails to pass a proper + * machine ID for example). + */ + __HEAD + +/* Determine validity of the r2 atags pointer. The heuristic requires + * that the pointer be aligned, in the first 16k of physical RAM and + * that the ATAG_CORE marker is first and present. If CONFIG_OF_FLATTREE + * is selected, then it will also accept a dtb pointer. Future revisions + * of this function may be more lenient with the physical address and + * may also be able to move the ATAGS block if necessary. + * + * Returns: + * r2 either valid atags pointer, valid dtb pointer, or zero + * r5, r6 corrupted + */ +__vet_atags: + tst r2, #0x3 @ aligned? + bne 1f + + ldr r5, [r2, #0] +#ifdef CONFIG_OF_FLATTREE + ldr r6, =OF_DT_MAGIC @ is it a DTB? + cmp r5, r6 + beq 2f +#endif + cmp r5, #ATAG_CORE_SIZE @ is first tag ATAG_CORE? + cmpne r5, #ATAG_CORE_SIZE_EMPTY + bne 1f + ldr r5, [r2, #4] + ldr r6, =ATAG_CORE + cmp r5, r6 + bne 1f + +2: ret lr @ atag/dtb pointer is ok + +1: mov r2, #0 + ret lr +ENDPROC(__vet_atags) + +/* + * The following fragment of code is executed with the MMU on in MMU mode, + * and uses absolute addresses; this is not position independent. + * + * r0 = cp#15 control register (exc_ret for M-class) + * r1 = machine ID + * r2 = atags/dtb pointer + * r9 = processor ID + */ + __INIT +__mmap_switched: + + mov r7, r1 + mov r8, r2 + mov r10, r0 + + adr r4, __mmap_switched_data + mov fp, #0 + +#if defined(CONFIG_XIP_DEFLATED_DATA) + ARM( ldr sp, [r4], #4 ) + THUMB( ldr sp, [r4] ) + THUMB( add r4, #4 ) + bl __inflate_kernel_data @ decompress .data to RAM + teq r0, #0 + bne __error +#elif defined(CONFIG_XIP_KERNEL) + ARM( ldmia r4!, {r0, r1, r2, sp} ) + THUMB( ldmia r4!, {r0, r1, r2, r3} ) + THUMB( mov sp, r3 ) + sub r2, r2, r1 + bl __memcpy @ copy .data to RAM +#endif + + ARM( ldmia r4!, {r0, r1, sp} ) + THUMB( ldmia r4!, {r0, r1, r3} ) + THUMB( mov sp, r3 ) + sub r2, r1, r0 + mov r1, #0 + bl __memset @ clear .bss + + adr_l r0, init_task @ get swapper task_struct + set_current r0, r1 + + ldmia r4, {r0, r1, r2, r3} + str r9, [r0] @ Save processor ID + str r7, [r1] @ Save machine type + str r8, [r2] @ Save atags pointer + cmp r3, #0 + strne r10, [r3] @ Save control register values +#ifdef CONFIG_KASAN + bl kasan_early_init +#endif + mov lr, #0 + b start_kernel +ENDPROC(__mmap_switched) + + .align 2 + .type __mmap_switched_data, %object +__mmap_switched_data: +#ifdef CONFIG_XIP_KERNEL +#ifndef CONFIG_XIP_DEFLATED_DATA + .long _sdata @ r0 + .long __data_loc @ r1 + .long _edata_loc @ r2 +#endif + .long __bss_stop @ sp (temporary stack in .bss) +#endif + + .long __bss_start @ r0 + .long __bss_stop @ r1 + .long init_thread_union + THREAD_START_SP @ sp + + .long processor_id @ r0 + .long __machine_arch_type @ r1 + .long __atags_pointer @ r2 +#ifdef CONFIG_CPU_CP15 + .long cr_alignment @ r3 +#else +M_CLASS(.long exc_ret) @ r3 +AR_CLASS(.long 0) @ r3 +#endif + .size __mmap_switched_data, . - __mmap_switched_data + + __FINIT + .text + +/* + * This provides a C-API version of __lookup_processor_type + */ +ENTRY(lookup_processor_type) + stmfd sp!, {r4 - r6, r9, lr} + mov r9, r0 + bl __lookup_processor_type + mov r0, r5 + ldmfd sp!, {r4 - r6, r9, pc} +ENDPROC(lookup_processor_type) + +/* + * Read processor ID register (CP#15, CR0), and look up in the linker-built + * supported processor list. Note that we can't use the absolute addresses + * for the __proc_info lists since we aren't running with the MMU on + * (and therefore, we are not in the correct address space). We have to + * calculate the offset. + * + * r9 = cpuid + * Returns: + * r3, r4, r6 corrupted + * r5 = proc_info pointer in physical address space + * r9 = cpuid (preserved) + */ +__lookup_processor_type: + /* + * Look in <asm/procinfo.h> for information about the __proc_info + * structure. + */ + adr_l r5, __proc_info_begin + adr_l r6, __proc_info_end +1: ldmia r5, {r3, r4} @ value, mask + and r4, r4, r9 @ mask wanted bits + teq r3, r4 + beq 2f + add r5, r5, #PROC_INFO_SZ @ sizeof(proc_info_list) + cmp r5, r6 + blo 1b + mov r5, #0 @ unknown processor +2: ret lr +ENDPROC(__lookup_processor_type) + +__error_lpae: +#ifdef CONFIG_DEBUG_LL + adr r0, str_lpae + bl printascii + b __error +str_lpae: .asciz "\nError: Kernel with LPAE support, but CPU does not support LPAE.\n" +#else + b __error +#endif + .align +ENDPROC(__error_lpae) + +__error_p: +#ifdef CONFIG_DEBUG_LL + adr r0, str_p1 + bl printascii + mov r0, r9 + bl printhex8 + adr r0, str_p2 + bl printascii + b __error +str_p1: .asciz "\nError: unrecognized/unsupported processor variant (0x" +str_p2: .asciz ").\n" + .align +#endif +ENDPROC(__error_p) + +__error: +#ifdef CONFIG_ARCH_RPC +/* + * Turn the screen red on a error - RiscPC only. + */ + mov r0, #0x02000000 + mov r3, #0x11 + orr r3, r3, r3, lsl #8 + orr r3, r3, r3, lsl #16 + str r3, [r0], #4 + str r3, [r0], #4 + str r3, [r0], #4 + str r3, [r0], #4 +#endif +1: mov r0, r0 + b 1b +ENDPROC(__error) diff --git a/arch/arm/kernel/head-inflate-data.c b/arch/arm/kernel/head-inflate-data.c new file mode 100644 index 000000000..89a52104d --- /dev/null +++ b/arch/arm/kernel/head-inflate-data.c @@ -0,0 +1,59 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * XIP kernel .data segment decompressor + * + * Created by: Nicolas Pitre, August 2017 + * Copyright: (C) 2017 Linaro Limited + */ + +#include <linux/init.h> +#include <linux/zutil.h> + +/* for struct inflate_state */ +#include "../../../lib/zlib_inflate/inftrees.h" +#include "../../../lib/zlib_inflate/inflate.h" +#include "../../../lib/zlib_inflate/infutil.h" + +extern char __data_loc[]; +extern char _edata_loc[]; +extern char _sdata[]; + +/* + * This code is called very early during the boot process to decompress + * the .data segment stored compressed in ROM. Therefore none of the global + * variables are valid yet, hence no kernel services such as memory + * allocation is available. Everything must be allocated on the stack and + * we must avoid any global data access. We use a temporary stack located + * in the .bss area. The linker script makes sure the .bss is big enough + * to hold our stack frame plus some room for called functions. + * + * We mimic the code in lib/decompress_inflate.c to use the smallest work + * area possible. And because everything is statically allocated on the + * stack then there is no need to clean up before returning. + */ + +int __init __inflate_kernel_data(void) +{ + struct z_stream_s stream, *strm = &stream; + struct inflate_state state; + char *in = __data_loc; + int rc; + + /* Check and skip gzip header (assume no filename) */ + if (in[0] != 0x1f || in[1] != 0x8b || in[2] != 0x08 || in[3] & ~3) + return -1; + in += 10; + + strm->workspace = &state; + strm->next_in = in; + strm->avail_in = _edata_loc - __data_loc; /* upper bound */ + strm->next_out = _sdata; + strm->avail_out = _edata_loc - __data_loc; + zlib_inflateInit2(strm, -MAX_WBITS); + WS(strm)->inflate_state.wsize = 0; + WS(strm)->inflate_state.window = NULL; + rc = zlib_inflate(strm, Z_FINISH); + if (rc == Z_OK || rc == Z_STREAM_END) + rc = strm->avail_out; /* should be 0 */ + return rc; +} diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S new file mode 100644 index 000000000..950bef833 --- /dev/null +++ b/arch/arm/kernel/head-nommu.S @@ -0,0 +1,537 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/arch/arm/kernel/head-nommu.S + * + * Copyright (C) 1994-2002 Russell King + * Copyright (C) 2003-2006 Hyok S. Choi + * + * Common kernel startup code (non-paged MM) + */ +#include <linux/linkage.h> +#include <linux/init.h> +#include <linux/errno.h> + +#include <asm/assembler.h> +#include <asm/ptrace.h> +#include <asm/asm-offsets.h> +#include <asm/memory.h> +#include <asm/cp15.h> +#include <asm/thread_info.h> +#include <asm/v7m.h> +#include <asm/mpu.h> +#include <asm/page.h> + +/* + * Kernel startup entry point. + * --------------------------- + * + * This is normally called from the decompressor code. The requirements + * are: MMU = off, D-cache = off, I-cache = dont care, r0 = 0, + * r1 = machine nr. + * + * See linux/arch/arm/tools/mach-types for the complete list of machine + * numbers for r1. + * + */ + + __HEAD + +#ifdef CONFIG_CPU_THUMBONLY + .thumb +ENTRY(stext) +#else + .arm +ENTRY(stext) + + THUMB( badr r9, 1f ) @ Kernel is always entered in ARM. + THUMB( bx r9 ) @ If this is a Thumb-2 kernel, + THUMB( .thumb ) @ switch to Thumb now. + THUMB(1: ) +#endif + +#ifdef CONFIG_ARM_VIRT_EXT + bl __hyp_stub_install +#endif + @ ensure svc mode and all interrupts masked + safe_svcmode_maskall r9 + @ and irqs disabled +#if defined(CONFIG_CPU_CP15) + mrc p15, 0, r9, c0, c0 @ get processor id +#elif defined(CONFIG_CPU_V7M) + ldr r9, =BASEADDR_V7M_SCB + ldr r9, [r9, V7M_SCB_CPUID] +#else + ldr r9, =CONFIG_PROCESSOR_ID +#endif + bl __lookup_processor_type @ r5=procinfo r9=cpuid + movs r10, r5 @ invalid processor (r5=0)? + beq __error_p @ yes, error 'p' + +#ifdef CONFIG_ARM_MPU + bl __setup_mpu +#endif + + badr lr, 1f @ return (PIC) address + ldr r12, [r10, #PROCINFO_INITFUNC] + add r12, r12, r10 + ret r12 +1: ldr lr, =__mmap_switched + b __after_proc_init +ENDPROC(stext) + +#ifdef CONFIG_SMP + .text +ENTRY(secondary_startup) + /* + * Common entry point for secondary CPUs. + * + * Ensure that we're in SVC mode, and IRQs are disabled. Lookup + * the processor type - there is no need to check the machine type + * as it has already been validated by the primary processor. + */ +#ifdef CONFIG_ARM_VIRT_EXT + bl __hyp_stub_install_secondary +#endif + safe_svcmode_maskall r9 + +#ifndef CONFIG_CPU_CP15 + ldr r9, =CONFIG_PROCESSOR_ID +#else + mrc p15, 0, r9, c0, c0 @ get processor id +#endif + bl __lookup_processor_type @ r5=procinfo r9=cpuid + movs r10, r5 @ invalid processor? + beq __error_p @ yes, error 'p' + + ldr r7, __secondary_data + +#ifdef CONFIG_ARM_MPU + bl __secondary_setup_mpu @ Initialize the MPU +#endif + + badr lr, 1f @ return (PIC) address + ldr r12, [r10, #PROCINFO_INITFUNC] + add r12, r12, r10 + ret r12 +1: bl __after_proc_init + ldr r7, __secondary_data @ reload r7 + ldr sp, [r7, #12] @ set up the stack pointer + ldr r0, [r7, #16] @ set up task pointer + mov fp, #0 + b secondary_start_kernel +ENDPROC(secondary_startup) + + .type __secondary_data, %object +__secondary_data: + .long secondary_data +#endif /* CONFIG_SMP */ + +/* + * Set the Control Register and Read the process ID. + */ + .text +__after_proc_init: +M_CLASS(movw r12, #:lower16:BASEADDR_V7M_SCB) +M_CLASS(movt r12, #:upper16:BASEADDR_V7M_SCB) +#ifdef CONFIG_ARM_MPU +M_CLASS(ldr r3, [r12, 0x50]) +AR_CLASS(mrc p15, 0, r3, c0, c1, 4) @ Read ID_MMFR0 + and r3, r3, #(MMFR0_PMSA) @ PMSA field + teq r3, #(MMFR0_PMSAv7) @ PMSA v7 + beq 1f + teq r3, #(MMFR0_PMSAv8) @ PMSA v8 + /* + * Memory region attributes for PMSAv8: + * + * n = AttrIndx[2:0] + * n MAIR + * DEVICE_nGnRnE 000 00000000 + * NORMAL 001 11111111 + */ + ldreq r3, =PMSAv8_MAIR(0x00, PMSAv8_RGN_DEVICE_nGnRnE) | \ + PMSAv8_MAIR(0xff, PMSAv8_RGN_NORMAL) +AR_CLASS(mcreq p15, 0, r3, c10, c2, 0) @ MAIR 0 +M_CLASS(streq r3, [r12, #PMSAv8_MAIR0]) + moveq r3, #0 +AR_CLASS(mcreq p15, 0, r3, c10, c2, 1) @ MAIR 1 +M_CLASS(streq r3, [r12, #PMSAv8_MAIR1]) + +1: +#endif +#ifdef CONFIG_CPU_CP15 + /* + * CP15 system control register value returned in r0 from + * the CPU init function. + */ + +#ifdef CONFIG_ARM_MPU + biceq r0, r0, #CR_BR @ Disable the 'default mem-map' + orreq r0, r0, #CR_M @ Set SCTRL.M (MPU on) +#endif +#if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6 + orr r0, r0, #CR_A +#else + bic r0, r0, #CR_A +#endif +#ifdef CONFIG_CPU_DCACHE_DISABLE + bic r0, r0, #CR_C +#endif +#ifdef CONFIG_CPU_BPREDICT_DISABLE + bic r0, r0, #CR_Z +#endif +#ifdef CONFIG_CPU_ICACHE_DISABLE + bic r0, r0, #CR_I +#endif + mcr p15, 0, r0, c1, c0, 0 @ write control reg + instr_sync +#elif defined (CONFIG_CPU_V7M) +#ifdef CONFIG_ARM_MPU + ldreq r3, [r12, MPU_CTRL] + biceq r3, #MPU_CTRL_PRIVDEFENA + orreq r3, #MPU_CTRL_ENABLE + streq r3, [r12, MPU_CTRL] + isb +#endif + /* For V7M systems we want to modify the CCR similarly to the SCTLR */ +#ifdef CONFIG_CPU_DCACHE_DISABLE + bic r0, r0, #V7M_SCB_CCR_DC +#endif +#ifdef CONFIG_CPU_BPREDICT_DISABLE + bic r0, r0, #V7M_SCB_CCR_BP +#endif +#ifdef CONFIG_CPU_ICACHE_DISABLE + bic r0, r0, #V7M_SCB_CCR_IC +#endif + str r0, [r12, V7M_SCB_CCR] + /* Pass exc_ret to __mmap_switched */ + mov r0, r10 +#endif /* CONFIG_CPU_CP15 elif CONFIG_CPU_V7M */ + ret lr +ENDPROC(__after_proc_init) + .ltorg + +#ifdef CONFIG_ARM_MPU + + +#ifndef CONFIG_CPU_V7M +/* Set which MPU region should be programmed */ +.macro set_region_nr tmp, rgnr, unused + mov \tmp, \rgnr @ Use static region numbers + mcr p15, 0, \tmp, c6, c2, 0 @ Write RGNR +.endm + +/* Setup a single MPU region, either D or I side (D-side for unified) */ +.macro setup_region bar, acr, sr, side = PMSAv7_DATA_SIDE, unused + mcr p15, 0, \bar, c6, c1, (0 + \side) @ I/DRBAR + mcr p15, 0, \acr, c6, c1, (4 + \side) @ I/DRACR + mcr p15, 0, \sr, c6, c1, (2 + \side) @ I/DRSR +.endm +#else +.macro set_region_nr tmp, rgnr, base + mov \tmp, \rgnr + str \tmp, [\base, #PMSAv7_RNR] +.endm + +.macro setup_region bar, acr, sr, unused, base + lsl \acr, \acr, #16 + orr \acr, \acr, \sr + str \bar, [\base, #PMSAv7_RBAR] + str \acr, [\base, #PMSAv7_RASR] +.endm + +#endif +/* + * Setup the MPU and initial MPU Regions. We create the following regions: + * Region 0: Use this for probing the MPU details, so leave disabled. + * Region 1: Background region - covers the whole of RAM as strongly ordered + * Region 2: Normal, Shared, cacheable for RAM. From PHYS_OFFSET, size from r6 + * Region 3: Normal, shared, inaccessible from PL0 to protect the vectors page + * + * r6: Value to be written to DRSR (and IRSR if required) for PMSAv7_RAM_REGION +*/ + __HEAD + +ENTRY(__setup_mpu) + + /* Probe for v7 PMSA compliance */ +M_CLASS(movw r12, #:lower16:BASEADDR_V7M_SCB) +M_CLASS(movt r12, #:upper16:BASEADDR_V7M_SCB) + +AR_CLASS(mrc p15, 0, r0, c0, c1, 4) @ Read ID_MMFR0 +M_CLASS(ldr r0, [r12, 0x50]) + and r0, r0, #(MMFR0_PMSA) @ PMSA field + teq r0, #(MMFR0_PMSAv7) @ PMSA v7 + beq __setup_pmsa_v7 + teq r0, #(MMFR0_PMSAv8) @ PMSA v8 + beq __setup_pmsa_v8 + + ret lr +ENDPROC(__setup_mpu) + +ENTRY(__setup_pmsa_v7) + /* Calculate the size of a region covering just the kernel */ + ldr r5, =PLAT_PHYS_OFFSET @ Region start: PHYS_OFFSET + ldr r6, =(_end) @ Cover whole kernel + sub r6, r6, r5 @ Minimum size of region to map + clz r6, r6 @ Region size must be 2^N... + rsb r6, r6, #31 @ ...so round up region size + lsl r6, r6, #PMSAv7_RSR_SZ @ Put size in right field + orr r6, r6, #(1 << PMSAv7_RSR_EN) @ Set region enabled bit + + /* Determine whether the D/I-side memory map is unified. We set the + * flags here and continue to use them for the rest of this function */ +AR_CLASS(mrc p15, 0, r0, c0, c0, 4) @ MPUIR +M_CLASS(ldr r0, [r12, #MPU_TYPE]) + ands r5, r0, #MPUIR_DREGION_SZMASK @ 0 size d region => No MPU + bxeq lr + tst r0, #MPUIR_nU @ MPUIR_nU = 0 for unified + + /* Setup second region first to free up r6 */ + set_region_nr r0, #PMSAv7_RAM_REGION, r12 + isb + /* Full access from PL0, PL1, shared for CONFIG_SMP, cacheable */ + ldr r0, =PLAT_PHYS_OFFSET @ RAM starts at PHYS_OFFSET + ldr r5,=(PMSAv7_AP_PL1RW_PL0RW | PMSAv7_RGN_NORMAL) + + setup_region r0, r5, r6, PMSAv7_DATA_SIDE, r12 @ PHYS_OFFSET, shared, enabled + beq 1f @ Memory-map not unified + setup_region r0, r5, r6, PMSAv7_INSTR_SIDE, r12 @ PHYS_OFFSET, shared, enabled +1: isb + + /* First/background region */ + set_region_nr r0, #PMSAv7_BG_REGION, r12 + isb + /* Execute Never, strongly ordered, inaccessible to PL0, rw PL1 */ + mov r0, #0 @ BG region starts at 0x0 + ldr r5,=(PMSAv7_ACR_XN | PMSAv7_RGN_STRONGLY_ORDERED | PMSAv7_AP_PL1RW_PL0NA) + mov r6, #PMSAv7_RSR_ALL_MEM @ 4GB region, enabled + + setup_region r0, r5, r6, PMSAv7_DATA_SIDE, r12 @ 0x0, BG region, enabled + beq 2f @ Memory-map not unified + setup_region r0, r5, r6, PMSAv7_INSTR_SIDE r12 @ 0x0, BG region, enabled +2: isb + +#ifdef CONFIG_XIP_KERNEL + set_region_nr r0, #PMSAv7_ROM_REGION, r12 + isb + + ldr r5,=(PMSAv7_AP_PL1RO_PL0NA | PMSAv7_RGN_NORMAL) + + ldr r0, =CONFIG_XIP_PHYS_ADDR @ ROM start + ldr r6, =(_exiprom) @ ROM end + sub r6, r6, r0 @ Minimum size of region to map + clz r6, r6 @ Region size must be 2^N... + rsb r6, r6, #31 @ ...so round up region size + lsl r6, r6, #PMSAv7_RSR_SZ @ Put size in right field + orr r6, r6, #(1 << PMSAv7_RSR_EN) @ Set region enabled bit + + setup_region r0, r5, r6, PMSAv7_DATA_SIDE, r12 @ XIP_PHYS_ADDR, shared, enabled + beq 3f @ Memory-map not unified + setup_region r0, r5, r6, PMSAv7_INSTR_SIDE, r12 @ XIP_PHYS_ADDR, shared, enabled +3: isb +#endif + ret lr +ENDPROC(__setup_pmsa_v7) + +ENTRY(__setup_pmsa_v8) + mov r0, #0 +AR_CLASS(mcr p15, 0, r0, c6, c2, 1) @ PRSEL +M_CLASS(str r0, [r12, #PMSAv8_RNR]) + isb + +#ifdef CONFIG_XIP_KERNEL + ldr r5, =CONFIG_XIP_PHYS_ADDR @ ROM start + ldr r6, =(_exiprom) @ ROM end + sub r6, r6, #1 + bic r6, r6, #(PMSAv8_MINALIGN - 1) + + orr r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED) + orr r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_NORMAL) | PMSAv8_LAR_EN) + +AR_CLASS(mcr p15, 0, r5, c6, c8, 0) @ PRBAR0 +AR_CLASS(mcr p15, 0, r6, c6, c8, 1) @ PRLAR0 +M_CLASS(str r5, [r12, #PMSAv8_RBAR_A(0)]) +M_CLASS(str r6, [r12, #PMSAv8_RLAR_A(0)]) +#endif + + ldr r5, =KERNEL_START + ldr r6, =KERNEL_END + sub r6, r6, #1 + bic r6, r6, #(PMSAv8_MINALIGN - 1) + + orr r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED) + orr r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_NORMAL) | PMSAv8_LAR_EN) + +AR_CLASS(mcr p15, 0, r5, c6, c8, 4) @ PRBAR1 +AR_CLASS(mcr p15, 0, r6, c6, c8, 5) @ PRLAR1 +M_CLASS(str r5, [r12, #PMSAv8_RBAR_A(1)]) +M_CLASS(str r6, [r12, #PMSAv8_RLAR_A(1)]) + + /* Setup Background: 0x0 - min(KERNEL_START, XIP_PHYS_ADDR) */ +#ifdef CONFIG_XIP_KERNEL + ldr r6, =KERNEL_START + ldr r5, =CONFIG_XIP_PHYS_ADDR + cmp r6, r5 + movcs r6, r5 +#else + ldr r6, =KERNEL_START +#endif + cmp r6, #0 + beq 1f + + mov r5, #0 + sub r6, r6, #1 + bic r6, r6, #(PMSAv8_MINALIGN - 1) + + orr r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED | PMSAv8_BAR_XN) + orr r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_DEVICE_nGnRnE) | PMSAv8_LAR_EN) + +AR_CLASS(mcr p15, 0, r5, c6, c9, 0) @ PRBAR2 +AR_CLASS(mcr p15, 0, r6, c6, c9, 1) @ PRLAR2 +M_CLASS(str r5, [r12, #PMSAv8_RBAR_A(2)]) +M_CLASS(str r6, [r12, #PMSAv8_RLAR_A(2)]) + +1: + /* Setup Background: max(KERNEL_END, _exiprom) - 0xffffffff */ +#ifdef CONFIG_XIP_KERNEL + ldr r5, =KERNEL_END + ldr r6, =(_exiprom) + cmp r5, r6 + movcc r5, r6 +#else + ldr r5, =KERNEL_END +#endif + mov r6, #0xffffffff + bic r6, r6, #(PMSAv8_MINALIGN - 1) + + orr r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED | PMSAv8_BAR_XN) + orr r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_DEVICE_nGnRnE) | PMSAv8_LAR_EN) + +AR_CLASS(mcr p15, 0, r5, c6, c9, 4) @ PRBAR3 +AR_CLASS(mcr p15, 0, r6, c6, c9, 5) @ PRLAR3 +M_CLASS(str r5, [r12, #PMSAv8_RBAR_A(3)]) +M_CLASS(str r6, [r12, #PMSAv8_RLAR_A(3)]) + +#ifdef CONFIG_XIP_KERNEL + /* Setup Background: min(_exiprom, KERNEL_END) - max(KERNEL_START, XIP_PHYS_ADDR) */ + ldr r5, =(_exiprom) + ldr r6, =KERNEL_END + cmp r5, r6 + movcs r5, r6 + + ldr r6, =KERNEL_START + ldr r0, =CONFIG_XIP_PHYS_ADDR + cmp r6, r0 + movcc r6, r0 + + sub r6, r6, #1 + bic r6, r6, #(PMSAv8_MINALIGN - 1) + + orr r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED | PMSAv8_BAR_XN) + orr r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_DEVICE_nGnRnE) | PMSAv8_LAR_EN) + +#ifdef CONFIG_CPU_V7M + /* There is no alias for n == 4 */ + mov r0, #4 + str r0, [r12, #PMSAv8_RNR] @ PRSEL + isb + + str r5, [r12, #PMSAv8_RBAR_A(0)] + str r6, [r12, #PMSAv8_RLAR_A(0)] +#else + mcr p15, 0, r5, c6, c10, 0 @ PRBAR4 + mcr p15, 0, r6, c6, c10, 1 @ PRLAR4 +#endif +#endif + ret lr +ENDPROC(__setup_pmsa_v8) + +#ifdef CONFIG_SMP +/* + * r6: pointer at mpu_rgn_info + */ + + .text +ENTRY(__secondary_setup_mpu) + /* Use MPU region info supplied by __cpu_up */ + ldr r6, [r7] @ get secondary_data.mpu_rgn_info + + /* Probe for v7 PMSA compliance */ + mrc p15, 0, r0, c0, c1, 4 @ Read ID_MMFR0 + and r0, r0, #(MMFR0_PMSA) @ PMSA field + teq r0, #(MMFR0_PMSAv7) @ PMSA v7 + beq __secondary_setup_pmsa_v7 + teq r0, #(MMFR0_PMSAv8) @ PMSA v8 + beq __secondary_setup_pmsa_v8 + b __error_p +ENDPROC(__secondary_setup_mpu) + +/* + * r6: pointer at mpu_rgn_info + */ +ENTRY(__secondary_setup_pmsa_v7) + /* Determine whether the D/I-side memory map is unified. We set the + * flags here and continue to use them for the rest of this function */ + mrc p15, 0, r0, c0, c0, 4 @ MPUIR + ands r5, r0, #MPUIR_DREGION_SZMASK @ 0 size d region => No MPU + beq __error_p + + ldr r4, [r6, #MPU_RNG_INFO_USED] + mov r5, #MPU_RNG_SIZE + add r3, r6, #MPU_RNG_INFO_RNGS + mla r3, r4, r5, r3 + +1: + tst r0, #MPUIR_nU @ MPUIR_nU = 0 for unified + sub r3, r3, #MPU_RNG_SIZE + sub r4, r4, #1 + + set_region_nr r0, r4 + isb + + ldr r0, [r3, #MPU_RGN_DRBAR] + ldr r6, [r3, #MPU_RGN_DRSR] + ldr r5, [r3, #MPU_RGN_DRACR] + + setup_region r0, r5, r6, PMSAv7_DATA_SIDE + beq 2f + setup_region r0, r5, r6, PMSAv7_INSTR_SIDE +2: isb + + mrc p15, 0, r0, c0, c0, 4 @ Reevaluate the MPUIR + cmp r4, #0 + bgt 1b + + ret lr +ENDPROC(__secondary_setup_pmsa_v7) + +ENTRY(__secondary_setup_pmsa_v8) + ldr r4, [r6, #MPU_RNG_INFO_USED] +#ifndef CONFIG_XIP_KERNEL + add r4, r4, #1 +#endif + mov r5, #MPU_RNG_SIZE + add r3, r6, #MPU_RNG_INFO_RNGS + mla r3, r4, r5, r3 + +1: + sub r3, r3, #MPU_RNG_SIZE + sub r4, r4, #1 + + mcr p15, 0, r4, c6, c2, 1 @ PRSEL + isb + + ldr r5, [r3, #MPU_RGN_PRBAR] + ldr r6, [r3, #MPU_RGN_PRLAR] + + mcr p15, 0, r5, c6, c3, 0 @ PRBAR + mcr p15, 0, r6, c6, c3, 1 @ PRLAR + + cmp r4, #0 + bgt 1b + + ret lr +ENDPROC(__secondary_setup_pmsa_v8) +#endif /* CONFIG_SMP */ +#endif /* CONFIG_ARM_MPU */ +#include "head-common.S" diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S new file mode 100644 index 000000000..29e290017 --- /dev/null +++ b/arch/arm/kernel/head.S @@ -0,0 +1,594 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/arch/arm/kernel/head.S + * + * Copyright (C) 1994-2002 Russell King + * Copyright (c) 2003 ARM Limited + * All Rights Reserved + * + * Kernel startup code for all 32-bit CPUs + */ +#include <linux/linkage.h> +#include <linux/init.h> +#include <linux/pgtable.h> + +#include <asm/assembler.h> +#include <asm/cp15.h> +#include <asm/domain.h> +#include <asm/ptrace.h> +#include <asm/asm-offsets.h> +#include <asm/memory.h> +#include <asm/thread_info.h> + +#if defined(CONFIG_DEBUG_LL) && !defined(CONFIG_DEBUG_SEMIHOSTING) +#include CONFIG_DEBUG_LL_INCLUDE +#endif +/* + * swapper_pg_dir is the virtual address of the initial page table. + * We place the page tables 16K below KERNEL_RAM_VADDR. Therefore, we must + * make sure that KERNEL_RAM_VADDR is correctly set. Currently, we expect + * the least significant 16 bits to be 0x8000, but we could probably + * relax this restriction to KERNEL_RAM_VADDR >= PAGE_OFFSET + 0x4000. + */ +#define KERNEL_RAM_VADDR (KERNEL_OFFSET + TEXT_OFFSET) +#if (KERNEL_RAM_VADDR & 0xffff) != 0x8000 +#error KERNEL_RAM_VADDR must start at 0xXXXX8000 +#endif + +#ifdef CONFIG_ARM_LPAE + /* LPAE requires an additional page for the PGD */ +#define PG_DIR_SIZE 0x5000 +#define PMD_ENTRY_ORDER 3 /* PMD entry size is 2^PMD_ENTRY_ORDER */ +#else +#define PG_DIR_SIZE 0x4000 +#define PMD_ENTRY_ORDER 2 +#endif + + .globl swapper_pg_dir + .equ swapper_pg_dir, KERNEL_RAM_VADDR - PG_DIR_SIZE + + /* + * This needs to be assigned at runtime when the linker symbols are + * resolved. These are unsigned 64bit really, but in this assembly code + * We store them as 32bit. + */ + .pushsection .data + .align 2 + .globl kernel_sec_start + .globl kernel_sec_end +kernel_sec_start: + .long 0 + .long 0 +kernel_sec_end: + .long 0 + .long 0 + .popsection + + .macro pgtbl, rd, phys + add \rd, \phys, #TEXT_OFFSET + sub \rd, \rd, #PG_DIR_SIZE + .endm + +/* + * Kernel startup entry point. + * --------------------------- + * + * This is normally called from the decompressor code. The requirements + * are: MMU = off, D-cache = off, I-cache = dont care, r0 = 0, + * r1 = machine nr, r2 = atags or dtb pointer. + * + * This code is mostly position independent, so if you link the kernel at + * 0xc0008000, you call this at __pa(0xc0008000). + * + * See linux/arch/arm/tools/mach-types for the complete list of machine + * numbers for r1. + * + * We're trying to keep crap to a minimum; DO NOT add any machine specific + * crap here - that's what the boot loader (or in extreme, well justified + * circumstances, zImage) is for. + */ + .arm + + __HEAD +ENTRY(stext) + ARM_BE8(setend be ) @ ensure we are in BE8 mode + + THUMB( badr r9, 1f ) @ Kernel is always entered in ARM. + THUMB( bx r9 ) @ If this is a Thumb-2 kernel, + THUMB( .thumb ) @ switch to Thumb now. + THUMB(1: ) + +#ifdef CONFIG_ARM_VIRT_EXT + bl __hyp_stub_install +#endif + @ ensure svc mode and all interrupts masked + safe_svcmode_maskall r9 + + mrc p15, 0, r9, c0, c0 @ get processor id + bl __lookup_processor_type @ r5=procinfo r9=cpuid + movs r10, r5 @ invalid processor (r5=0)? + THUMB( it eq ) @ force fixup-able long branch encoding + beq __error_p @ yes, error 'p' + +#ifdef CONFIG_ARM_LPAE + mrc p15, 0, r3, c0, c1, 4 @ read ID_MMFR0 + and r3, r3, #0xf @ extract VMSA support + cmp r3, #5 @ long-descriptor translation table format? + THUMB( it lo ) @ force fixup-able long branch encoding + blo __error_lpae @ only classic page table format +#endif + +#ifndef CONFIG_XIP_KERNEL + adr_l r8, _text @ __pa(_text) + sub r8, r8, #TEXT_OFFSET @ PHYS_OFFSET +#else + ldr r8, =PLAT_PHYS_OFFSET @ always constant in this case +#endif + + /* + * r1 = machine no, r2 = atags or dtb, + * r8 = phys_offset, r9 = cpuid, r10 = procinfo + */ + bl __vet_atags +#ifdef CONFIG_SMP_ON_UP + bl __fixup_smp +#endif +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT + bl __fixup_pv_table +#endif + bl __create_page_tables + + /* + * The following calls CPU specific code in a position independent + * manner. See arch/arm/mm/proc-*.S for details. r10 = base of + * xxx_proc_info structure selected by __lookup_processor_type + * above. + * + * The processor init function will be called with: + * r1 - machine type + * r2 - boot data (atags/dt) pointer + * r4 - translation table base (low word) + * r5 - translation table base (high word, if LPAE) + * r8 - translation table base 1 (pfn if LPAE) + * r9 - cpuid + * r13 - virtual address for __enable_mmu -> __turn_mmu_on + * + * On return, the CPU will be ready for the MMU to be turned on, + * r0 will hold the CPU control register value, r1, r2, r4, and + * r9 will be preserved. r5 will also be preserved if LPAE. + */ + ldr r13, =__mmap_switched @ address to jump to after + @ mmu has been enabled + badr lr, 1f @ return (PIC) address +#ifdef CONFIG_ARM_LPAE + mov r5, #0 @ high TTBR0 + mov r8, r4, lsr #12 @ TTBR1 is swapper_pg_dir pfn +#else + mov r8, r4 @ set TTBR1 to swapper_pg_dir +#endif + ldr r12, [r10, #PROCINFO_INITFUNC] + add r12, r12, r10 + ret r12 +1: b __enable_mmu +ENDPROC(stext) + .ltorg + +/* + * Setup the initial page tables. We only setup the barest + * amount which are required to get the kernel running, which + * generally means mapping in the kernel code. + * + * r8 = phys_offset, r9 = cpuid, r10 = procinfo + * + * Returns: + * r0, r3, r5-r7 corrupted + * r4 = physical page table address + */ +__create_page_tables: + pgtbl r4, r8 @ page table address + + /* + * Clear the swapper page table + */ + mov r0, r4 + mov r3, #0 + add r6, r0, #PG_DIR_SIZE +1: str r3, [r0], #4 + str r3, [r0], #4 + str r3, [r0], #4 + str r3, [r0], #4 + teq r0, r6 + bne 1b + +#ifdef CONFIG_ARM_LPAE + /* + * Build the PGD table (first level) to point to the PMD table. A PGD + * entry is 64-bit wide. + */ + mov r0, r4 + add r3, r4, #0x1000 @ first PMD table address + orr r3, r3, #3 @ PGD block type + mov r6, #4 @ PTRS_PER_PGD + mov r7, #1 << (55 - 32) @ L_PGD_SWAPPER +1: +#ifdef CONFIG_CPU_ENDIAN_BE8 + str r7, [r0], #4 @ set top PGD entry bits + str r3, [r0], #4 @ set bottom PGD entry bits +#else + str r3, [r0], #4 @ set bottom PGD entry bits + str r7, [r0], #4 @ set top PGD entry bits +#endif + add r3, r3, #0x1000 @ next PMD table + subs r6, r6, #1 + bne 1b + + add r4, r4, #0x1000 @ point to the PMD tables +#ifdef CONFIG_CPU_ENDIAN_BE8 + add r4, r4, #4 @ we only write the bottom word +#endif +#endif + + ldr r7, [r10, #PROCINFO_MM_MMUFLAGS] @ mm_mmuflags + + /* + * Create identity mapping to cater for __enable_mmu. + * This identity mapping will be removed by paging_init(). + */ + adr_l r5, __turn_mmu_on @ _pa(__turn_mmu_on) + adr_l r6, __turn_mmu_on_end @ _pa(__turn_mmu_on_end) + mov r5, r5, lsr #SECTION_SHIFT + mov r6, r6, lsr #SECTION_SHIFT + +1: orr r3, r7, r5, lsl #SECTION_SHIFT @ flags + kernel base + str r3, [r4, r5, lsl #PMD_ENTRY_ORDER] @ identity mapping + cmp r5, r6 + addlo r5, r5, #1 @ next section + blo 1b + + /* + * The main matter: map in the kernel using section mappings, and + * set two variables to indicate the physical start and end of the + * kernel. + */ + add r0, r4, #KERNEL_OFFSET >> (SECTION_SHIFT - PMD_ENTRY_ORDER) + ldr r6, =(_end - 1) + adr_l r5, kernel_sec_start @ _pa(kernel_sec_start) +#if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32 + str r8, [r5, #4] @ Save physical start of kernel (BE) +#else + str r8, [r5] @ Save physical start of kernel (LE) +#endif + orr r3, r8, r7 @ Add the MMU flags + add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ENTRY_ORDER) +1: str r3, [r0], #1 << PMD_ENTRY_ORDER + add r3, r3, #1 << SECTION_SHIFT + cmp r0, r6 + bls 1b + eor r3, r3, r7 @ Remove the MMU flags + adr_l r5, kernel_sec_end @ _pa(kernel_sec_end) +#if defined CONFIG_CPU_ENDIAN_BE8 || defined CONFIG_CPU_ENDIAN_BE32 + str r3, [r5, #4] @ Save physical end of kernel (BE) +#else + str r3, [r5] @ Save physical end of kernel (LE) +#endif + +#ifdef CONFIG_XIP_KERNEL + /* + * Map the kernel image separately as it is not located in RAM. + */ +#define XIP_START XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR) + mov r3, pc + mov r3, r3, lsr #SECTION_SHIFT + orr r3, r7, r3, lsl #SECTION_SHIFT + add r0, r4, #(XIP_START & 0xff000000) >> (SECTION_SHIFT - PMD_ENTRY_ORDER) + str r3, [r0, #((XIP_START & 0x00f00000) >> SECTION_SHIFT) << PMD_ENTRY_ORDER]! + ldr r6, =(_edata_loc - 1) + add r0, r0, #1 << PMD_ENTRY_ORDER + add r6, r4, r6, lsr #(SECTION_SHIFT - PMD_ENTRY_ORDER) +1: cmp r0, r6 + add r3, r3, #1 << SECTION_SHIFT + strls r3, [r0], #1 << PMD_ENTRY_ORDER + bls 1b +#endif + + /* + * Then map boot params address in r2 if specified. + * We map 2 sections in case the ATAGs/DTB crosses a section boundary. + */ + mov r0, r2, lsr #SECTION_SHIFT + cmp r2, #0 + ldrne r3, =FDT_FIXED_BASE >> (SECTION_SHIFT - PMD_ENTRY_ORDER) + addne r3, r3, r4 + orrne r6, r7, r0, lsl #SECTION_SHIFT + strne r6, [r3], #1 << PMD_ENTRY_ORDER + addne r6, r6, #1 << SECTION_SHIFT + strne r6, [r3] + +#if defined(CONFIG_ARM_LPAE) && defined(CONFIG_CPU_ENDIAN_BE8) + sub r4, r4, #4 @ Fixup page table pointer + @ for 64-bit descriptors +#endif + +#ifdef CONFIG_DEBUG_LL +#if !defined(CONFIG_DEBUG_ICEDCC) && !defined(CONFIG_DEBUG_SEMIHOSTING) + /* + * Map in IO space for serial debugging. + * This allows debug messages to be output + * via a serial console before paging_init. + */ + addruart r7, r3, r0 + + mov r3, r3, lsr #SECTION_SHIFT + mov r3, r3, lsl #PMD_ENTRY_ORDER + + add r0, r4, r3 + mov r3, r7, lsr #SECTION_SHIFT + ldr r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags + orr r3, r7, r3, lsl #SECTION_SHIFT +#ifdef CONFIG_ARM_LPAE + mov r7, #1 << (54 - 32) @ XN +#ifdef CONFIG_CPU_ENDIAN_BE8 + str r7, [r0], #4 + str r3, [r0], #4 +#else + str r3, [r0], #4 + str r7, [r0], #4 +#endif +#else + orr r3, r3, #PMD_SECT_XN + str r3, [r0], #4 +#endif + +#else /* CONFIG_DEBUG_ICEDCC || CONFIG_DEBUG_SEMIHOSTING */ + /* we don't need any serial debugging mappings */ + ldr r7, [r10, #PROCINFO_IO_MMUFLAGS] @ io_mmuflags +#endif + +#if defined(CONFIG_ARCH_NETWINDER) || defined(CONFIG_ARCH_CATS) + /* + * If we're using the NetWinder or CATS, we also need to map + * in the 16550-type serial port for the debug messages + */ + add r0, r4, #0xff000000 >> (SECTION_SHIFT - PMD_ENTRY_ORDER) + orr r3, r7, #0x7c000000 + str r3, [r0] +#endif +#ifdef CONFIG_ARCH_RPC + /* + * Map in screen at 0x02000000 & SCREEN2_BASE + * Similar reasons here - for debug. This is + * only for Acorn RiscPC architectures. + */ + add r0, r4, #0x02000000 >> (SECTION_SHIFT - PMD_ENTRY_ORDER) + orr r3, r7, #0x02000000 + str r3, [r0] + add r0, r4, #0xd8000000 >> (SECTION_SHIFT - PMD_ENTRY_ORDER) + str r3, [r0] +#endif +#endif +#ifdef CONFIG_ARM_LPAE + sub r4, r4, #0x1000 @ point to the PGD table +#endif + ret lr +ENDPROC(__create_page_tables) + .ltorg + +#if defined(CONFIG_SMP) + .text + .arm +ENTRY(secondary_startup_arm) + THUMB( badr r9, 1f ) @ Kernel is entered in ARM. + THUMB( bx r9 ) @ If this is a Thumb-2 kernel, + THUMB( .thumb ) @ switch to Thumb now. + THUMB(1: ) +ENTRY(secondary_startup) + /* + * Common entry point for secondary CPUs. + * + * Ensure that we're in SVC mode, and IRQs are disabled. Lookup + * the processor type - there is no need to check the machine type + * as it has already been validated by the primary processor. + */ + + ARM_BE8(setend be) @ ensure we are in BE8 mode + +#ifdef CONFIG_ARM_VIRT_EXT + bl __hyp_stub_install_secondary +#endif + safe_svcmode_maskall r9 + + mrc p15, 0, r9, c0, c0 @ get processor id + bl __lookup_processor_type + movs r10, r5 @ invalid processor? + moveq r0, #'p' @ yes, error 'p' + THUMB( it eq ) @ force fixup-able long branch encoding + beq __error_p + + /* + * Use the page tables supplied from __cpu_up. + */ + adr_l r3, secondary_data + mov_l r12, __secondary_switched + ldrd r4, r5, [r3, #0] @ get secondary_data.pgdir +ARM_BE8(eor r4, r4, r5) @ Swap r5 and r4 in BE: +ARM_BE8(eor r5, r4, r5) @ it can be done in 3 steps +ARM_BE8(eor r4, r4, r5) @ without using a temp reg. + ldr r8, [r3, #8] @ get secondary_data.swapper_pg_dir + badr lr, __enable_mmu @ return address + mov r13, r12 @ __secondary_switched address + ldr r12, [r10, #PROCINFO_INITFUNC] + add r12, r12, r10 @ initialise processor + @ (return control reg) + ret r12 +ENDPROC(secondary_startup) +ENDPROC(secondary_startup_arm) + +ENTRY(__secondary_switched) +#if defined(CONFIG_VMAP_STACK) && !defined(CONFIG_ARM_LPAE) + @ Before using the vmap'ed stack, we have to switch to swapper_pg_dir + @ as the ID map does not cover the vmalloc region. + mrc p15, 0, ip, c2, c0, 1 @ read TTBR1 + mcr p15, 0, ip, c2, c0, 0 @ set TTBR0 + instr_sync +#endif + adr_l r7, secondary_data + 12 @ get secondary_data.stack + ldr sp, [r7] + ldr r0, [r7, #4] @ get secondary_data.task + mov fp, #0 + b secondary_start_kernel +ENDPROC(__secondary_switched) + +#endif /* defined(CONFIG_SMP) */ + + + +/* + * Setup common bits before finally enabling the MMU. Essentially + * this is just loading the page table pointer and domain access + * registers. All these registers need to be preserved by the + * processor setup function (or set in the case of r0) + * + * r0 = cp#15 control register + * r1 = machine ID + * r2 = atags or dtb pointer + * r4 = TTBR pointer (low word) + * r5 = TTBR pointer (high word if LPAE) + * r9 = processor ID + * r13 = *virtual* address to jump to upon completion + */ +__enable_mmu: +#if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6 + orr r0, r0, #CR_A +#else + bic r0, r0, #CR_A +#endif +#ifdef CONFIG_CPU_DCACHE_DISABLE + bic r0, r0, #CR_C +#endif +#ifdef CONFIG_CPU_BPREDICT_DISABLE + bic r0, r0, #CR_Z +#endif +#ifdef CONFIG_CPU_ICACHE_DISABLE + bic r0, r0, #CR_I +#endif +#ifdef CONFIG_ARM_LPAE + mcrr p15, 0, r4, r5, c2 @ load TTBR0 +#else + mov r5, #DACR_INIT + mcr p15, 0, r5, c3, c0, 0 @ load domain access register + mcr p15, 0, r4, c2, c0, 0 @ load page table pointer +#endif + b __turn_mmu_on +ENDPROC(__enable_mmu) + +/* + * Enable the MMU. This completely changes the structure of the visible + * memory space. You will not be able to trace execution through this. + * If you have an enquiry about this, *please* check the linux-arm-kernel + * mailing list archives BEFORE sending another post to the list. + * + * r0 = cp#15 control register + * r1 = machine ID + * r2 = atags or dtb pointer + * r9 = processor ID + * r13 = *virtual* address to jump to upon completion + * + * other registers depend on the function called upon completion + */ + .align 5 + .pushsection .idmap.text, "ax" +ENTRY(__turn_mmu_on) + mov r0, r0 + instr_sync + mcr p15, 0, r0, c1, c0, 0 @ write control reg + mrc p15, 0, r3, c0, c0, 0 @ read id reg + instr_sync + mov r3, r3 + mov r3, r13 + ret r3 +__turn_mmu_on_end: +ENDPROC(__turn_mmu_on) + .popsection + + +#ifdef CONFIG_SMP_ON_UP + __HEAD +__fixup_smp: + and r3, r9, #0x000f0000 @ architecture version + teq r3, #0x000f0000 @ CPU ID supported? + bne __fixup_smp_on_up @ no, assume UP + + bic r3, r9, #0x00ff0000 + bic r3, r3, #0x0000000f @ mask 0xff00fff0 + mov r4, #0x41000000 + orr r4, r4, #0x0000b000 + orr r4, r4, #0x00000020 @ val 0x4100b020 + teq r3, r4 @ ARM 11MPCore? + reteq lr @ yes, assume SMP + + mrc p15, 0, r0, c0, c0, 5 @ read MPIDR + and r0, r0, #0xc0000000 @ multiprocessing extensions and + teq r0, #0x80000000 @ not part of a uniprocessor system? + bne __fixup_smp_on_up @ no, assume UP + + @ Core indicates it is SMP. Check for Aegis SOC where a single + @ Cortex-A9 CPU is present but SMP operations fault. + mov r4, #0x41000000 + orr r4, r4, #0x0000c000 + orr r4, r4, #0x00000090 + teq r3, r4 @ Check for ARM Cortex-A9 + retne lr @ Not ARM Cortex-A9, + + @ If a future SoC *does* use 0x0 as the PERIPH_BASE, then the + @ below address check will need to be #ifdef'd or equivalent + @ for the Aegis platform. + mrc p15, 4, r0, c15, c0 @ get SCU base address + teq r0, #0x0 @ '0' on actual UP A9 hardware + beq __fixup_smp_on_up @ So its an A9 UP + ldr r0, [r0, #4] @ read SCU Config +ARM_BE8(rev r0, r0) @ byteswap if big endian + and r0, r0, #0x3 @ number of CPUs + teq r0, #0x0 @ is 1? + retne lr + +__fixup_smp_on_up: + adr_l r4, __smpalt_begin + adr_l r5, __smpalt_end + b __do_fixup_smp_on_up +ENDPROC(__fixup_smp) + + .pushsection .data + .align 2 + .globl smp_on_up +smp_on_up: + ALT_SMP(.long 1) + ALT_UP(.long 0) + .popsection +#endif + + .text +__do_fixup_smp_on_up: + cmp r4, r5 + reths lr + ldmia r4, {r0, r6} + ARM( str r6, [r0, r4] ) + THUMB( add r0, r0, r4 ) + add r4, r4, #8 +#ifdef __ARMEB__ + THUMB( mov r6, r6, ror #16 ) @ Convert word order for big-endian. +#endif + THUMB( strh r6, [r0], #2 ) @ For Thumb-2, store as two halfwords + THUMB( mov r6, r6, lsr #16 ) @ to be robust against misaligned r0. + THUMB( strh r6, [r0] ) + b __do_fixup_smp_on_up +ENDPROC(__do_fixup_smp_on_up) + +ENTRY(fixup_smp) + stmfd sp!, {r4 - r6, lr} + mov r4, r0 + add r5, r0, r1 + bl __do_fixup_smp_on_up + ldmfd sp!, {r4 - r6, pc} +ENDPROC(fixup_smp) + +#include "head-common.S" diff --git a/arch/arm/kernel/hibernate.c b/arch/arm/kernel/hibernate.c new file mode 100644 index 000000000..2373020af --- /dev/null +++ b/arch/arm/kernel/hibernate.c @@ -0,0 +1,105 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Hibernation support specific for ARM + * + * Derived from work on ARM hibernation support by: + * + * Ubuntu project, hibernation support for mach-dove + * Copyright (C) 2010 Nokia Corporation (Hiroshi Doyu) + * Copyright (C) 2010 Texas Instruments, Inc. (Teerth Reddy et al.) + * https://lkml.org/lkml/2010/6/18/4 + * https://lists.linux-foundation.org/pipermail/linux-pm/2010-June/027422.html + * https://patchwork.kernel.org/patch/96442/ + * + * Copyright (C) 2006 Rafael J. Wysocki <rjw@sisk.pl> + */ + +#include <linux/mm.h> +#include <linux/suspend.h> +#include <asm/system_misc.h> +#include <asm/idmap.h> +#include <asm/suspend.h> +#include <asm/memory.h> +#include <asm/sections.h> +#include "reboot.h" + +int pfn_is_nosave(unsigned long pfn) +{ + unsigned long nosave_begin_pfn = virt_to_pfn(&__nosave_begin); + unsigned long nosave_end_pfn = virt_to_pfn(&__nosave_end - 1); + + return (pfn >= nosave_begin_pfn) && (pfn <= nosave_end_pfn); +} + +void notrace save_processor_state(void) +{ + WARN_ON(num_online_cpus() != 1); + local_fiq_disable(); +} + +void notrace restore_processor_state(void) +{ + local_fiq_enable(); +} + +/* + * Snapshot kernel memory and reset the system. + * + * swsusp_save() is executed in the suspend finisher so that the CPU + * context pointer and memory are part of the saved image, which is + * required by the resume kernel image to restart execution from + * swsusp_arch_suspend(). + * + * soft_restart is not technically needed, but is used to get success + * returned from cpu_suspend. + * + * When soft reboot completes, the hibernation snapshot is written out. + */ +static int notrace arch_save_image(unsigned long unused) +{ + int ret; + + ret = swsusp_save(); + if (ret == 0) + _soft_restart(virt_to_idmap(cpu_resume), false); + return ret; +} + +/* + * Save the current CPU state before suspend / poweroff. + */ +int notrace swsusp_arch_suspend(void) +{ + return cpu_suspend(0, arch_save_image); +} + +/* + * Restore page contents for physical pages that were in use during loading + * hibernation image. Switch to idmap_pgd so the physical page tables + * are overwritten with the same contents. + */ +static void notrace arch_restore_image(void *unused) +{ + struct pbe *pbe; + + cpu_switch_mm(idmap_pgd, &init_mm); + for (pbe = restore_pblist; pbe; pbe = pbe->next) + copy_page(pbe->orig_address, pbe->address); + + _soft_restart(virt_to_idmap(cpu_resume), false); +} + +static u64 resume_stack[PAGE_SIZE/2/sizeof(u64)] __nosavedata; + +/* + * Resume from the hibernation image. + * Due to the kernel heap / data restore, stack contents change underneath + * and that would make function calls impossible; switch to a temporary + * stack within the nosave region to avoid that problem. + */ +int swsusp_arch_resume(void) +{ + call_with_stack(arch_restore_image, 0, + resume_stack + ARRAY_SIZE(resume_stack)); + return 0; +} diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c new file mode 100644 index 000000000..dc0fb7a81 --- /dev/null +++ b/arch/arm/kernel/hw_breakpoint.c @@ -0,0 +1,1231 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * + * Copyright (C) 2009, 2010 ARM Limited + * + * Author: Will Deacon <will.deacon@arm.com> + */ + +/* + * HW_breakpoint: a unified kernel/user-space hardware breakpoint facility, + * using the CPU's debug registers. + */ +#define pr_fmt(fmt) "hw-breakpoint: " fmt + +#include <linux/errno.h> +#include <linux/hardirq.h> +#include <linux/perf_event.h> +#include <linux/hw_breakpoint.h> +#include <linux/smp.h> +#include <linux/cpu_pm.h> +#include <linux/coresight.h> + +#include <asm/cacheflush.h> +#include <asm/cputype.h> +#include <asm/current.h> +#include <asm/hw_breakpoint.h> +#include <asm/traps.h> + +/* Breakpoint currently in use for each BRP. */ +static DEFINE_PER_CPU(struct perf_event *, bp_on_reg[ARM_MAX_BRP]); + +/* Watchpoint currently in use for each WRP. */ +static DEFINE_PER_CPU(struct perf_event *, wp_on_reg[ARM_MAX_WRP]); + +/* Number of BRP/WRP registers on this CPU. */ +static int core_num_brps __ro_after_init; +static int core_num_wrps __ro_after_init; + +/* Debug architecture version. */ +static u8 debug_arch __ro_after_init; + +/* Does debug architecture support OS Save and Restore? */ +static bool has_ossr __ro_after_init; + +/* Maximum supported watchpoint length. */ +static u8 max_watchpoint_len __ro_after_init; + +#define READ_WB_REG_CASE(OP2, M, VAL) \ + case ((OP2 << 4) + M): \ + ARM_DBG_READ(c0, c ## M, OP2, VAL); \ + break + +#define WRITE_WB_REG_CASE(OP2, M, VAL) \ + case ((OP2 << 4) + M): \ + ARM_DBG_WRITE(c0, c ## M, OP2, VAL); \ + break + +#define GEN_READ_WB_REG_CASES(OP2, VAL) \ + READ_WB_REG_CASE(OP2, 0, VAL); \ + READ_WB_REG_CASE(OP2, 1, VAL); \ + READ_WB_REG_CASE(OP2, 2, VAL); \ + READ_WB_REG_CASE(OP2, 3, VAL); \ + READ_WB_REG_CASE(OP2, 4, VAL); \ + READ_WB_REG_CASE(OP2, 5, VAL); \ + READ_WB_REG_CASE(OP2, 6, VAL); \ + READ_WB_REG_CASE(OP2, 7, VAL); \ + READ_WB_REG_CASE(OP2, 8, VAL); \ + READ_WB_REG_CASE(OP2, 9, VAL); \ + READ_WB_REG_CASE(OP2, 10, VAL); \ + READ_WB_REG_CASE(OP2, 11, VAL); \ + READ_WB_REG_CASE(OP2, 12, VAL); \ + READ_WB_REG_CASE(OP2, 13, VAL); \ + READ_WB_REG_CASE(OP2, 14, VAL); \ + READ_WB_REG_CASE(OP2, 15, VAL) + +#define GEN_WRITE_WB_REG_CASES(OP2, VAL) \ + WRITE_WB_REG_CASE(OP2, 0, VAL); \ + WRITE_WB_REG_CASE(OP2, 1, VAL); \ + WRITE_WB_REG_CASE(OP2, 2, VAL); \ + WRITE_WB_REG_CASE(OP2, 3, VAL); \ + WRITE_WB_REG_CASE(OP2, 4, VAL); \ + WRITE_WB_REG_CASE(OP2, 5, VAL); \ + WRITE_WB_REG_CASE(OP2, 6, VAL); \ + WRITE_WB_REG_CASE(OP2, 7, VAL); \ + WRITE_WB_REG_CASE(OP2, 8, VAL); \ + WRITE_WB_REG_CASE(OP2, 9, VAL); \ + WRITE_WB_REG_CASE(OP2, 10, VAL); \ + WRITE_WB_REG_CASE(OP2, 11, VAL); \ + WRITE_WB_REG_CASE(OP2, 12, VAL); \ + WRITE_WB_REG_CASE(OP2, 13, VAL); \ + WRITE_WB_REG_CASE(OP2, 14, VAL); \ + WRITE_WB_REG_CASE(OP2, 15, VAL) + +static u32 read_wb_reg(int n) +{ + u32 val = 0; + + switch (n) { + GEN_READ_WB_REG_CASES(ARM_OP2_BVR, val); + GEN_READ_WB_REG_CASES(ARM_OP2_BCR, val); + GEN_READ_WB_REG_CASES(ARM_OP2_WVR, val); + GEN_READ_WB_REG_CASES(ARM_OP2_WCR, val); + default: + pr_warn("attempt to read from unknown breakpoint register %d\n", + n); + } + + return val; +} + +static void write_wb_reg(int n, u32 val) +{ + switch (n) { + GEN_WRITE_WB_REG_CASES(ARM_OP2_BVR, val); + GEN_WRITE_WB_REG_CASES(ARM_OP2_BCR, val); + GEN_WRITE_WB_REG_CASES(ARM_OP2_WVR, val); + GEN_WRITE_WB_REG_CASES(ARM_OP2_WCR, val); + default: + pr_warn("attempt to write to unknown breakpoint register %d\n", + n); + } + isb(); +} + +/* Determine debug architecture. */ +static u8 get_debug_arch(void) +{ + u32 didr; + + /* Do we implement the extended CPUID interface? */ + if (((read_cpuid_id() >> 16) & 0xf) != 0xf) { + pr_warn_once("CPUID feature registers not supported. " + "Assuming v6 debug is present.\n"); + return ARM_DEBUG_ARCH_V6; + } + + ARM_DBG_READ(c0, c0, 0, didr); + return (didr >> 16) & 0xf; +} + +u8 arch_get_debug_arch(void) +{ + return debug_arch; +} + +static int debug_arch_supported(void) +{ + u8 arch = get_debug_arch(); + + /* We don't support the memory-mapped interface. */ + return (arch >= ARM_DEBUG_ARCH_V6 && arch <= ARM_DEBUG_ARCH_V7_ECP14) || + arch >= ARM_DEBUG_ARCH_V7_1; +} + +/* Can we determine the watchpoint access type from the fsr? */ +static int debug_exception_updates_fsr(void) +{ + return get_debug_arch() >= ARM_DEBUG_ARCH_V8; +} + +/* Determine number of WRP registers available. */ +static int get_num_wrp_resources(void) +{ + u32 didr; + ARM_DBG_READ(c0, c0, 0, didr); + return ((didr >> 28) & 0xf) + 1; +} + +/* Determine number of BRP registers available. */ +static int get_num_brp_resources(void) +{ + u32 didr; + ARM_DBG_READ(c0, c0, 0, didr); + return ((didr >> 24) & 0xf) + 1; +} + +/* Does this core support mismatch breakpoints? */ +static int core_has_mismatch_brps(void) +{ + return (get_debug_arch() >= ARM_DEBUG_ARCH_V7_ECP14 && + get_num_brp_resources() > 1); +} + +/* Determine number of usable WRPs available. */ +static int get_num_wrps(void) +{ + /* + * On debug architectures prior to 7.1, when a watchpoint fires, the + * only way to work out which watchpoint it was is by disassembling + * the faulting instruction and working out the address of the memory + * access. + * + * Furthermore, we can only do this if the watchpoint was precise + * since imprecise watchpoints prevent us from calculating register + * based addresses. + * + * Providing we have more than 1 breakpoint register, we only report + * a single watchpoint register for the time being. This way, we always + * know which watchpoint fired. In the future we can either add a + * disassembler and address generation emulator, or we can insert a + * check to see if the DFAR is set on watchpoint exception entry + * [the ARM ARM states that the DFAR is UNKNOWN, but experience shows + * that it is set on some implementations]. + */ + if (get_debug_arch() < ARM_DEBUG_ARCH_V7_1) + return 1; + + return get_num_wrp_resources(); +} + +/* Determine number of usable BRPs available. */ +static int get_num_brps(void) +{ + int brps = get_num_brp_resources(); + return core_has_mismatch_brps() ? brps - 1 : brps; +} + +/* + * In order to access the breakpoint/watchpoint control registers, + * we must be running in debug monitor mode. Unfortunately, we can + * be put into halting debug mode at any time by an external debugger + * but there is nothing we can do to prevent that. + */ +static int monitor_mode_enabled(void) +{ + u32 dscr; + ARM_DBG_READ(c0, c1, 0, dscr); + return !!(dscr & ARM_DSCR_MDBGEN); +} + +static int enable_monitor_mode(void) +{ + u32 dscr; + ARM_DBG_READ(c0, c1, 0, dscr); + + /* If monitor mode is already enabled, just return. */ + if (dscr & ARM_DSCR_MDBGEN) + goto out; + + /* Write to the corresponding DSCR. */ + switch (get_debug_arch()) { + case ARM_DEBUG_ARCH_V6: + case ARM_DEBUG_ARCH_V6_1: + ARM_DBG_WRITE(c0, c1, 0, (dscr | ARM_DSCR_MDBGEN)); + break; + case ARM_DEBUG_ARCH_V7_ECP14: + case ARM_DEBUG_ARCH_V7_1: + case ARM_DEBUG_ARCH_V8: + case ARM_DEBUG_ARCH_V8_1: + case ARM_DEBUG_ARCH_V8_2: + case ARM_DEBUG_ARCH_V8_4: + ARM_DBG_WRITE(c0, c2, 2, (dscr | ARM_DSCR_MDBGEN)); + isb(); + break; + default: + return -ENODEV; + } + + /* Check that the write made it through. */ + ARM_DBG_READ(c0, c1, 0, dscr); + if (!(dscr & ARM_DSCR_MDBGEN)) { + pr_warn_once("Failed to enable monitor mode on CPU %d.\n", + smp_processor_id()); + return -EPERM; + } + +out: + return 0; +} + +int hw_breakpoint_slots(int type) +{ + if (!debug_arch_supported()) + return 0; + + /* + * We can be called early, so don't rely on + * our static variables being initialised. + */ + switch (type) { + case TYPE_INST: + return get_num_brps(); + case TYPE_DATA: + return get_num_wrps(); + default: + pr_warn("unknown slot type: %d\n", type); + return 0; + } +} + +/* + * Check if 8-bit byte-address select is available. + * This clobbers WRP 0. + */ +static u8 get_max_wp_len(void) +{ + u32 ctrl_reg; + struct arch_hw_breakpoint_ctrl ctrl; + u8 size = 4; + + if (debug_arch < ARM_DEBUG_ARCH_V7_ECP14) + goto out; + + memset(&ctrl, 0, sizeof(ctrl)); + ctrl.len = ARM_BREAKPOINT_LEN_8; + ctrl_reg = encode_ctrl_reg(ctrl); + + write_wb_reg(ARM_BASE_WVR, 0); + write_wb_reg(ARM_BASE_WCR, ctrl_reg); + if ((read_wb_reg(ARM_BASE_WCR) & ctrl_reg) == ctrl_reg) + size = 8; + +out: + return size; +} + +u8 arch_get_max_wp_len(void) +{ + return max_watchpoint_len; +} + +/* + * Install a perf counter breakpoint. + */ +int arch_install_hw_breakpoint(struct perf_event *bp) +{ + struct arch_hw_breakpoint *info = counter_arch_bp(bp); + struct perf_event **slot, **slots; + int i, max_slots, ctrl_base, val_base; + u32 addr, ctrl; + + addr = info->address; + ctrl = encode_ctrl_reg(info->ctrl) | 0x1; + + if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { + /* Breakpoint */ + ctrl_base = ARM_BASE_BCR; + val_base = ARM_BASE_BVR; + slots = this_cpu_ptr(bp_on_reg); + max_slots = core_num_brps; + } else { + /* Watchpoint */ + ctrl_base = ARM_BASE_WCR; + val_base = ARM_BASE_WVR; + slots = this_cpu_ptr(wp_on_reg); + max_slots = core_num_wrps; + } + + for (i = 0; i < max_slots; ++i) { + slot = &slots[i]; + + if (!*slot) { + *slot = bp; + break; + } + } + + if (i == max_slots) { + pr_warn("Can't find any breakpoint slot\n"); + return -EBUSY; + } + + /* Override the breakpoint data with the step data. */ + if (info->step_ctrl.enabled) { + addr = info->trigger & ~0x3; + ctrl = encode_ctrl_reg(info->step_ctrl); + if (info->ctrl.type != ARM_BREAKPOINT_EXECUTE) { + i = 0; + ctrl_base = ARM_BASE_BCR + core_num_brps; + val_base = ARM_BASE_BVR + core_num_brps; + } + } + + /* Setup the address register. */ + write_wb_reg(val_base + i, addr); + + /* Setup the control register. */ + write_wb_reg(ctrl_base + i, ctrl); + return 0; +} + +void arch_uninstall_hw_breakpoint(struct perf_event *bp) +{ + struct arch_hw_breakpoint *info = counter_arch_bp(bp); + struct perf_event **slot, **slots; + int i, max_slots, base; + + if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) { + /* Breakpoint */ + base = ARM_BASE_BCR; + slots = this_cpu_ptr(bp_on_reg); + max_slots = core_num_brps; + } else { + /* Watchpoint */ + base = ARM_BASE_WCR; + slots = this_cpu_ptr(wp_on_reg); + max_slots = core_num_wrps; + } + + /* Remove the breakpoint. */ + for (i = 0; i < max_slots; ++i) { + slot = &slots[i]; + + if (*slot == bp) { + *slot = NULL; + break; + } + } + + if (i == max_slots) { + pr_warn("Can't find any breakpoint slot\n"); + return; + } + + /* Ensure that we disable the mismatch breakpoint. */ + if (info->ctrl.type != ARM_BREAKPOINT_EXECUTE && + info->step_ctrl.enabled) { + i = 0; + base = ARM_BASE_BCR + core_num_brps; + } + + /* Reset the control register. */ + write_wb_reg(base + i, 0); +} + +static int get_hbp_len(u8 hbp_len) +{ + unsigned int len_in_bytes = 0; + + switch (hbp_len) { + case ARM_BREAKPOINT_LEN_1: + len_in_bytes = 1; + break; + case ARM_BREAKPOINT_LEN_2: + len_in_bytes = 2; + break; + case ARM_BREAKPOINT_LEN_4: + len_in_bytes = 4; + break; + case ARM_BREAKPOINT_LEN_8: + len_in_bytes = 8; + break; + } + + return len_in_bytes; +} + +/* + * Check whether bp virtual address is in kernel space. + */ +int arch_check_bp_in_kernelspace(struct arch_hw_breakpoint *hw) +{ + unsigned int len; + unsigned long va; + + va = hw->address; + len = get_hbp_len(hw->ctrl.len); + + return (va >= TASK_SIZE) && ((va + len - 1) >= TASK_SIZE); +} + +/* + * Extract generic type and length encodings from an arch_hw_breakpoint_ctrl. + * Hopefully this will disappear when ptrace can bypass the conversion + * to generic breakpoint descriptions. + */ +int arch_bp_generic_fields(struct arch_hw_breakpoint_ctrl ctrl, + int *gen_len, int *gen_type) +{ + /* Type */ + switch (ctrl.type) { + case ARM_BREAKPOINT_EXECUTE: + *gen_type = HW_BREAKPOINT_X; + break; + case ARM_BREAKPOINT_LOAD: + *gen_type = HW_BREAKPOINT_R; + break; + case ARM_BREAKPOINT_STORE: + *gen_type = HW_BREAKPOINT_W; + break; + case ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE: + *gen_type = HW_BREAKPOINT_RW; + break; + default: + return -EINVAL; + } + + /* Len */ + switch (ctrl.len) { + case ARM_BREAKPOINT_LEN_1: + *gen_len = HW_BREAKPOINT_LEN_1; + break; + case ARM_BREAKPOINT_LEN_2: + *gen_len = HW_BREAKPOINT_LEN_2; + break; + case ARM_BREAKPOINT_LEN_4: + *gen_len = HW_BREAKPOINT_LEN_4; + break; + case ARM_BREAKPOINT_LEN_8: + *gen_len = HW_BREAKPOINT_LEN_8; + break; + default: + return -EINVAL; + } + + return 0; +} + +/* + * Construct an arch_hw_breakpoint from a perf_event. + */ +static int arch_build_bp_info(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) +{ + /* Type */ + switch (attr->bp_type) { + case HW_BREAKPOINT_X: + hw->ctrl.type = ARM_BREAKPOINT_EXECUTE; + break; + case HW_BREAKPOINT_R: + hw->ctrl.type = ARM_BREAKPOINT_LOAD; + break; + case HW_BREAKPOINT_W: + hw->ctrl.type = ARM_BREAKPOINT_STORE; + break; + case HW_BREAKPOINT_RW: + hw->ctrl.type = ARM_BREAKPOINT_LOAD | ARM_BREAKPOINT_STORE; + break; + default: + return -EINVAL; + } + + /* Len */ + switch (attr->bp_len) { + case HW_BREAKPOINT_LEN_1: + hw->ctrl.len = ARM_BREAKPOINT_LEN_1; + break; + case HW_BREAKPOINT_LEN_2: + hw->ctrl.len = ARM_BREAKPOINT_LEN_2; + break; + case HW_BREAKPOINT_LEN_4: + hw->ctrl.len = ARM_BREAKPOINT_LEN_4; + break; + case HW_BREAKPOINT_LEN_8: + hw->ctrl.len = ARM_BREAKPOINT_LEN_8; + if ((hw->ctrl.type != ARM_BREAKPOINT_EXECUTE) + && max_watchpoint_len >= 8) + break; + fallthrough; + default: + return -EINVAL; + } + + /* + * Breakpoints must be of length 2 (thumb) or 4 (ARM) bytes. + * Watchpoints can be of length 1, 2, 4 or 8 bytes if supported + * by the hardware and must be aligned to the appropriate number of + * bytes. + */ + if (hw->ctrl.type == ARM_BREAKPOINT_EXECUTE && + hw->ctrl.len != ARM_BREAKPOINT_LEN_2 && + hw->ctrl.len != ARM_BREAKPOINT_LEN_4) + return -EINVAL; + + /* Address */ + hw->address = attr->bp_addr; + + /* Privilege */ + hw->ctrl.privilege = ARM_BREAKPOINT_USER; + if (arch_check_bp_in_kernelspace(hw)) + hw->ctrl.privilege |= ARM_BREAKPOINT_PRIV; + + /* Enabled? */ + hw->ctrl.enabled = !attr->disabled; + + /* Mismatch */ + hw->ctrl.mismatch = 0; + + return 0; +} + +/* + * Validate the arch-specific HW Breakpoint register settings. + */ +int hw_breakpoint_arch_parse(struct perf_event *bp, + const struct perf_event_attr *attr, + struct arch_hw_breakpoint *hw) +{ + int ret = 0; + u32 offset, alignment_mask = 0x3; + + /* Ensure that we are in monitor debug mode. */ + if (!monitor_mode_enabled()) + return -ENODEV; + + /* Build the arch_hw_breakpoint. */ + ret = arch_build_bp_info(bp, attr, hw); + if (ret) + goto out; + + /* Check address alignment. */ + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_8) + alignment_mask = 0x7; + offset = hw->address & alignment_mask; + switch (offset) { + case 0: + /* Aligned */ + break; + case 1: + case 2: + /* Allow halfword watchpoints and breakpoints. */ + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_2) + break; + fallthrough; + case 3: + /* Allow single byte watchpoint. */ + if (hw->ctrl.len == ARM_BREAKPOINT_LEN_1) + break; + fallthrough; + default: + ret = -EINVAL; + goto out; + } + + hw->address &= ~alignment_mask; + hw->ctrl.len <<= offset; + + if (uses_default_overflow_handler(bp)) { + /* + * Mismatch breakpoints are required for single-stepping + * breakpoints. + */ + if (!core_has_mismatch_brps()) + return -EINVAL; + + /* We don't allow mismatch breakpoints in kernel space. */ + if (arch_check_bp_in_kernelspace(hw)) + return -EPERM; + + /* + * Per-cpu breakpoints are not supported by our stepping + * mechanism. + */ + if (!bp->hw.target) + return -EINVAL; + + /* + * We only support specific access types if the fsr + * reports them. + */ + if (!debug_exception_updates_fsr() && + (hw->ctrl.type == ARM_BREAKPOINT_LOAD || + hw->ctrl.type == ARM_BREAKPOINT_STORE)) + return -EINVAL; + } + +out: + return ret; +} + +/* + * Enable/disable single-stepping over the breakpoint bp at address addr. + */ +static void enable_single_step(struct perf_event *bp, u32 addr) +{ + struct arch_hw_breakpoint *info = counter_arch_bp(bp); + + arch_uninstall_hw_breakpoint(bp); + info->step_ctrl.mismatch = 1; + info->step_ctrl.len = ARM_BREAKPOINT_LEN_4; + info->step_ctrl.type = ARM_BREAKPOINT_EXECUTE; + info->step_ctrl.privilege = info->ctrl.privilege; + info->step_ctrl.enabled = 1; + info->trigger = addr; + arch_install_hw_breakpoint(bp); +} + +static void disable_single_step(struct perf_event *bp) +{ + arch_uninstall_hw_breakpoint(bp); + counter_arch_bp(bp)->step_ctrl.enabled = 0; + arch_install_hw_breakpoint(bp); +} + +/* + * Arm32 hardware does not always report a watchpoint hit address that matches + * one of the watchpoints set. It can also report an address "near" the + * watchpoint if a single instruction access both watched and unwatched + * addresses. There is no straight-forward way, short of disassembling the + * offending instruction, to map that address back to the watchpoint. This + * function computes the distance of the memory access from the watchpoint as a + * heuristic for the likelyhood that a given access triggered the watchpoint. + * + * See this same function in the arm64 platform code, which has the same + * problem. + * + * The function returns the distance of the address from the bytes watched by + * the watchpoint. In case of an exact match, it returns 0. + */ +static u32 get_distance_from_watchpoint(unsigned long addr, u32 val, + struct arch_hw_breakpoint_ctrl *ctrl) +{ + u32 wp_low, wp_high; + u32 lens, lene; + + lens = __ffs(ctrl->len); + lene = __fls(ctrl->len); + + wp_low = val + lens; + wp_high = val + lene; + if (addr < wp_low) + return wp_low - addr; + else if (addr > wp_high) + return addr - wp_high; + else + return 0; +} + +static int watchpoint_fault_on_uaccess(struct pt_regs *regs, + struct arch_hw_breakpoint *info) +{ + return !user_mode(regs) && info->ctrl.privilege == ARM_BREAKPOINT_USER; +} + +static void watchpoint_handler(unsigned long addr, unsigned int fsr, + struct pt_regs *regs) +{ + int i, access, closest_match = 0; + u32 min_dist = -1, dist; + u32 val, ctrl_reg; + struct perf_event *wp, **slots; + struct arch_hw_breakpoint *info; + struct arch_hw_breakpoint_ctrl ctrl; + + slots = this_cpu_ptr(wp_on_reg); + + /* + * Find all watchpoints that match the reported address. If no exact + * match is found. Attribute the hit to the closest watchpoint. + */ + rcu_read_lock(); + for (i = 0; i < core_num_wrps; ++i) { + wp = slots[i]; + if (wp == NULL) + continue; + + /* + * The DFAR is an unknown value on debug architectures prior + * to 7.1. Since we only allow a single watchpoint on these + * older CPUs, we can set the trigger to the lowest possible + * faulting address. + */ + if (debug_arch < ARM_DEBUG_ARCH_V7_1) { + BUG_ON(i > 0); + info = counter_arch_bp(wp); + info->trigger = wp->attr.bp_addr; + } else { + /* Check that the access type matches. */ + if (debug_exception_updates_fsr()) { + access = (fsr & ARM_FSR_ACCESS_MASK) ? + HW_BREAKPOINT_W : HW_BREAKPOINT_R; + if (!(access & hw_breakpoint_type(wp))) + continue; + } + + val = read_wb_reg(ARM_BASE_WVR + i); + ctrl_reg = read_wb_reg(ARM_BASE_WCR + i); + decode_ctrl_reg(ctrl_reg, &ctrl); + dist = get_distance_from_watchpoint(addr, val, &ctrl); + if (dist < min_dist) { + min_dist = dist; + closest_match = i; + } + /* Is this an exact match? */ + if (dist != 0) + continue; + + /* We have a winner. */ + info = counter_arch_bp(wp); + info->trigger = addr; + } + + pr_debug("watchpoint fired: address = 0x%x\n", info->trigger); + + /* + * If we triggered a user watchpoint from a uaccess routine, + * then handle the stepping ourselves since userspace really + * can't help us with this. + */ + if (watchpoint_fault_on_uaccess(regs, info)) + goto step; + + perf_bp_event(wp, regs); + + /* + * Defer stepping to the overflow handler if one is installed. + * Otherwise, insert a temporary mismatch breakpoint so that + * we can single-step over the watchpoint trigger. + */ + if (!uses_default_overflow_handler(wp)) + continue; +step: + enable_single_step(wp, instruction_pointer(regs)); + } + + if (min_dist > 0 && min_dist != -1) { + /* No exact match found. */ + wp = slots[closest_match]; + info = counter_arch_bp(wp); + info->trigger = addr; + pr_debug("watchpoint fired: address = 0x%x\n", info->trigger); + perf_bp_event(wp, regs); + if (uses_default_overflow_handler(wp)) + enable_single_step(wp, instruction_pointer(regs)); + } + + rcu_read_unlock(); +} + +static void watchpoint_single_step_handler(unsigned long pc) +{ + int i; + struct perf_event *wp, **slots; + struct arch_hw_breakpoint *info; + + slots = this_cpu_ptr(wp_on_reg); + + for (i = 0; i < core_num_wrps; ++i) { + rcu_read_lock(); + + wp = slots[i]; + + if (wp == NULL) + goto unlock; + + info = counter_arch_bp(wp); + if (!info->step_ctrl.enabled) + goto unlock; + + /* + * Restore the original watchpoint if we've completed the + * single-step. + */ + if (info->trigger != pc) + disable_single_step(wp); + +unlock: + rcu_read_unlock(); + } +} + +static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs) +{ + int i; + u32 ctrl_reg, val, addr; + struct perf_event *bp, **slots; + struct arch_hw_breakpoint *info; + struct arch_hw_breakpoint_ctrl ctrl; + + slots = this_cpu_ptr(bp_on_reg); + + /* The exception entry code places the amended lr in the PC. */ + addr = regs->ARM_pc; + + /* Check the currently installed breakpoints first. */ + for (i = 0; i < core_num_brps; ++i) { + rcu_read_lock(); + + bp = slots[i]; + + if (bp == NULL) + goto unlock; + + info = counter_arch_bp(bp); + + /* Check if the breakpoint value matches. */ + val = read_wb_reg(ARM_BASE_BVR + i); + if (val != (addr & ~0x3)) + goto mismatch; + + /* Possible match, check the byte address select to confirm. */ + ctrl_reg = read_wb_reg(ARM_BASE_BCR + i); + decode_ctrl_reg(ctrl_reg, &ctrl); + if ((1 << (addr & 0x3)) & ctrl.len) { + info->trigger = addr; + pr_debug("breakpoint fired: address = 0x%x\n", addr); + perf_bp_event(bp, regs); + if (uses_default_overflow_handler(bp)) + enable_single_step(bp, addr); + goto unlock; + } + +mismatch: + /* If we're stepping a breakpoint, it can now be restored. */ + if (info->step_ctrl.enabled) + disable_single_step(bp); +unlock: + rcu_read_unlock(); + } + + /* Handle any pending watchpoint single-step breakpoints. */ + watchpoint_single_step_handler(addr); +} + +/* + * Called from either the Data Abort Handler [watchpoint] or the + * Prefetch Abort Handler [breakpoint] with interrupts disabled. + */ +static int hw_breakpoint_pending(unsigned long addr, unsigned int fsr, + struct pt_regs *regs) +{ + int ret = 0; + u32 dscr; + + preempt_disable(); + + if (interrupts_enabled(regs)) + local_irq_enable(); + + /* We only handle watchpoints and hardware breakpoints. */ + ARM_DBG_READ(c0, c1, 0, dscr); + + /* Perform perf callbacks. */ + switch (ARM_DSCR_MOE(dscr)) { + case ARM_ENTRY_BREAKPOINT: + breakpoint_handler(addr, regs); + break; + case ARM_ENTRY_ASYNC_WATCHPOINT: + WARN(1, "Asynchronous watchpoint exception taken. Debugging results may be unreliable\n"); + fallthrough; + case ARM_ENTRY_SYNC_WATCHPOINT: + watchpoint_handler(addr, fsr, regs); + break; + default: + ret = 1; /* Unhandled fault. */ + } + + preempt_enable(); + + return ret; +} + +#ifdef CONFIG_ARM_ERRATA_764319 +static int oslsr_fault; + +static int debug_oslsr_trap(struct pt_regs *regs, unsigned int instr) +{ + oslsr_fault = 1; + instruction_pointer(regs) += 4; + return 0; +} + +static struct undef_hook debug_oslsr_hook = { + .instr_mask = 0xffffffff, + .instr_val = 0xee115e91, + .fn = debug_oslsr_trap, +}; +#endif + +/* + * One-time initialisation. + */ +static cpumask_t debug_err_mask; + +static int debug_reg_trap(struct pt_regs *regs, unsigned int instr) +{ + int cpu = smp_processor_id(); + + pr_warn("Debug register access (0x%x) caused undefined instruction on CPU %d\n", + instr, cpu); + + /* Set the error flag for this CPU and skip the faulting instruction. */ + cpumask_set_cpu(cpu, &debug_err_mask); + instruction_pointer(regs) += 4; + return 0; +} + +static struct undef_hook debug_reg_hook = { + .instr_mask = 0x0fe80f10, + .instr_val = 0x0e000e10, + .fn = debug_reg_trap, +}; + +/* Does this core support OS Save and Restore? */ +static bool core_has_os_save_restore(void) +{ + u32 oslsr; + + switch (get_debug_arch()) { + case ARM_DEBUG_ARCH_V7_1: + return true; + case ARM_DEBUG_ARCH_V7_ECP14: +#ifdef CONFIG_ARM_ERRATA_764319 + oslsr_fault = 0; + register_undef_hook(&debug_oslsr_hook); + ARM_DBG_READ(c1, c1, 4, oslsr); + unregister_undef_hook(&debug_oslsr_hook); + if (oslsr_fault) + return false; +#else + ARM_DBG_READ(c1, c1, 4, oslsr); +#endif + if (oslsr & ARM_OSLSR_OSLM0) + return true; + fallthrough; + default: + return false; + } +} + +static void reset_ctrl_regs(unsigned int cpu) +{ + int i, raw_num_brps, err = 0; + u32 val; + + /* + * v7 debug contains save and restore registers so that debug state + * can be maintained across low-power modes without leaving the debug + * logic powered up. It is IMPLEMENTATION DEFINED whether we can access + * the debug registers out of reset, so we must unlock the OS Lock + * Access Register to avoid taking undefined instruction exceptions + * later on. + */ + switch (debug_arch) { + case ARM_DEBUG_ARCH_V6: + case ARM_DEBUG_ARCH_V6_1: + /* ARMv6 cores clear the registers out of reset. */ + goto out_mdbgen; + case ARM_DEBUG_ARCH_V7_ECP14: + /* + * Ensure sticky power-down is clear (i.e. debug logic is + * powered up). + */ + ARM_DBG_READ(c1, c5, 4, val); + if ((val & 0x1) == 0) + err = -EPERM; + + if (!has_ossr) + goto clear_vcr; + break; + case ARM_DEBUG_ARCH_V7_1: + /* + * Ensure the OS double lock is clear. + */ + ARM_DBG_READ(c1, c3, 4, val); + if ((val & 0x1) == 1) + err = -EPERM; + break; + } + + if (err) { + pr_warn_once("CPU %d debug is powered down!\n", cpu); + cpumask_or(&debug_err_mask, &debug_err_mask, cpumask_of(cpu)); + return; + } + + /* + * Unconditionally clear the OS lock by writing a value + * other than CS_LAR_KEY to the access register. + */ + ARM_DBG_WRITE(c1, c0, 4, ~CORESIGHT_UNLOCK); + isb(); + + /* + * Clear any configured vector-catch events before + * enabling monitor mode. + */ +clear_vcr: + ARM_DBG_WRITE(c0, c7, 0, 0); + isb(); + + if (cpumask_intersects(&debug_err_mask, cpumask_of(cpu))) { + pr_warn_once("CPU %d failed to disable vector catch\n", cpu); + return; + } + + /* + * The control/value register pairs are UNKNOWN out of reset so + * clear them to avoid spurious debug events. + */ + raw_num_brps = get_num_brp_resources(); + for (i = 0; i < raw_num_brps; ++i) { + write_wb_reg(ARM_BASE_BCR + i, 0UL); + write_wb_reg(ARM_BASE_BVR + i, 0UL); + } + + for (i = 0; i < core_num_wrps; ++i) { + write_wb_reg(ARM_BASE_WCR + i, 0UL); + write_wb_reg(ARM_BASE_WVR + i, 0UL); + } + + if (cpumask_intersects(&debug_err_mask, cpumask_of(cpu))) { + pr_warn_once("CPU %d failed to clear debug register pairs\n", cpu); + return; + } + + /* + * Have a crack at enabling monitor mode. We don't actually need + * it yet, but reporting an error early is useful if it fails. + */ +out_mdbgen: + if (enable_monitor_mode()) + cpumask_or(&debug_err_mask, &debug_err_mask, cpumask_of(cpu)); +} + +static int dbg_reset_online(unsigned int cpu) +{ + local_irq_disable(); + reset_ctrl_regs(cpu); + local_irq_enable(); + return 0; +} + +#ifdef CONFIG_CPU_PM +static int dbg_cpu_pm_notify(struct notifier_block *self, unsigned long action, + void *v) +{ + if (action == CPU_PM_EXIT) + reset_ctrl_regs(smp_processor_id()); + + return NOTIFY_OK; +} + +static struct notifier_block dbg_cpu_pm_nb = { + .notifier_call = dbg_cpu_pm_notify, +}; + +static void __init pm_init(void) +{ + cpu_pm_register_notifier(&dbg_cpu_pm_nb); +} +#else +static inline void pm_init(void) +{ +} +#endif + +static int __init arch_hw_breakpoint_init(void) +{ + int ret; + + debug_arch = get_debug_arch(); + + if (!debug_arch_supported()) { + pr_info("debug architecture 0x%x unsupported.\n", debug_arch); + return 0; + } + + /* + * Scorpion CPUs (at least those in APQ8060) seem to set DBGPRSR.SPD + * whenever a WFI is issued, even if the core is not powered down, in + * violation of the architecture. When DBGPRSR.SPD is set, accesses to + * breakpoint and watchpoint registers are treated as undefined, so + * this results in boot time and runtime failures when these are + * accessed and we unexpectedly take a trap. + * + * It's not clear if/how this can be worked around, so we blacklist + * Scorpion CPUs to avoid these issues. + */ + if (read_cpuid_part() == ARM_CPU_PART_SCORPION) { + pr_info("Scorpion CPU detected. Hardware breakpoints and watchpoints disabled\n"); + return 0; + } + + has_ossr = core_has_os_save_restore(); + + /* Determine how many BRPs/WRPs are available. */ + core_num_brps = get_num_brps(); + core_num_wrps = get_num_wrps(); + + /* + * We need to tread carefully here because DBGSWENABLE may be + * driven low on this core and there isn't an architected way to + * determine that. + */ + cpus_read_lock(); + register_undef_hook(&debug_reg_hook); + + /* + * Register CPU notifier which resets the breakpoint resources. We + * assume that a halting debugger will leave the world in a nice state + * for us. + */ + ret = cpuhp_setup_state_cpuslocked(CPUHP_AP_ONLINE_DYN, + "arm/hw_breakpoint:online", + dbg_reset_online, NULL); + unregister_undef_hook(&debug_reg_hook); + if (WARN_ON(ret < 0) || !cpumask_empty(&debug_err_mask)) { + core_num_brps = 0; + core_num_wrps = 0; + if (ret > 0) + cpuhp_remove_state_nocalls_cpuslocked(ret); + cpus_read_unlock(); + return 0; + } + + pr_info("found %d " "%s" "breakpoint and %d watchpoint registers.\n", + core_num_brps, core_has_mismatch_brps() ? "(+1 reserved) " : + "", core_num_wrps); + + /* Work out the maximum supported watchpoint length. */ + max_watchpoint_len = get_max_wp_len(); + pr_info("maximum watchpoint size is %u bytes.\n", + max_watchpoint_len); + + /* Register debug fault handler. */ + hook_fault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP, + TRAP_HWBKPT, "watchpoint debug exception"); + hook_ifault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP, + TRAP_HWBKPT, "breakpoint debug exception"); + cpus_read_unlock(); + + /* Register PM notifiers. */ + pm_init(); + return 0; +} +arch_initcall(arch_hw_breakpoint_init); + +void hw_breakpoint_pmu_read(struct perf_event *bp) +{ +} + +/* + * Dummy function to register with die_notifier. + */ +int hw_breakpoint_exceptions_notify(struct notifier_block *unused, + unsigned long val, void *data) +{ + return NOTIFY_DONE; +} diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S new file mode 100644 index 000000000..b699b22a4 --- /dev/null +++ b/arch/arm/kernel/hyp-stub.S @@ -0,0 +1,239 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * Copyright (c) 2012 Linaro Limited. + */ + +#include <linux/init.h> +#include <linux/irqchip/arm-gic-v3.h> +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/virt.h> + +#ifndef ZIMAGE +/* + * For the kernel proper, we need to find out the CPU boot mode long after + * boot, so we need to store it in a writable variable. + * + * This is not in .bss, because we set it sufficiently early that the boot-time + * zeroing of .bss would clobber it. + */ +.data + .align 2 +ENTRY(__boot_cpu_mode) + .long 0 +.text + + /* + * Save the primary CPU boot mode. Requires 2 scratch registers. + */ + .macro store_primary_cpu_mode reg1, reg2 + mrs \reg1, cpsr + and \reg1, \reg1, #MODE_MASK + str_l \reg1, __boot_cpu_mode, \reg2 + .endm + + /* + * Compare the current mode with the one saved on the primary CPU. + * If they don't match, record that fact. The Z bit indicates + * if there's a match or not. + * Requires 2 additional scratch registers. + */ + .macro compare_cpu_mode_with_primary mode, reg1, reg2 + adr_l \reg2, __boot_cpu_mode + ldr \reg1, [\reg2] + cmp \mode, \reg1 @ matches primary CPU boot mode? + orrne \reg1, \reg1, #BOOT_CPU_MODE_MISMATCH + strne \reg1, [\reg2] @ record what happened and give up + .endm + +#else /* ZIMAGE */ + + .macro store_primary_cpu_mode reg1:req, reg2:req + .endm + +/* + * The zImage loader only runs on one CPU, so we don't bother with mult-CPU + * consistency checking: + */ + .macro compare_cpu_mode_with_primary mode, reg1, reg2 + cmp \mode, \mode + .endm + +#endif /* ZIMAGE */ + +/* + * Hypervisor stub installation functions. + * + * These must be called with the MMU and D-cache off. + * They are not ABI compliant and are only intended to be called from the kernel + * entry points in head.S. + */ +@ Call this from the primary CPU +ENTRY(__hyp_stub_install) + store_primary_cpu_mode r4, r5 +ENDPROC(__hyp_stub_install) + + @ fall through... + +@ Secondary CPUs should call here +ENTRY(__hyp_stub_install_secondary) + mrs r4, cpsr + and r4, r4, #MODE_MASK + + /* + * If the secondary has booted with a different mode, give up + * immediately. + */ + compare_cpu_mode_with_primary r4, r5, r6 + retne lr + + /* + * Once we have given up on one CPU, we do not try to install the + * stub hypervisor on the remaining ones: because the saved boot mode + * is modified, it can't compare equal to the CPSR mode field any + * more. + * + * Otherwise... + */ + + cmp r4, #HYP_MODE + retne lr @ give up if the CPU is not in HYP mode + +/* + * Configure HSCTLR to set correct exception endianness/instruction set + * state etc. + * Turn off all traps + * Eventually, CPU-specific code might be needed -- assume not for now + * + * This code relies on the "eret" instruction to synchronize the + * various coprocessor accesses. This is done when we switch to SVC + * (see safe_svcmode_maskall). + */ + @ Now install the hypervisor stub: + W(adr) r7, __hyp_stub_vectors + mcr p15, 4, r7, c12, c0, 0 @ set hypervisor vector base (HVBAR) + + @ Disable all traps, so we don't get any nasty surprise + mov r7, #0 + mcr p15, 4, r7, c1, c1, 0 @ HCR + mcr p15, 4, r7, c1, c1, 2 @ HCPTR + mcr p15, 4, r7, c1, c1, 3 @ HSTR + +THUMB( orr r7, #(1 << 30) ) @ HSCTLR.TE +ARM_BE8(orr r7, r7, #(1 << 25)) @ HSCTLR.EE + mcr p15, 4, r7, c1, c0, 0 @ HSCTLR + + mrc p15, 4, r7, c1, c1, 1 @ HDCR + and r7, #0x1f @ Preserve HPMN + mcr p15, 4, r7, c1, c1, 1 @ HDCR + + @ Make sure NS-SVC is initialised appropriately + mrc p15, 0, r7, c1, c0, 0 @ SCTLR + orr r7, #(1 << 5) @ CP15 barriers enabled + bic r7, #(3 << 7) @ Clear SED/ITD for v8 (RES0 for v7) + bic r7, #(3 << 19) @ WXN and UWXN disabled + mcr p15, 0, r7, c1, c0, 0 @ SCTLR + + mrc p15, 0, r7, c0, c0, 0 @ MIDR + mcr p15, 4, r7, c0, c0, 0 @ VPIDR + + mrc p15, 0, r7, c0, c0, 5 @ MPIDR + mcr p15, 4, r7, c0, c0, 5 @ VMPIDR + +#if !defined(ZIMAGE) && defined(CONFIG_ARM_ARCH_TIMER) + @ make CNTP_* and CNTPCT accessible from PL1 + mrc p15, 0, r7, c0, c1, 1 @ ID_PFR1 + ubfx r7, r7, #16, #4 + teq r7, #0 + beq 1f + mrc p15, 4, r7, c14, c1, 0 @ CNTHCTL + orr r7, r7, #3 @ PL1PCEN | PL1PCTEN + mcr p15, 4, r7, c14, c1, 0 @ CNTHCTL + mov r7, #0 + mcrr p15, 4, r7, r7, c14 @ CNTVOFF + + @ Disable virtual timer in case it was counting + mrc p15, 0, r7, c14, c3, 1 @ CNTV_CTL + bic r7, #1 @ Clear ENABLE + mcr p15, 0, r7, c14, c3, 1 @ CNTV_CTL +1: +#endif + +#ifdef CONFIG_ARM_GIC_V3 + @ Check whether GICv3 system registers are available + mrc p15, 0, r7, c0, c1, 1 @ ID_PFR1 + ubfx r7, r7, #28, #4 + teq r7, #0 + beq 2f + + @ Enable system register accesses + mrc p15, 4, r7, c12, c9, 5 @ ICC_HSRE + orr r7, r7, #(ICC_SRE_EL2_ENABLE | ICC_SRE_EL2_SRE) + mcr p15, 4, r7, c12, c9, 5 @ ICC_HSRE + isb + + @ SRE bit could be forced to 0 by firmware. + @ Check whether it sticks before accessing any other sysreg + mrc p15, 4, r7, c12, c9, 5 @ ICC_HSRE + tst r7, #ICC_SRE_EL2_SRE + beq 2f + mov r7, #0 + mcr p15, 4, r7, c12, c11, 0 @ ICH_HCR +2: +#endif + + bx lr @ The boot CPU mode is left in r4. +ENDPROC(__hyp_stub_install_secondary) + +__hyp_stub_do_trap: +#ifdef ZIMAGE + teq r0, #HVC_SET_VECTORS + bne 1f + /* Only the ZIMAGE stubs can change the HYP vectors */ + mcr p15, 4, r1, c12, c0, 0 @ set HVBAR + b __hyp_stub_exit +#endif + +1: teq r0, #HVC_SOFT_RESTART + bne 2f + bx r1 + +2: ldr r0, =HVC_STUB_ERR + __ERET + +__hyp_stub_exit: + mov r0, #0 + __ERET +ENDPROC(__hyp_stub_do_trap) + +/* + * __hyp_set_vectors is only used when ZIMAGE must bounce between HYP + * and SVC. For the kernel itself, the vectors are set once and for + * all by the stubs. + */ +ENTRY(__hyp_set_vectors) + mov r1, r0 + mov r0, #HVC_SET_VECTORS + __HVC(0) + ret lr +ENDPROC(__hyp_set_vectors) + +ENTRY(__hyp_soft_restart) + mov r1, r0 + mov r0, #HVC_SOFT_RESTART + __HVC(0) + ret lr +ENDPROC(__hyp_soft_restart) + +.align 5 +ENTRY(__hyp_stub_vectors) +__hyp_stub_reset: W(b) . +__hyp_stub_und: W(b) . +__hyp_stub_svc: W(b) . +__hyp_stub_pabort: W(b) . +__hyp_stub_dabort: W(b) . +__hyp_stub_trap: W(b) __hyp_stub_do_trap +__hyp_stub_irq: W(b) . +__hyp_stub_fiq: W(b) . +ENDPROC(__hyp_stub_vectors) + diff --git a/arch/arm/kernel/insn.c b/arch/arm/kernel/insn.c new file mode 100644 index 000000000..db0acbb7d --- /dev/null +++ b/arch/arm/kernel/insn.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/bug.h> +#include <linux/kernel.h> +#include <asm/opcodes.h> + +static unsigned long __arm_gen_branch_thumb2(unsigned long pc, + unsigned long addr, bool link, + bool warn) +{ + unsigned long s, j1, j2, i1, i2, imm10, imm11; + unsigned long first, second; + long offset; + + offset = (long)addr - (long)(pc + 4); + if (offset < -16777216 || offset > 16777214) { + WARN_ON_ONCE(warn); + return 0; + } + + s = (offset >> 24) & 0x1; + i1 = (offset >> 23) & 0x1; + i2 = (offset >> 22) & 0x1; + imm10 = (offset >> 12) & 0x3ff; + imm11 = (offset >> 1) & 0x7ff; + + j1 = (!i1) ^ s; + j2 = (!i2) ^ s; + + first = 0xf000 | (s << 10) | imm10; + second = 0x9000 | (j1 << 13) | (j2 << 11) | imm11; + if (link) + second |= 1 << 14; + + return __opcode_thumb32_compose(first, second); +} + +static unsigned long __arm_gen_branch_arm(unsigned long pc, unsigned long addr, + bool link, bool warn) +{ + unsigned long opcode = 0xea000000; + long offset; + + if (link) + opcode |= 1 << 24; + + offset = (long)addr - (long)(pc + 8); + if (unlikely(offset < -33554432 || offset > 33554428)) { + WARN_ON_ONCE(warn); + return 0; + } + + offset = (offset >> 2) & 0x00ffffff; + + return opcode | offset; +} + +unsigned long +__arm_gen_branch(unsigned long pc, unsigned long addr, bool link, bool warn) +{ + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) + return __arm_gen_branch_thumb2(pc, addr, link, warn); + else + return __arm_gen_branch_arm(pc, addr, link, warn); +} diff --git a/arch/arm/kernel/io.c b/arch/arm/kernel/io.c new file mode 100644 index 000000000..60b621295 --- /dev/null +++ b/arch/arm/kernel/io.c @@ -0,0 +1,85 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/export.h> +#include <linux/types.h> +#include <linux/io.h> +#include <linux/spinlock.h> + +static DEFINE_RAW_SPINLOCK(__io_lock); + +/* + * Generic atomic MMIO modify. + * + * Allows thread-safe access to registers shared by unrelated subsystems. + * The access is protected by a single MMIO-wide lock. + */ +void atomic_io_modify_relaxed(void __iomem *reg, u32 mask, u32 set) +{ + unsigned long flags; + u32 value; + + raw_spin_lock_irqsave(&__io_lock, flags); + value = readl_relaxed(reg) & ~mask; + value |= (set & mask); + writel_relaxed(value, reg); + raw_spin_unlock_irqrestore(&__io_lock, flags); +} +EXPORT_SYMBOL(atomic_io_modify_relaxed); + +void atomic_io_modify(void __iomem *reg, u32 mask, u32 set) +{ + unsigned long flags; + u32 value; + + raw_spin_lock_irqsave(&__io_lock, flags); + value = readl_relaxed(reg) & ~mask; + value |= (set & mask); + writel(value, reg); + raw_spin_unlock_irqrestore(&__io_lock, flags); +} +EXPORT_SYMBOL(atomic_io_modify); + +/* + * Copy data from IO memory space to "real" memory space. + * This needs to be optimized. + */ +void _memcpy_fromio(void *to, const volatile void __iomem *from, size_t count) +{ + unsigned char *t = to; + while (count) { + count--; + *t = readb(from); + t++; + from++; + } +} +EXPORT_SYMBOL(_memcpy_fromio); + +/* + * Copy data from "real" memory space to IO memory space. + * This needs to be optimized. + */ +void _memcpy_toio(volatile void __iomem *to, const void *from, size_t count) +{ + const unsigned char *f = from; + while (count) { + count--; + writeb(*f, to); + f++; + to++; + } +} +EXPORT_SYMBOL(_memcpy_toio); + +/* + * "memset" on IO memory space. + * This needs to be optimized. + */ +void _memset_io(volatile void __iomem *dst, int c, size_t count) +{ + while (count) { + count--; + writeb(c, dst); + dst++; + } +} +EXPORT_SYMBOL(_memset_io); diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c new file mode 100644 index 000000000..fe28fc1f7 --- /dev/null +++ b/arch/arm/kernel/irq.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/irq.c + * + * Copyright (C) 1992 Linus Torvalds + * Modifications for ARM processor Copyright (C) 1995-2000 Russell King. + * + * Support for Dynamic Tick Timer Copyright (C) 2004-2005 Nokia Corporation. + * Dynamic Tick Timer written by Tony Lindgren <tony@atomide.com> and + * Tuukka Tikkanen <tuukka.tikkanen@elektrobit.com>. + * + * This file contains the code used by various IRQ handling routines: + * asking for different IRQ's should be done through these routines + * instead of just grabbing them. Thus setups with different IRQ numbers + * shouldn't result in any weird surprises, and installing new handlers + * should be easier. + * + * IRQ's are in fact implemented a bit like signal handlers for the kernel. + * Naturally it's not a 1:1 relation, but there are similarities. + */ +#include <linux/signal.h> +#include <linux/ioport.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqchip.h> +#include <linux/random.h> +#include <linux/smp.h> +#include <linux/init.h> +#include <linux/seq_file.h> +#include <linux/errno.h> +#include <linux/list.h> +#include <linux/kallsyms.h> +#include <linux/proc_fs.h> +#include <linux/export.h> + +#include <asm/hardware/cache-l2x0.h> +#include <asm/hardware/cache-uniphier.h> +#include <asm/outercache.h> +#include <asm/softirq_stack.h> +#include <asm/exception.h> +#include <asm/mach/arch.h> +#include <asm/mach/irq.h> +#include <asm/mach/time.h> + +#include "reboot.h" + +unsigned long irq_err_count; + +#ifdef CONFIG_IRQSTACKS + +asmlinkage DEFINE_PER_CPU_READ_MOSTLY(u8 *, irq_stack_ptr); + +static void __init init_irq_stacks(void) +{ + u8 *stack; + int cpu; + + for_each_possible_cpu(cpu) { + if (!IS_ENABLED(CONFIG_VMAP_STACK)) + stack = (u8 *)__get_free_pages(GFP_KERNEL, + THREAD_SIZE_ORDER); + else + stack = __vmalloc_node(THREAD_SIZE, THREAD_ALIGN, + THREADINFO_GFP, NUMA_NO_NODE, + __builtin_return_address(0)); + + if (WARN_ON(!stack)) + break; + per_cpu(irq_stack_ptr, cpu) = &stack[THREAD_SIZE]; + } +} + +#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK +static void ____do_softirq(void *arg) +{ + __do_softirq(); +} + +void do_softirq_own_stack(void) +{ + call_with_stack(____do_softirq, NULL, + __this_cpu_read(irq_stack_ptr)); +} +#endif +#endif + +int arch_show_interrupts(struct seq_file *p, int prec) +{ +#ifdef CONFIG_FIQ + show_fiq_list(p, prec); +#endif +#ifdef CONFIG_SMP + show_ipi_list(p, prec); +#endif + seq_printf(p, "%*s: %10lu\n", prec, "Err", irq_err_count); + return 0; +} + +/* + * handle_IRQ handles all hardware IRQ's. Decoded IRQs should + * not come via this function. Instead, they should provide their + * own 'handler'. Used by platform code implementing C-based 1st + * level decoding. + */ +void handle_IRQ(unsigned int irq, struct pt_regs *regs) +{ + struct irq_desc *desc; + + /* + * Some hardware gives randomly wrong interrupts. Rather + * than crashing, do something sensible. + */ + if (unlikely(!irq || irq >= nr_irqs)) + desc = NULL; + else + desc = irq_to_desc(irq); + + if (likely(desc)) + handle_irq_desc(desc); + else + ack_bad_irq(irq); +} + +void __init init_IRQ(void) +{ + int ret; + +#ifdef CONFIG_IRQSTACKS + init_irq_stacks(); +#endif + + if (IS_ENABLED(CONFIG_OF) && !machine_desc->init_irq) + irqchip_init(); + else + machine_desc->init_irq(); + + if (IS_ENABLED(CONFIG_OF) && IS_ENABLED(CONFIG_CACHE_L2X0) && + (machine_desc->l2c_aux_mask || machine_desc->l2c_aux_val)) { + if (!outer_cache.write_sec) + outer_cache.write_sec = machine_desc->l2c_write_sec; + ret = l2x0_of_init(machine_desc->l2c_aux_val, + machine_desc->l2c_aux_mask); + if (ret && ret != -ENODEV) + pr_err("L2C: failed to init: %d\n", ret); + } + + uniphier_cache_init(); +} + +#ifdef CONFIG_SPARSE_IRQ +int __init arch_probe_nr_irqs(void) +{ + nr_irqs = machine_desc->nr_irqs ? machine_desc->nr_irqs : NR_IRQS; + return nr_irqs; +} +#endif diff --git a/arch/arm/kernel/isa.c b/arch/arm/kernel/isa.c new file mode 100644 index 000000000..d8a509c5d --- /dev/null +++ b/arch/arm/kernel/isa.c @@ -0,0 +1,66 @@ +// SPDX-License-Identifier: GPL-2.0-or-later +/* + * linux/arch/arm/kernel/isa.c + * + * Copyright (C) 1999 Phil Blundell + * + * ISA shared memory and I/O port support, and is required to support + * iopl, inb, outb and friends in userspace via glibc emulation. + */ +#include <linux/stddef.h> +#include <linux/types.h> +#include <linux/fs.h> +#include <linux/sysctl.h> +#include <linux/init.h> +#include <linux/io.h> + +static unsigned int isa_membase, isa_portbase, isa_portshift; + +static struct ctl_table ctl_isa_vars[4] = { + { + .procname = "membase", + .data = &isa_membase, + .maxlen = sizeof(isa_membase), + .mode = 0444, + .proc_handler = proc_dointvec, + }, { + .procname = "portbase", + .data = &isa_portbase, + .maxlen = sizeof(isa_portbase), + .mode = 0444, + .proc_handler = proc_dointvec, + }, { + .procname = "portshift", + .data = &isa_portshift, + .maxlen = sizeof(isa_portshift), + .mode = 0444, + .proc_handler = proc_dointvec, + }, {} +}; + +static struct ctl_table_header *isa_sysctl_header; + +static struct ctl_table ctl_isa[2] = { + { + .procname = "isa", + .mode = 0555, + .child = ctl_isa_vars, + }, {} +}; + +static struct ctl_table ctl_bus[2] = { + { + .procname = "bus", + .mode = 0555, + .child = ctl_isa, + }, {} +}; + +void __init +register_isa_ports(unsigned int membase, unsigned int portbase, unsigned int portshift) +{ + isa_membase = membase; + isa_portbase = portbase; + isa_portshift = portshift; + isa_sysctl_header = register_sysctl_table(ctl_bus); +} diff --git a/arch/arm/kernel/iwmmxt.S b/arch/arm/kernel/iwmmxt.S new file mode 100644 index 000000000..d2b4ac06e --- /dev/null +++ b/arch/arm/kernel/iwmmxt.S @@ -0,0 +1,371 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * linux/arch/arm/kernel/iwmmxt.S + * + * XScale iWMMXt (Concan) context switching and handling + * + * Initial code: + * Copyright (c) 2003, Intel Corporation + * + * Full lazy switching support, optimizations and more, by Nicolas Pitre +* Copyright (c) 2003-2004, MontaVista Software, Inc. + */ + +#include <linux/linkage.h> +#include <asm/ptrace.h> +#include <asm/thread_info.h> +#include <asm/asm-offsets.h> +#include <asm/assembler.h> +#include "iwmmxt.h" + +#if defined(CONFIG_CPU_PJ4) || defined(CONFIG_CPU_PJ4B) +#define PJ4(code...) code +#define XSC(code...) +#elif defined(CONFIG_CPU_MOHAWK) || \ + defined(CONFIG_CPU_XSC3) || \ + defined(CONFIG_CPU_XSCALE) +#define PJ4(code...) +#define XSC(code...) code +#else +#error "Unsupported iWMMXt architecture" +#endif + +#define MMX_WR0 (0x00) +#define MMX_WR1 (0x08) +#define MMX_WR2 (0x10) +#define MMX_WR3 (0x18) +#define MMX_WR4 (0x20) +#define MMX_WR5 (0x28) +#define MMX_WR6 (0x30) +#define MMX_WR7 (0x38) +#define MMX_WR8 (0x40) +#define MMX_WR9 (0x48) +#define MMX_WR10 (0x50) +#define MMX_WR11 (0x58) +#define MMX_WR12 (0x60) +#define MMX_WR13 (0x68) +#define MMX_WR14 (0x70) +#define MMX_WR15 (0x78) +#define MMX_WCSSF (0x80) +#define MMX_WCASF (0x84) +#define MMX_WCGR0 (0x88) +#define MMX_WCGR1 (0x8C) +#define MMX_WCGR2 (0x90) +#define MMX_WCGR3 (0x94) + +#define MMX_SIZE (0x98) + + .text + .arm + +/* + * Lazy switching of Concan coprocessor context + * + * r10 = struct thread_info pointer + * r9 = ret_from_exception + * lr = undefined instr exit + * + * called from prefetch exception handler with interrupts enabled + */ + +ENTRY(iwmmxt_task_enable) + inc_preempt_count r10, r3 + + XSC(mrc p15, 0, r2, c15, c1, 0) + PJ4(mrc p15, 0, r2, c1, c0, 2) + @ CP0 and CP1 accessible? + XSC(tst r2, #0x3) + PJ4(tst r2, #0xf) + bne 4f @ if so no business here + @ enable access to CP0 and CP1 + XSC(orr r2, r2, #0x3) + XSC(mcr p15, 0, r2, c15, c1, 0) + PJ4(orr r2, r2, #0xf) + PJ4(mcr p15, 0, r2, c1, c0, 2) + + ldr r3, =concan_owner + add r0, r10, #TI_IWMMXT_STATE @ get task Concan save area + ldr r2, [sp, #60] @ current task pc value + ldr r1, [r3] @ get current Concan owner + str r0, [r3] @ this task now owns Concan regs + sub r2, r2, #4 @ adjust pc back + str r2, [sp, #60] + + mrc p15, 0, r2, c2, c0, 0 + mov r2, r2 @ cpwait + bl concan_save + +#ifdef CONFIG_PREEMPT_COUNT + get_thread_info r10 +#endif +4: dec_preempt_count r10, r3 + ret r9 @ normal exit from exception + +concan_save: + + teq r1, #0 @ test for last ownership + beq concan_load @ no owner, skip save + + tmrc r2, wCon + + @ CUP? wCx + tst r2, #0x1 + beq 1f + +concan_dump: + + wstrw wCSSF, r1, MMX_WCSSF + wstrw wCASF, r1, MMX_WCASF + wstrw wCGR0, r1, MMX_WCGR0 + wstrw wCGR1, r1, MMX_WCGR1 + wstrw wCGR2, r1, MMX_WCGR2 + wstrw wCGR3, r1, MMX_WCGR3 + +1: @ MUP? wRn + tst r2, #0x2 + beq 2f + + wstrd wR0, r1, MMX_WR0 + wstrd wR1, r1, MMX_WR1 + wstrd wR2, r1, MMX_WR2 + wstrd wR3, r1, MMX_WR3 + wstrd wR4, r1, MMX_WR4 + wstrd wR5, r1, MMX_WR5 + wstrd wR6, r1, MMX_WR6 + wstrd wR7, r1, MMX_WR7 + wstrd wR8, r1, MMX_WR8 + wstrd wR9, r1, MMX_WR9 + wstrd wR10, r1, MMX_WR10 + wstrd wR11, r1, MMX_WR11 + wstrd wR12, r1, MMX_WR12 + wstrd wR13, r1, MMX_WR13 + wstrd wR14, r1, MMX_WR14 + wstrd wR15, r1, MMX_WR15 + +2: teq r0, #0 @ anything to load? + reteq lr @ if not, return + +concan_load: + + @ Load wRn + wldrd wR0, r0, MMX_WR0 + wldrd wR1, r0, MMX_WR1 + wldrd wR2, r0, MMX_WR2 + wldrd wR3, r0, MMX_WR3 + wldrd wR4, r0, MMX_WR4 + wldrd wR5, r0, MMX_WR5 + wldrd wR6, r0, MMX_WR6 + wldrd wR7, r0, MMX_WR7 + wldrd wR8, r0, MMX_WR8 + wldrd wR9, r0, MMX_WR9 + wldrd wR10, r0, MMX_WR10 + wldrd wR11, r0, MMX_WR11 + wldrd wR12, r0, MMX_WR12 + wldrd wR13, r0, MMX_WR13 + wldrd wR14, r0, MMX_WR14 + wldrd wR15, r0, MMX_WR15 + + @ Load wCx + wldrw wCSSF, r0, MMX_WCSSF + wldrw wCASF, r0, MMX_WCASF + wldrw wCGR0, r0, MMX_WCGR0 + wldrw wCGR1, r0, MMX_WCGR1 + wldrw wCGR2, r0, MMX_WCGR2 + wldrw wCGR3, r0, MMX_WCGR3 + + @ clear CUP/MUP (only if r1 != 0) + teq r1, #0 + mov r2, #0 + reteq lr + + tmcr wCon, r2 + ret lr + +ENDPROC(iwmmxt_task_enable) + +/* + * Back up Concan regs to save area and disable access to them + * (mainly for gdb or sleep mode usage) + * + * r0 = struct thread_info pointer of target task or NULL for any + */ + +ENTRY(iwmmxt_task_disable) + + stmfd sp!, {r4, lr} + + mrs ip, cpsr + orr r2, ip, #PSR_I_BIT @ disable interrupts + msr cpsr_c, r2 + + ldr r3, =concan_owner + add r2, r0, #TI_IWMMXT_STATE @ get task Concan save area + ldr r1, [r3] @ get current Concan owner + teq r1, #0 @ any current owner? + beq 1f @ no: quit + teq r0, #0 @ any owner? + teqne r1, r2 @ or specified one? + bne 1f @ no: quit + + @ enable access to CP0 and CP1 + XSC(mrc p15, 0, r4, c15, c1, 0) + XSC(orr r4, r4, #0x3) + XSC(mcr p15, 0, r4, c15, c1, 0) + PJ4(mrc p15, 0, r4, c1, c0, 2) + PJ4(orr r4, r4, #0xf) + PJ4(mcr p15, 0, r4, c1, c0, 2) + + mov r0, #0 @ nothing to load + str r0, [r3] @ no more current owner + mrc p15, 0, r2, c2, c0, 0 + mov r2, r2 @ cpwait + bl concan_save + + @ disable access to CP0 and CP1 + XSC(bic r4, r4, #0x3) + XSC(mcr p15, 0, r4, c15, c1, 0) + PJ4(bic r4, r4, #0xf) + PJ4(mcr p15, 0, r4, c1, c0, 2) + + mrc p15, 0, r2, c2, c0, 0 + mov r2, r2 @ cpwait + +1: msr cpsr_c, ip @ restore interrupt mode + ldmfd sp!, {r4, pc} + +ENDPROC(iwmmxt_task_disable) + +/* + * Copy Concan state to given memory address + * + * r0 = struct thread_info pointer of target task + * r1 = memory address where to store Concan state + * + * this is called mainly in the creation of signal stack frames + */ + +ENTRY(iwmmxt_task_copy) + + mrs ip, cpsr + orr r2, ip, #PSR_I_BIT @ disable interrupts + msr cpsr_c, r2 + + ldr r3, =concan_owner + add r2, r0, #TI_IWMMXT_STATE @ get task Concan save area + ldr r3, [r3] @ get current Concan owner + teq r2, r3 @ does this task own it... + beq 1f + + @ current Concan values are in the task save area + msr cpsr_c, ip @ restore interrupt mode + mov r0, r1 + mov r1, r2 + mov r2, #MMX_SIZE + b memcpy + +1: @ this task owns Concan regs -- grab a copy from there + mov r0, #0 @ nothing to load + mov r2, #3 @ save all regs + mov r3, lr @ preserve return address + bl concan_dump + msr cpsr_c, ip @ restore interrupt mode + ret r3 + +ENDPROC(iwmmxt_task_copy) + +/* + * Restore Concan state from given memory address + * + * r0 = struct thread_info pointer of target task + * r1 = memory address where to get Concan state from + * + * this is used to restore Concan state when unwinding a signal stack frame + */ + +ENTRY(iwmmxt_task_restore) + + mrs ip, cpsr + orr r2, ip, #PSR_I_BIT @ disable interrupts + msr cpsr_c, r2 + + ldr r3, =concan_owner + add r2, r0, #TI_IWMMXT_STATE @ get task Concan save area + ldr r3, [r3] @ get current Concan owner + bic r2, r2, #0x7 @ 64-bit alignment + teq r2, r3 @ does this task own it... + beq 1f + + @ this task doesn't own Concan regs -- use its save area + msr cpsr_c, ip @ restore interrupt mode + mov r0, r2 + mov r2, #MMX_SIZE + b memcpy + +1: @ this task owns Concan regs -- load them directly + mov r0, r1 + mov r1, #0 @ don't clear CUP/MUP + mov r3, lr @ preserve return address + bl concan_load + msr cpsr_c, ip @ restore interrupt mode + ret r3 + +ENDPROC(iwmmxt_task_restore) + +/* + * Concan handling on task switch + * + * r0 = next thread_info pointer + * + * Called only from the iwmmxt notifier with task preemption disabled. + */ +ENTRY(iwmmxt_task_switch) + + XSC(mrc p15, 0, r1, c15, c1, 0) + PJ4(mrc p15, 0, r1, c1, c0, 2) + @ CP0 and CP1 accessible? + XSC(tst r1, #0x3) + PJ4(tst r1, #0xf) + bne 1f @ yes: block them for next task + + ldr r2, =concan_owner + add r3, r0, #TI_IWMMXT_STATE @ get next task Concan save area + ldr r2, [r2] @ get current Concan owner + teq r2, r3 @ next task owns it? + retne lr @ no: leave Concan disabled + +1: @ flip Concan access + XSC(eor r1, r1, #0x3) + XSC(mcr p15, 0, r1, c15, c1, 0) + PJ4(eor r1, r1, #0xf) + PJ4(mcr p15, 0, r1, c1, c0, 2) + + mrc p15, 0, r1, c2, c0, 0 + sub pc, lr, r1, lsr #32 @ cpwait and return + +ENDPROC(iwmmxt_task_switch) + +/* + * Remove Concan ownership of given task + * + * r0 = struct thread_info pointer + */ +ENTRY(iwmmxt_task_release) + + mrs r2, cpsr + orr ip, r2, #PSR_I_BIT @ disable interrupts + msr cpsr_c, ip + ldr r3, =concan_owner + add r0, r0, #TI_IWMMXT_STATE @ get task Concan save area + ldr r1, [r3] @ get current Concan owner + eors r0, r0, r1 @ if equal... + streq r0, [r3] @ then clear ownership + msr cpsr_c, r2 @ restore interrupts + ret lr + +ENDPROC(iwmmxt_task_release) + + .data + .align 2 +concan_owner: + .word 0 + diff --git a/arch/arm/kernel/iwmmxt.h b/arch/arm/kernel/iwmmxt.h new file mode 100644 index 000000000..fb627286f --- /dev/null +++ b/arch/arm/kernel/iwmmxt.h @@ -0,0 +1,47 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __IWMMXT_H__ +#define __IWMMXT_H__ + +.irp b, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 +.set .LwR\b, \b +.set .Lr\b, \b +.endr + +.set .LwCSSF, 0x2 +.set .LwCASF, 0x3 +.set .LwCGR0, 0x8 +.set .LwCGR1, 0x9 +.set .LwCGR2, 0xa +.set .LwCGR3, 0xb + +.macro wldrd, reg:req, base:req, offset:req +.inst 0xedd00100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2) +.endm + +.macro wldrw, reg:req, base:req, offset:req +.inst 0xfd900100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2) +.endm + +.macro wstrd, reg:req, base:req, offset:req +.inst 0xedc00100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2) +.endm + +.macro wstrw, reg:req, base:req, offset:req +.inst 0xfd800100 | (.L\reg << 12) | (.L\base << 16) | (\offset >> 2) +.endm + +#ifdef __clang__ + +#define wCon c1 + +.macro tmrc, dest:req, control:req +mrc p1, 0, \dest, \control, c0, 0 +.endm + +.macro tmcr, control:req, src:req +mcr p1, 0, \src, \control, c0, 0 +.endm +#endif + +#endif diff --git a/arch/arm/kernel/jump_label.c b/arch/arm/kernel/jump_label.c new file mode 100644 index 000000000..eb9c24b6e --- /dev/null +++ b/arch/arm/kernel/jump_label.c @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/jump_label.h> +#include <asm/patch.h> +#include <asm/insn.h> + +static void __arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type, + bool is_static) +{ + void *addr = (void *)entry->code; + unsigned int insn; + + if (type == JUMP_LABEL_JMP) + insn = arm_gen_branch(entry->code, entry->target); + else + insn = arm_gen_nop(); + + if (is_static) + __patch_text_early(addr, insn); + else + patch_text(addr, insn); +} + +void arch_jump_label_transform(struct jump_entry *entry, + enum jump_label_type type) +{ + __arch_jump_label_transform(entry, type, false); +} diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c new file mode 100644 index 000000000..22f937e6f --- /dev/null +++ b/arch/arm/kernel/kgdb.c @@ -0,0 +1,291 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * arch/arm/kernel/kgdb.c + * + * ARM KGDB support + * + * Copyright (c) 2002-2004 MontaVista Software, Inc + * Copyright (c) 2008 Wind River Systems, Inc. + * + * Authors: George Davis <davis_g@mvista.com> + * Deepak Saxena <dsaxena@plexity.net> + */ +#include <linux/irq.h> +#include <linux/kdebug.h> +#include <linux/kgdb.h> +#include <linux/uaccess.h> + +#include <asm/patch.h> +#include <asm/traps.h> + +struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = +{ + { "r0", 4, offsetof(struct pt_regs, ARM_r0)}, + { "r1", 4, offsetof(struct pt_regs, ARM_r1)}, + { "r2", 4, offsetof(struct pt_regs, ARM_r2)}, + { "r3", 4, offsetof(struct pt_regs, ARM_r3)}, + { "r4", 4, offsetof(struct pt_regs, ARM_r4)}, + { "r5", 4, offsetof(struct pt_regs, ARM_r5)}, + { "r6", 4, offsetof(struct pt_regs, ARM_r6)}, + { "r7", 4, offsetof(struct pt_regs, ARM_r7)}, + { "r8", 4, offsetof(struct pt_regs, ARM_r8)}, + { "r9", 4, offsetof(struct pt_regs, ARM_r9)}, + { "r10", 4, offsetof(struct pt_regs, ARM_r10)}, + { "fp", 4, offsetof(struct pt_regs, ARM_fp)}, + { "ip", 4, offsetof(struct pt_regs, ARM_ip)}, + { "sp", 4, offsetof(struct pt_regs, ARM_sp)}, + { "lr", 4, offsetof(struct pt_regs, ARM_lr)}, + { "pc", 4, offsetof(struct pt_regs, ARM_pc)}, + { "f0", 12, -1 }, + { "f1", 12, -1 }, + { "f2", 12, -1 }, + { "f3", 12, -1 }, + { "f4", 12, -1 }, + { "f5", 12, -1 }, + { "f6", 12, -1 }, + { "f7", 12, -1 }, + { "fps", 4, -1 }, + { "cpsr", 4, offsetof(struct pt_regs, ARM_cpsr)}, +}; + +char *dbg_get_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return NULL; + + if (dbg_reg_def[regno].offset != -1) + memcpy(mem, (void *)regs + dbg_reg_def[regno].offset, + dbg_reg_def[regno].size); + else + memset(mem, 0, dbg_reg_def[regno].size); + return dbg_reg_def[regno].name; +} + +int dbg_set_reg(int regno, void *mem, struct pt_regs *regs) +{ + if (regno >= DBG_MAX_REG_NUM || regno < 0) + return -EINVAL; + + if (dbg_reg_def[regno].offset != -1) + memcpy((void *)regs + dbg_reg_def[regno].offset, mem, + dbg_reg_def[regno].size); + return 0; +} + +void +sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task) +{ + struct thread_info *ti; + int regno; + + /* Just making sure... */ + if (task == NULL) + return; + + /* Initialize to zero */ + for (regno = 0; regno < GDB_MAX_REGS; regno++) + gdb_regs[regno] = 0; + + /* Otherwise, we have only some registers from switch_to() */ + ti = task_thread_info(task); + gdb_regs[_R4] = ti->cpu_context.r4; + gdb_regs[_R5] = ti->cpu_context.r5; + gdb_regs[_R6] = ti->cpu_context.r6; + gdb_regs[_R7] = ti->cpu_context.r7; + gdb_regs[_R8] = ti->cpu_context.r8; + gdb_regs[_R9] = ti->cpu_context.r9; + gdb_regs[_R10] = ti->cpu_context.sl; + gdb_regs[_FP] = ti->cpu_context.fp; + gdb_regs[_SPT] = ti->cpu_context.sp; + gdb_regs[_PC] = ti->cpu_context.pc; +} + +void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc) +{ + regs->ARM_pc = pc; +} + +static int compiled_break; + +int kgdb_arch_handle_exception(int exception_vector, int signo, + int err_code, char *remcom_in_buffer, + char *remcom_out_buffer, + struct pt_regs *linux_regs) +{ + unsigned long addr; + char *ptr; + + switch (remcom_in_buffer[0]) { + case 'D': + case 'k': + case 'c': + /* + * Try to read optional parameter, pc unchanged if no parm. + * If this was a compiled breakpoint, we need to move + * to the next instruction or we will just breakpoint + * over and over again. + */ + ptr = &remcom_in_buffer[1]; + if (kgdb_hex2long(&ptr, &addr)) + linux_regs->ARM_pc = addr; + else if (compiled_break == 1) + linux_regs->ARM_pc += 4; + + compiled_break = 0; + + return 0; + } + + return -1; +} + +static int kgdb_brk_fn(struct pt_regs *regs, unsigned int instr) +{ + kgdb_handle_exception(1, SIGTRAP, 0, regs); + + return 0; +} + +static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int instr) +{ + compiled_break = 1; + kgdb_handle_exception(1, SIGTRAP, 0, regs); + + return 0; +} + +static struct undef_hook kgdb_brkpt_arm_hook = { + .instr_mask = 0xffffffff, + .instr_val = KGDB_BREAKINST, + .cpsr_mask = PSR_T_BIT | MODE_MASK, + .cpsr_val = SVC_MODE, + .fn = kgdb_brk_fn +}; + +static struct undef_hook kgdb_brkpt_thumb_hook = { + .instr_mask = 0xffff, + .instr_val = KGDB_BREAKINST & 0xffff, + .cpsr_mask = PSR_T_BIT | MODE_MASK, + .cpsr_val = PSR_T_BIT | SVC_MODE, + .fn = kgdb_brk_fn +}; + +static struct undef_hook kgdb_compiled_brkpt_arm_hook = { + .instr_mask = 0xffffffff, + .instr_val = KGDB_COMPILED_BREAK, + .cpsr_mask = PSR_T_BIT | MODE_MASK, + .cpsr_val = SVC_MODE, + .fn = kgdb_compiled_brk_fn +}; + +static struct undef_hook kgdb_compiled_brkpt_thumb_hook = { + .instr_mask = 0xffff, + .instr_val = KGDB_COMPILED_BREAK & 0xffff, + .cpsr_mask = PSR_T_BIT | MODE_MASK, + .cpsr_val = PSR_T_BIT | SVC_MODE, + .fn = kgdb_compiled_brk_fn +}; + +static int __kgdb_notify(struct die_args *args, unsigned long cmd) +{ + struct pt_regs *regs = args->regs; + + if (kgdb_handle_exception(1, args->signr, cmd, regs)) + return NOTIFY_DONE; + return NOTIFY_STOP; +} +static int +kgdb_notify(struct notifier_block *self, unsigned long cmd, void *ptr) +{ + unsigned long flags; + int ret; + + local_irq_save(flags); + ret = __kgdb_notify(ptr, cmd); + local_irq_restore(flags); + + return ret; +} + +static struct notifier_block kgdb_notifier = { + .notifier_call = kgdb_notify, + .priority = -INT_MAX, +}; + + +/** + * kgdb_arch_init - Perform any architecture specific initalization. + * + * This function will handle the initalization of any architecture + * specific callbacks. + */ +int kgdb_arch_init(void) +{ + int ret = register_die_notifier(&kgdb_notifier); + + if (ret != 0) + return ret; + + register_undef_hook(&kgdb_brkpt_arm_hook); + register_undef_hook(&kgdb_brkpt_thumb_hook); + register_undef_hook(&kgdb_compiled_brkpt_arm_hook); + register_undef_hook(&kgdb_compiled_brkpt_thumb_hook); + + return 0; +} + +/** + * kgdb_arch_exit - Perform any architecture specific uninitalization. + * + * This function will handle the uninitalization of any architecture + * specific callbacks, for dynamic registration and unregistration. + */ +void kgdb_arch_exit(void) +{ + unregister_undef_hook(&kgdb_brkpt_arm_hook); + unregister_undef_hook(&kgdb_brkpt_thumb_hook); + unregister_undef_hook(&kgdb_compiled_brkpt_arm_hook); + unregister_undef_hook(&kgdb_compiled_brkpt_thumb_hook); + unregister_die_notifier(&kgdb_notifier); +} + +int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) +{ + int err; + + /* patch_text() only supports int-sized breakpoints */ + BUILD_BUG_ON(sizeof(int) != BREAK_INSTR_SIZE); + + err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr, + BREAK_INSTR_SIZE); + if (err) + return err; + + /* Machine is already stopped, so we can use __patch_text() directly */ + __patch_text((void *)bpt->bpt_addr, + *(unsigned int *)arch_kgdb_ops.gdb_bpt_instr); + + return err; +} + +int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) +{ + /* Machine is already stopped, so we can use __patch_text() directly */ + __patch_text((void *)bpt->bpt_addr, *(unsigned int *)bpt->saved_instr); + + return 0; +} + +/* + * Register our undef instruction hooks with ARM undef core. + * We register a hook specifically looking for the KGB break inst + * and we handle the normal undef case within the do_undefinstr + * handler. + */ +const struct kgdb_arch arch_kgdb_ops = { +#ifndef __ARMEB__ + .gdb_bpt_instr = {0xfe, 0xde, 0xff, 0xe7} +#else /* ! __ARMEB__ */ + .gdb_bpt_instr = {0xe7, 0xff, 0xde, 0xfe} +#endif +}; diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c new file mode 100644 index 000000000..6d1938d1b --- /dev/null +++ b/arch/arm/kernel/machine_kexec.c @@ -0,0 +1,205 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * machine_kexec.c - handle transition of Linux booting another kernel + */ + +#include <linux/mm.h> +#include <linux/kexec.h> +#include <linux/delay.h> +#include <linux/reboot.h> +#include <linux/io.h> +#include <linux/irq.h> +#include <linux/memblock.h> +#include <linux/of_fdt.h> +#include <asm/mmu_context.h> +#include <asm/cacheflush.h> +#include <asm/kexec-internal.h> +#include <asm/fncpy.h> +#include <asm/mach-types.h> +#include <asm/smp_plat.h> +#include <asm/system_misc.h> +#include <asm/set_memory.h> + +extern void relocate_new_kernel(void); +extern const unsigned int relocate_new_kernel_size; + +static atomic_t waiting_for_crash_ipi; + +/* + * Provide a dummy crash_notes definition while crash dump arrives to arm. + * This prevents breakage of crash_notes attribute in kernel/ksysfs.c. + */ + +int machine_kexec_prepare(struct kimage *image) +{ + struct kexec_segment *current_segment; + __be32 header; + int i, err; + + image->arch.kernel_r2 = image->start - KEXEC_ARM_ZIMAGE_OFFSET + + KEXEC_ARM_ATAGS_OFFSET; + + /* + * Validate that if the current HW supports SMP, then the SW supports + * and implements CPU hotplug for the current HW. If not, we won't be + * able to kexec reliably, so fail the prepare operation. + */ + if (num_possible_cpus() > 1 && platform_can_secondary_boot() && + !platform_can_cpu_hotplug()) + return -EINVAL; + + /* + * No segment at default ATAGs address. try to locate + * a dtb using magic. + */ + for (i = 0; i < image->nr_segments; i++) { + current_segment = &image->segment[i]; + + if (!memblock_is_region_memory(idmap_to_phys(current_segment->mem), + current_segment->memsz)) + return -EINVAL; + + err = get_user(header, (__be32*)current_segment->buf); + if (err) + return err; + + if (header == cpu_to_be32(OF_DT_HEADER)) + image->arch.kernel_r2 = current_segment->mem; + } + return 0; +} + +void machine_kexec_cleanup(struct kimage *image) +{ +} + +void machine_crash_nonpanic_core(void *unused) +{ + struct pt_regs regs; + + crash_setup_regs(®s, get_irq_regs()); + printk(KERN_DEBUG "CPU %u will stop doing anything useful since another CPU has crashed\n", + smp_processor_id()); + crash_save_cpu(®s, smp_processor_id()); + flush_cache_all(); + + set_cpu_online(smp_processor_id(), false); + atomic_dec(&waiting_for_crash_ipi); + + while (1) { + cpu_relax(); + wfe(); + } +} + +static DEFINE_PER_CPU(call_single_data_t, cpu_stop_csd) = + CSD_INIT(machine_crash_nonpanic_core, NULL); + +void crash_smp_send_stop(void) +{ + static int cpus_stopped; + unsigned long msecs; + call_single_data_t *csd; + int cpu, this_cpu = raw_smp_processor_id(); + + if (cpus_stopped) + return; + + atomic_set(&waiting_for_crash_ipi, num_online_cpus() - 1); + for_each_online_cpu(cpu) { + if (cpu == this_cpu) + continue; + + csd = &per_cpu(cpu_stop_csd, cpu); + smp_call_function_single_async(cpu, csd); + } + + msecs = 1000; /* Wait at most a second for the other cpus to stop */ + while ((atomic_read(&waiting_for_crash_ipi) > 0) && msecs) { + mdelay(1); + msecs--; + } + if (atomic_read(&waiting_for_crash_ipi) > 0) + pr_warn("Non-crashing CPUs did not react to IPI\n"); + + cpus_stopped = 1; +} + +static void machine_kexec_mask_interrupts(void) +{ + unsigned int i; + struct irq_desc *desc; + + for_each_irq_desc(i, desc) { + struct irq_chip *chip; + + chip = irq_desc_get_chip(desc); + if (!chip) + continue; + + if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data)) + chip->irq_eoi(&desc->irq_data); + + if (chip->irq_mask) + chip->irq_mask(&desc->irq_data); + + if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data)) + chip->irq_disable(&desc->irq_data); + } +} + +void machine_crash_shutdown(struct pt_regs *regs) +{ + local_irq_disable(); + crash_smp_send_stop(); + + crash_save_cpu(regs, smp_processor_id()); + machine_kexec_mask_interrupts(); + + pr_info("Loading crashdump kernel...\n"); +} + +void machine_kexec(struct kimage *image) +{ + unsigned long page_list, reboot_entry_phys; + struct kexec_relocate_data *data; + void (*reboot_entry)(void); + void *reboot_code_buffer; + + /* + * This can only happen if machine_shutdown() failed to disable some + * CPU, and that can only happen if the checks in + * machine_kexec_prepare() were not correct. If this fails, we can't + * reliably kexec anyway, so BUG_ON is appropriate. + */ + BUG_ON(num_online_cpus() > 1); + + page_list = image->head & PAGE_MASK; + + reboot_code_buffer = page_address(image->control_code_page); + + /* copy our kernel relocation code to the control code page */ + reboot_entry = fncpy(reboot_code_buffer, + &relocate_new_kernel, + relocate_new_kernel_size); + + data = reboot_code_buffer + relocate_new_kernel_size; + data->kexec_start_address = image->start; + data->kexec_indirection_page = page_list; + data->kexec_mach_type = machine_arch_type; + data->kexec_r2 = image->arch.kernel_r2; + + /* get the identity mapping physical address for the reboot code */ + reboot_entry_phys = virt_to_idmap(reboot_entry); + + pr_info("Bye!\n"); + + soft_restart(reboot_entry_phys); +} + +void arch_crash_save_vmcoreinfo(void) +{ +#ifdef CONFIG_ARM_LPAE + VMCOREINFO_CONFIG(ARM_LPAE); +#endif +} diff --git a/arch/arm/kernel/module-plts.c b/arch/arm/kernel/module-plts.c new file mode 100644 index 000000000..8d809724c --- /dev/null +++ b/arch/arm/kernel/module-plts.c @@ -0,0 +1,286 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2014-2017 Linaro Ltd. <ard.biesheuvel@linaro.org> + */ + +#include <linux/elf.h> +#include <linux/ftrace.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/sort.h> +#include <linux/moduleloader.h> + +#include <asm/cache.h> +#include <asm/opcodes.h> + +#ifdef CONFIG_THUMB2_KERNEL +#define PLT_ENT_LDR __opcode_to_mem_thumb32(0xf8dff000 | \ + (PLT_ENT_STRIDE - 4)) +#else +#define PLT_ENT_LDR __opcode_to_mem_arm(0xe59ff000 | \ + (PLT_ENT_STRIDE - 8)) +#endif + +static const u32 fixed_plts[] = { +#ifdef CONFIG_DYNAMIC_FTRACE + FTRACE_ADDR, + MCOUNT_ADDR, +#endif +}; + +static bool in_init(const struct module *mod, unsigned long loc) +{ + return loc - (u32)mod->init_layout.base < mod->init_layout.size; +} + +static void prealloc_fixed(struct mod_plt_sec *pltsec, struct plt_entries *plt) +{ + int i; + + if (!ARRAY_SIZE(fixed_plts) || pltsec->plt_count) + return; + pltsec->plt_count = ARRAY_SIZE(fixed_plts); + + for (i = 0; i < ARRAY_SIZE(plt->ldr); ++i) + plt->ldr[i] = PLT_ENT_LDR; + + BUILD_BUG_ON(sizeof(fixed_plts) > sizeof(plt->lit)); + memcpy(plt->lit, fixed_plts, sizeof(fixed_plts)); +} + +u32 get_module_plt(struct module *mod, unsigned long loc, Elf32_Addr val) +{ + struct mod_plt_sec *pltsec = !in_init(mod, loc) ? &mod->arch.core : + &mod->arch.init; + struct plt_entries *plt; + int idx; + + /* cache the address, ELF header is available only during module load */ + if (!pltsec->plt_ent) + pltsec->plt_ent = (struct plt_entries *)pltsec->plt->sh_addr; + plt = pltsec->plt_ent; + + prealloc_fixed(pltsec, plt); + + for (idx = 0; idx < ARRAY_SIZE(fixed_plts); ++idx) + if (plt->lit[idx] == val) + return (u32)&plt->ldr[idx]; + + idx = 0; + /* + * Look for an existing entry pointing to 'val'. Given that the + * relocations are sorted, this will be the last entry we allocated. + * (if one exists). + */ + if (pltsec->plt_count > 0) { + plt += (pltsec->plt_count - 1) / PLT_ENT_COUNT; + idx = (pltsec->plt_count - 1) % PLT_ENT_COUNT; + + if (plt->lit[idx] == val) + return (u32)&plt->ldr[idx]; + + idx = (idx + 1) % PLT_ENT_COUNT; + if (!idx) + plt++; + } + + pltsec->plt_count++; + BUG_ON(pltsec->plt_count * PLT_ENT_SIZE > pltsec->plt->sh_size); + + if (!idx) + /* Populate a new set of entries */ + *plt = (struct plt_entries){ + { [0 ... PLT_ENT_COUNT - 1] = PLT_ENT_LDR, }, + { val, } + }; + else + plt->lit[idx] = val; + + return (u32)&plt->ldr[idx]; +} + +#define cmp_3way(a,b) ((a) < (b) ? -1 : (a) > (b)) + +static int cmp_rel(const void *a, const void *b) +{ + const Elf32_Rel *x = a, *y = b; + int i; + + /* sort by type and symbol index */ + i = cmp_3way(ELF32_R_TYPE(x->r_info), ELF32_R_TYPE(y->r_info)); + if (i == 0) + i = cmp_3way(ELF32_R_SYM(x->r_info), ELF32_R_SYM(y->r_info)); + return i; +} + +static bool is_zero_addend_relocation(Elf32_Addr base, const Elf32_Rel *rel) +{ + u32 *tval = (u32 *)(base + rel->r_offset); + + /* + * Do a bitwise compare on the raw addend rather than fully decoding + * the offset and doing an arithmetic comparison. + * Note that a zero-addend jump/call relocation is encoded taking the + * PC bias into account, i.e., -8 for ARM and -4 for Thumb2. + */ + switch (ELF32_R_TYPE(rel->r_info)) { + u16 upper, lower; + + case R_ARM_THM_CALL: + case R_ARM_THM_JUMP24: + upper = __mem_to_opcode_thumb16(((u16 *)tval)[0]); + lower = __mem_to_opcode_thumb16(((u16 *)tval)[1]); + + return (upper & 0x7ff) == 0x7ff && (lower & 0x2fff) == 0x2ffe; + + case R_ARM_CALL: + case R_ARM_PC24: + case R_ARM_JUMP24: + return (__mem_to_opcode_arm(*tval) & 0xffffff) == 0xfffffe; + } + BUG(); +} + +static bool duplicate_rel(Elf32_Addr base, const Elf32_Rel *rel, int num) +{ + const Elf32_Rel *prev; + + /* + * Entries are sorted by type and symbol index. That means that, + * if a duplicate entry exists, it must be in the preceding + * slot. + */ + if (!num) + return false; + + prev = rel + num - 1; + return cmp_rel(rel + num, prev) == 0 && + is_zero_addend_relocation(base, prev); +} + +/* Count how many PLT entries we may need */ +static unsigned int count_plts(const Elf32_Sym *syms, Elf32_Addr base, + const Elf32_Rel *rel, int num, Elf32_Word dstidx) +{ + unsigned int ret = 0; + const Elf32_Sym *s; + int i; + + for (i = 0; i < num; i++) { + switch (ELF32_R_TYPE(rel[i].r_info)) { + case R_ARM_CALL: + case R_ARM_PC24: + case R_ARM_JUMP24: + case R_ARM_THM_CALL: + case R_ARM_THM_JUMP24: + /* + * We only have to consider branch targets that resolve + * to symbols that are defined in a different section. + * This is not simply a heuristic, it is a fundamental + * limitation, since there is no guaranteed way to emit + * PLT entries sufficiently close to the branch if the + * section size exceeds the range of a branch + * instruction. So ignore relocations against defined + * symbols if they live in the same section as the + * relocation target. + */ + s = syms + ELF32_R_SYM(rel[i].r_info); + if (s->st_shndx == dstidx) + break; + + /* + * Jump relocations with non-zero addends against + * undefined symbols are supported by the ELF spec, but + * do not occur in practice (e.g., 'jump n bytes past + * the entry point of undefined function symbol f'). + * So we need to support them, but there is no need to + * take them into consideration when trying to optimize + * this code. So let's only check for duplicates when + * the addend is zero. (Note that calls into the core + * module via init PLT entries could involve section + * relative symbol references with non-zero addends, for + * which we may end up emitting duplicates, but the init + * PLT is released along with the rest of the .init + * region as soon as module loading completes.) + */ + if (!is_zero_addend_relocation(base, rel + i) || + !duplicate_rel(base, rel, i)) + ret++; + } + } + return ret; +} + +int module_frob_arch_sections(Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, + char *secstrings, struct module *mod) +{ + unsigned long core_plts = ARRAY_SIZE(fixed_plts); + unsigned long init_plts = ARRAY_SIZE(fixed_plts); + Elf32_Shdr *s, *sechdrs_end = sechdrs + ehdr->e_shnum; + Elf32_Sym *syms = NULL; + + /* + * To store the PLTs, we expand the .text section for core module code + * and for initialization code. + */ + for (s = sechdrs; s < sechdrs_end; ++s) { + if (strcmp(".plt", secstrings + s->sh_name) == 0) + mod->arch.core.plt = s; + else if (strcmp(".init.plt", secstrings + s->sh_name) == 0) + mod->arch.init.plt = s; + else if (s->sh_type == SHT_SYMTAB) + syms = (Elf32_Sym *)s->sh_addr; + } + + if (!mod->arch.core.plt || !mod->arch.init.plt) { + pr_err("%s: module PLT section(s) missing\n", mod->name); + return -ENOEXEC; + } + if (!syms) { + pr_err("%s: module symtab section missing\n", mod->name); + return -ENOEXEC; + } + + for (s = sechdrs + 1; s < sechdrs_end; ++s) { + Elf32_Rel *rels = (void *)ehdr + s->sh_offset; + int numrels = s->sh_size / sizeof(Elf32_Rel); + Elf32_Shdr *dstsec = sechdrs + s->sh_info; + + if (s->sh_type != SHT_REL) + continue; + + /* ignore relocations that operate on non-exec sections */ + if (!(dstsec->sh_flags & SHF_EXECINSTR)) + continue; + + /* sort by type and symbol index */ + sort(rels, numrels, sizeof(Elf32_Rel), cmp_rel, NULL); + + if (!module_init_layout_section(secstrings + dstsec->sh_name)) + core_plts += count_plts(syms, dstsec->sh_addr, rels, + numrels, s->sh_info); + else + init_plts += count_plts(syms, dstsec->sh_addr, rels, + numrels, s->sh_info); + } + + mod->arch.core.plt->sh_type = SHT_NOBITS; + mod->arch.core.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC; + mod->arch.core.plt->sh_addralign = L1_CACHE_BYTES; + mod->arch.core.plt->sh_size = round_up(core_plts * PLT_ENT_SIZE, + sizeof(struct plt_entries)); + mod->arch.core.plt_count = 0; + mod->arch.core.plt_ent = NULL; + + mod->arch.init.plt->sh_type = SHT_NOBITS; + mod->arch.init.plt->sh_flags = SHF_EXECINSTR | SHF_ALLOC; + mod->arch.init.plt->sh_addralign = L1_CACHE_BYTES; + mod->arch.init.plt->sh_size = round_up(init_plts * PLT_ENT_SIZE, + sizeof(struct plt_entries)); + mod->arch.init.plt_count = 0; + mod->arch.init.plt_ent = NULL; + + pr_debug("%s: plt=%x, init.plt=%x\n", __func__, + mod->arch.core.plt->sh_size, mod->arch.init.plt->sh_size); + return 0; +} diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c new file mode 100644 index 000000000..d59c36dc0 --- /dev/null +++ b/arch/arm/kernel/module.c @@ -0,0 +1,539 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/module.c + * + * Copyright (C) 2002 Russell King. + * Modified for nommu by Hyok S. Choi + * + * Module allocation method suggested by Andi Kleen. + */ +#include <linux/module.h> +#include <linux/moduleloader.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/elf.h> +#include <linux/vmalloc.h> +#include <linux/fs.h> +#include <linux/string.h> +#include <linux/gfp.h> + +#include <asm/sections.h> +#include <asm/smp_plat.h> +#include <asm/unwind.h> +#include <asm/opcodes.h> + +#ifdef CONFIG_XIP_KERNEL +/* + * The XIP kernel text is mapped in the module area for modules and + * some other stuff to work without any indirect relocations. + * MODULES_VADDR is redefined here and not in asm/memory.h to avoid + * recompiling the whole kernel when CONFIG_XIP_KERNEL is turned on/off. + */ +#undef MODULES_VADDR +#define MODULES_VADDR (((unsigned long)_exiprom + ~PMD_MASK) & PMD_MASK) +#endif + +#ifdef CONFIG_MMU +void *module_alloc(unsigned long size) +{ + gfp_t gfp_mask = GFP_KERNEL; + void *p; + + /* Silence the initial allocation */ + if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS)) + gfp_mask |= __GFP_NOWARN; + + p = __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, + gfp_mask, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + __builtin_return_address(0)); + if (!IS_ENABLED(CONFIG_ARM_MODULE_PLTS) || p) + return p; + return __vmalloc_node_range(size, 1, VMALLOC_START, VMALLOC_END, + GFP_KERNEL, PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE, + __builtin_return_address(0)); +} +#endif + +bool module_init_section(const char *name) +{ + return strstarts(name, ".init") || + strstarts(name, ".ARM.extab.init") || + strstarts(name, ".ARM.exidx.init"); +} + +bool module_exit_section(const char *name) +{ + return strstarts(name, ".exit") || + strstarts(name, ".ARM.extab.exit") || + strstarts(name, ".ARM.exidx.exit"); +} + +#ifdef CONFIG_ARM_HAS_GROUP_RELOCS +/* + * This implements the partitioning algorithm for group relocations as + * documented in the ARM AArch32 ELF psABI (IHI 0044). + * + * A single PC-relative symbol reference is divided in up to 3 add or subtract + * operations, where the final one could be incorporated into a load/store + * instruction with immediate offset. E.g., + * + * ADD Rd, PC, #... or ADD Rd, PC, #... + * ADD Rd, Rd, #... ADD Rd, Rd, #... + * LDR Rd, [Rd, #...] ADD Rd, Rd, #... + * + * The latter has a guaranteed range of only 16 MiB (3x8 == 24 bits), so it is + * of limited use in the kernel. However, the ADD/ADD/LDR combo has a range of + * -/+ 256 MiB, (2x8 + 12 == 28 bits), which means it has sufficient range for + * any in-kernel symbol reference (unless module PLTs are being used). + * + * The main advantage of this approach over the typical pattern using a literal + * load is that literal loads may miss in the D-cache, and generally lead to + * lower cache efficiency for variables that are referenced often from many + * different places in the code. + */ +static u32 get_group_rem(u32 group, u32 *offset) +{ + u32 val = *offset; + u32 shift; + do { + shift = val ? (31 - __fls(val)) & ~1 : 32; + *offset = val; + if (!val) + break; + val &= 0xffffff >> shift; + } while (group--); + return shift; +} +#endif + +int +apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex, + unsigned int relindex, struct module *module) +{ + Elf32_Shdr *symsec = sechdrs + symindex; + Elf32_Shdr *relsec = sechdrs + relindex; + Elf32_Shdr *dstsec = sechdrs + relsec->sh_info; + Elf32_Rel *rel = (void *)relsec->sh_addr; + unsigned int i; + + for (i = 0; i < relsec->sh_size / sizeof(Elf32_Rel); i++, rel++) { + unsigned long loc; + Elf32_Sym *sym; + const char *symname; +#ifdef CONFIG_ARM_HAS_GROUP_RELOCS + u32 shift, group = 1; +#endif + s32 offset; + u32 tmp; +#ifdef CONFIG_THUMB2_KERNEL + u32 upper, lower, sign, j1, j2; +#endif + + offset = ELF32_R_SYM(rel->r_info); + if (offset < 0 || offset > (symsec->sh_size / sizeof(Elf32_Sym))) { + pr_err("%s: section %u reloc %u: bad relocation sym offset\n", + module->name, relindex, i); + return -ENOEXEC; + } + + sym = ((Elf32_Sym *)symsec->sh_addr) + offset; + symname = strtab + sym->st_name; + + if (rel->r_offset < 0 || rel->r_offset > dstsec->sh_size - sizeof(u32)) { + pr_err("%s: section %u reloc %u sym '%s': out of bounds relocation, offset %d size %u\n", + module->name, relindex, i, symname, + rel->r_offset, dstsec->sh_size); + return -ENOEXEC; + } + + loc = dstsec->sh_addr + rel->r_offset; + + switch (ELF32_R_TYPE(rel->r_info)) { + case R_ARM_NONE: + /* ignore */ + break; + + case R_ARM_ABS32: + case R_ARM_TARGET1: + *(u32 *)loc += sym->st_value; + break; + + case R_ARM_PC24: + case R_ARM_CALL: + case R_ARM_JUMP24: + if (sym->st_value & 3) { + pr_err("%s: section %u reloc %u sym '%s': unsupported interworking call (ARM -> Thumb)\n", + module->name, relindex, i, symname); + return -ENOEXEC; + } + + offset = __mem_to_opcode_arm(*(u32 *)loc); + offset = (offset & 0x00ffffff) << 2; + if (offset & 0x02000000) + offset -= 0x04000000; + + offset += sym->st_value - loc; + + /* + * Route through a PLT entry if 'offset' exceeds the + * supported range. Note that 'offset + loc + 8' + * contains the absolute jump target, i.e., + * @sym + addend, corrected for the +8 PC bias. + */ + if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS) && + (offset <= (s32)0xfe000000 || + offset >= (s32)0x02000000)) + offset = get_module_plt(module, loc, + offset + loc + 8) + - loc - 8; + + if (offset <= (s32)0xfe000000 || + offset >= (s32)0x02000000) { + pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n", + module->name, relindex, i, symname, + ELF32_R_TYPE(rel->r_info), loc, + sym->st_value); + return -ENOEXEC; + } + + offset >>= 2; + offset &= 0x00ffffff; + + *(u32 *)loc &= __opcode_to_mem_arm(0xff000000); + *(u32 *)loc |= __opcode_to_mem_arm(offset); + break; + + case R_ARM_V4BX: + /* Preserve Rm and the condition code. Alter + * other bits to re-code instruction as + * MOV PC,Rm. + */ + *(u32 *)loc &= __opcode_to_mem_arm(0xf000000f); + *(u32 *)loc |= __opcode_to_mem_arm(0x01a0f000); + break; + + case R_ARM_PREL31: + offset = (*(s32 *)loc << 1) >> 1; /* sign extend */ + offset += sym->st_value - loc; + if (offset >= 0x40000000 || offset < -0x40000000) { + pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n", + module->name, relindex, i, symname, + ELF32_R_TYPE(rel->r_info), loc, + sym->st_value); + return -ENOEXEC; + } + *(u32 *)loc &= 0x80000000; + *(u32 *)loc |= offset & 0x7fffffff; + break; + + case R_ARM_REL32: + *(u32 *)loc += sym->st_value - loc; + break; + + case R_ARM_MOVW_ABS_NC: + case R_ARM_MOVT_ABS: + case R_ARM_MOVW_PREL_NC: + case R_ARM_MOVT_PREL: + offset = tmp = __mem_to_opcode_arm(*(u32 *)loc); + offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff); + offset = (offset ^ 0x8000) - 0x8000; + + offset += sym->st_value; + if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_PREL || + ELF32_R_TYPE(rel->r_info) == R_ARM_MOVW_PREL_NC) + offset -= loc; + if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS || + ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_PREL) + offset >>= 16; + + tmp &= 0xfff0f000; + tmp |= ((offset & 0xf000) << 4) | + (offset & 0x0fff); + + *(u32 *)loc = __opcode_to_mem_arm(tmp); + break; + +#ifdef CONFIG_ARM_HAS_GROUP_RELOCS + case R_ARM_ALU_PC_G0_NC: + group = 0; + fallthrough; + case R_ARM_ALU_PC_G1_NC: + tmp = __mem_to_opcode_arm(*(u32 *)loc); + offset = ror32(tmp & 0xff, (tmp & 0xf00) >> 7); + if (tmp & BIT(22)) + offset = -offset; + offset += sym->st_value - loc; + if (offset < 0) { + offset = -offset; + tmp = (tmp & ~BIT(23)) | BIT(22); // SUB opcode + } else { + tmp = (tmp & ~BIT(22)) | BIT(23); // ADD opcode + } + + shift = get_group_rem(group, &offset); + if (shift < 24) { + offset >>= 24 - shift; + offset |= (shift + 8) << 7; + } + *(u32 *)loc = __opcode_to_mem_arm((tmp & ~0xfff) | offset); + break; + + case R_ARM_LDR_PC_G2: + tmp = __mem_to_opcode_arm(*(u32 *)loc); + offset = tmp & 0xfff; + if (~tmp & BIT(23)) // U bit cleared? + offset = -offset; + offset += sym->st_value - loc; + if (offset < 0) { + offset = -offset; + tmp &= ~BIT(23); // clear U bit + } else { + tmp |= BIT(23); // set U bit + } + get_group_rem(2, &offset); + + if (offset > 0xfff) { + pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n", + module->name, relindex, i, symname, + ELF32_R_TYPE(rel->r_info), loc, + sym->st_value); + return -ENOEXEC; + } + *(u32 *)loc = __opcode_to_mem_arm((tmp & ~0xfff) | offset); + break; +#endif +#ifdef CONFIG_THUMB2_KERNEL + case R_ARM_THM_CALL: + case R_ARM_THM_JUMP24: + /* + * For function symbols, only Thumb addresses are + * allowed (no interworking). + * + * For non-function symbols, the destination + * has no specific ARM/Thumb disposition, so + * the branch is resolved under the assumption + * that interworking is not required. + */ + if (ELF32_ST_TYPE(sym->st_info) == STT_FUNC && + !(sym->st_value & 1)) { + pr_err("%s: section %u reloc %u sym '%s': unsupported interworking call (Thumb -> ARM)\n", + module->name, relindex, i, symname); + return -ENOEXEC; + } + + upper = __mem_to_opcode_thumb16(*(u16 *)loc); + lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2)); + + /* + * 25 bit signed address range (Thumb-2 BL and B.W + * instructions): + * S:I1:I2:imm10:imm11:0 + * where: + * S = upper[10] = offset[24] + * I1 = ~(J1 ^ S) = offset[23] + * I2 = ~(J2 ^ S) = offset[22] + * imm10 = upper[9:0] = offset[21:12] + * imm11 = lower[10:0] = offset[11:1] + * J1 = lower[13] + * J2 = lower[11] + */ + sign = (upper >> 10) & 1; + j1 = (lower >> 13) & 1; + j2 = (lower >> 11) & 1; + offset = (sign << 24) | ((~(j1 ^ sign) & 1) << 23) | + ((~(j2 ^ sign) & 1) << 22) | + ((upper & 0x03ff) << 12) | + ((lower & 0x07ff) << 1); + if (offset & 0x01000000) + offset -= 0x02000000; + offset += sym->st_value - loc; + + /* + * Route through a PLT entry if 'offset' exceeds the + * supported range. + */ + if (IS_ENABLED(CONFIG_ARM_MODULE_PLTS) && + (offset <= (s32)0xff000000 || + offset >= (s32)0x01000000)) + offset = get_module_plt(module, loc, + offset + loc + 4) + - loc - 4; + + if (offset <= (s32)0xff000000 || + offset >= (s32)0x01000000) { + pr_err("%s: section %u reloc %u sym '%s': relocation %u out of range (%#lx -> %#x)\n", + module->name, relindex, i, symname, + ELF32_R_TYPE(rel->r_info), loc, + sym->st_value); + return -ENOEXEC; + } + + sign = (offset >> 24) & 1; + j1 = sign ^ (~(offset >> 23) & 1); + j2 = sign ^ (~(offset >> 22) & 1); + upper = (u16)((upper & 0xf800) | (sign << 10) | + ((offset >> 12) & 0x03ff)); + lower = (u16)((lower & 0xd000) | + (j1 << 13) | (j2 << 11) | + ((offset >> 1) & 0x07ff)); + + *(u16 *)loc = __opcode_to_mem_thumb16(upper); + *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower); + break; + + case R_ARM_THM_MOVW_ABS_NC: + case R_ARM_THM_MOVT_ABS: + case R_ARM_THM_MOVW_PREL_NC: + case R_ARM_THM_MOVT_PREL: + upper = __mem_to_opcode_thumb16(*(u16 *)loc); + lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2)); + + /* + * MOVT/MOVW instructions encoding in Thumb-2: + * + * i = upper[10] + * imm4 = upper[3:0] + * imm3 = lower[14:12] + * imm8 = lower[7:0] + * + * imm16 = imm4:i:imm3:imm8 + */ + offset = ((upper & 0x000f) << 12) | + ((upper & 0x0400) << 1) | + ((lower & 0x7000) >> 4) | (lower & 0x00ff); + offset = (offset ^ 0x8000) - 0x8000; + offset += sym->st_value; + + if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_PREL || + ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVW_PREL_NC) + offset -= loc; + if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS || + ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_PREL) + offset >>= 16; + + upper = (u16)((upper & 0xfbf0) | + ((offset & 0xf000) >> 12) | + ((offset & 0x0800) >> 1)); + lower = (u16)((lower & 0x8f00) | + ((offset & 0x0700) << 4) | + (offset & 0x00ff)); + *(u16 *)loc = __opcode_to_mem_thumb16(upper); + *(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower); + break; +#endif + + default: + pr_err("%s: unknown relocation: %u\n", + module->name, ELF32_R_TYPE(rel->r_info)); + return -ENOEXEC; + } + } + return 0; +} + +struct mod_unwind_map { + const Elf_Shdr *unw_sec; + const Elf_Shdr *txt_sec; +}; + +static const Elf_Shdr *find_mod_section(const Elf32_Ehdr *hdr, + const Elf_Shdr *sechdrs, const char *name) +{ + const Elf_Shdr *s, *se; + const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + + for (s = sechdrs, se = sechdrs + hdr->e_shnum; s < se; s++) + if (strcmp(name, secstrs + s->sh_name) == 0) + return s; + + return NULL; +} + +extern void fixup_pv_table(const void *, unsigned long); +extern void fixup_smp(const void *, unsigned long); + +int module_finalize(const Elf32_Ehdr *hdr, const Elf_Shdr *sechdrs, + struct module *mod) +{ + const Elf_Shdr *s = NULL; +#ifdef CONFIG_ARM_UNWIND + const char *secstrs = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset; + const Elf_Shdr *sechdrs_end = sechdrs + hdr->e_shnum; + struct list_head *unwind_list = &mod->arch.unwind_list; + + INIT_LIST_HEAD(unwind_list); + mod->arch.init_table = NULL; + + for (s = sechdrs; s < sechdrs_end; s++) { + const char *secname = secstrs + s->sh_name; + const char *txtname; + const Elf_Shdr *txt_sec; + + if (!(s->sh_flags & SHF_ALLOC) || + s->sh_type != ELF_SECTION_UNWIND) + continue; + + if (!strcmp(".ARM.exidx", secname)) + txtname = ".text"; + else + txtname = secname + strlen(".ARM.exidx"); + txt_sec = find_mod_section(hdr, sechdrs, txtname); + + if (txt_sec) { + struct unwind_table *table = + unwind_table_add(s->sh_addr, + s->sh_size, + txt_sec->sh_addr, + txt_sec->sh_size); + + list_add(&table->mod_list, unwind_list); + + /* save init table for module_arch_freeing_init */ + if (strcmp(".ARM.exidx.init.text", secname) == 0) + mod->arch.init_table = table; + } + } +#endif +#ifdef CONFIG_ARM_PATCH_PHYS_VIRT + s = find_mod_section(hdr, sechdrs, ".pv_table"); + if (s) + fixup_pv_table((void *)s->sh_addr, s->sh_size); +#endif + s = find_mod_section(hdr, sechdrs, ".alt.smp.init"); + if (s && !is_smp()) +#ifdef CONFIG_SMP_ON_UP + fixup_smp((void *)s->sh_addr, s->sh_size); +#else + return -EINVAL; +#endif + return 0; +} + +void +module_arch_cleanup(struct module *mod) +{ +#ifdef CONFIG_ARM_UNWIND + struct unwind_table *tmp; + struct unwind_table *n; + + list_for_each_entry_safe(tmp, n, + &mod->arch.unwind_list, mod_list) { + list_del(&tmp->mod_list); + unwind_table_del(tmp); + } + mod->arch.init_table = NULL; +#endif +} + +void __weak module_arch_freeing_init(struct module *mod) +{ +#ifdef CONFIG_ARM_UNWIND + struct unwind_table *init = mod->arch.init_table; + + if (init) { + mod->arch.init_table = NULL; + list_del(&init->mod_list); + unwind_table_del(init); + } +#endif +} diff --git a/arch/arm/kernel/opcodes.c b/arch/arm/kernel/opcodes.c new file mode 100644 index 000000000..651914947 --- /dev/null +++ b/arch/arm/kernel/opcodes.c @@ -0,0 +1,69 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/opcodes.c + * + * A32 condition code lookup feature moved from nwfpe/fpopcode.c + */ + +#include <linux/module.h> +#include <asm/opcodes.h> + +#define ARM_OPCODE_CONDITION_UNCOND 0xf + +/* + * condition code lookup table + * index into the table is test code: EQ, NE, ... LT, GT, AL, NV + * + * bit position in short is condition code: NZCV + */ +static const unsigned short cc_map[16] = { + 0xF0F0, /* EQ == Z set */ + 0x0F0F, /* NE */ + 0xCCCC, /* CS == C set */ + 0x3333, /* CC */ + 0xFF00, /* MI == N set */ + 0x00FF, /* PL */ + 0xAAAA, /* VS == V set */ + 0x5555, /* VC */ + 0x0C0C, /* HI == C set && Z clear */ + 0xF3F3, /* LS == C clear || Z set */ + 0xAA55, /* GE == (N==V) */ + 0x55AA, /* LT == (N!=V) */ + 0x0A05, /* GT == (!Z && (N==V)) */ + 0xF5FA, /* LE == (Z || (N!=V)) */ + 0xFFFF, /* AL always */ + 0 /* NV */ +}; + +/* + * Returns: + * ARM_OPCODE_CONDTEST_FAIL - if condition fails + * ARM_OPCODE_CONDTEST_PASS - if condition passes (including AL) + * ARM_OPCODE_CONDTEST_UNCOND - if NV condition, or separate unconditional + * opcode space from v5 onwards + * + * Code that tests whether a conditional instruction would pass its condition + * check should check that return value == ARM_OPCODE_CONDTEST_PASS. + * + * Code that tests if a condition means that the instruction would be executed + * (regardless of conditional or unconditional) should instead check that the + * return value != ARM_OPCODE_CONDTEST_FAIL. + */ +asmlinkage unsigned int arm_check_condition(u32 opcode, u32 psr) +{ + u32 cc_bits = opcode >> 28; + u32 psr_cond = psr >> 28; + unsigned int ret; + + if (cc_bits != ARM_OPCODE_CONDITION_UNCOND) { + if ((cc_map[cc_bits] >> (psr_cond)) & 1) + ret = ARM_OPCODE_CONDTEST_PASS; + else + ret = ARM_OPCODE_CONDTEST_FAIL; + } else { + ret = ARM_OPCODE_CONDTEST_UNCOND; + } + + return ret; +} +EXPORT_SYMBOL_GPL(arm_check_condition); diff --git a/arch/arm/kernel/paravirt.c b/arch/arm/kernel/paravirt.c new file mode 100644 index 000000000..7dd980636 --- /dev/null +++ b/arch/arm/kernel/paravirt.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * + * Copyright (C) 2013 Citrix Systems + * + * Author: Stefano Stabellini <stefano.stabellini@eu.citrix.com> + */ + +#include <linux/export.h> +#include <linux/jump_label.h> +#include <linux/types.h> +#include <linux/static_call.h> +#include <asm/paravirt.h> + +struct static_key paravirt_steal_enabled; +struct static_key paravirt_steal_rq_enabled; + +static u64 native_steal_clock(int cpu) +{ + return 0; +} + +DEFINE_STATIC_CALL(pv_steal_clock, native_steal_clock); diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c new file mode 100644 index 000000000..e9e828b6b --- /dev/null +++ b/arch/arm/kernel/patch.c @@ -0,0 +1,128 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/kernel.h> +#include <linux/spinlock.h> +#include <linux/kprobes.h> +#include <linux/mm.h> +#include <linux/stop_machine.h> + +#include <asm/cacheflush.h> +#include <asm/fixmap.h> +#include <asm/smp_plat.h> +#include <asm/opcodes.h> +#include <asm/patch.h> + +struct patch { + void *addr; + unsigned int insn; +}; + +#ifdef CONFIG_MMU +static DEFINE_RAW_SPINLOCK(patch_lock); + +static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) +{ + unsigned int uintaddr = (uintptr_t) addr; + bool module = !core_kernel_text(uintaddr); + struct page *page; + + if (module && IS_ENABLED(CONFIG_STRICT_MODULE_RWX)) + page = vmalloc_to_page(addr); + else if (!module && IS_ENABLED(CONFIG_STRICT_KERNEL_RWX)) + page = virt_to_page(addr); + else + return addr; + + if (flags) + raw_spin_lock_irqsave(&patch_lock, *flags); + + set_fixmap(fixmap, page_to_phys(page)); + + return (void *) (__fix_to_virt(fixmap) + (uintaddr & ~PAGE_MASK)); +} + +static void __kprobes patch_unmap(int fixmap, unsigned long *flags) +{ + clear_fixmap(fixmap); + + if (flags) + raw_spin_unlock_irqrestore(&patch_lock, *flags); +} +#else +static void __kprobes *patch_map(void *addr, int fixmap, unsigned long *flags) +{ + return addr; +} +static void __kprobes patch_unmap(int fixmap, unsigned long *flags) { } +#endif + +void __kprobes __patch_text_real(void *addr, unsigned int insn, bool remap) +{ + bool thumb2 = IS_ENABLED(CONFIG_THUMB2_KERNEL); + unsigned int uintaddr = (uintptr_t) addr; + bool twopage = false; + unsigned long flags; + void *waddr = addr; + int size; + + if (remap) + waddr = patch_map(addr, FIX_TEXT_POKE0, &flags); + + if (thumb2 && __opcode_is_thumb16(insn)) { + *(u16 *)waddr = __opcode_to_mem_thumb16(insn); + size = sizeof(u16); + } else if (thumb2 && (uintaddr & 2)) { + u16 first = __opcode_thumb32_first(insn); + u16 second = __opcode_thumb32_second(insn); + u16 *addrh0 = waddr; + u16 *addrh1 = waddr + 2; + + twopage = (uintaddr & ~PAGE_MASK) == PAGE_SIZE - 2; + if (twopage && remap) + addrh1 = patch_map(addr + 2, FIX_TEXT_POKE1, NULL); + + *addrh0 = __opcode_to_mem_thumb16(first); + *addrh1 = __opcode_to_mem_thumb16(second); + + if (twopage && addrh1 != addr + 2) { + flush_kernel_vmap_range(addrh1, 2); + patch_unmap(FIX_TEXT_POKE1, NULL); + } + + size = sizeof(u32); + } else { + if (thumb2) + insn = __opcode_to_mem_thumb32(insn); + else + insn = __opcode_to_mem_arm(insn); + + *(u32 *)waddr = insn; + size = sizeof(u32); + } + + if (waddr != addr) { + flush_kernel_vmap_range(waddr, twopage ? size / 2 : size); + patch_unmap(FIX_TEXT_POKE0, &flags); + } + + flush_icache_range((uintptr_t)(addr), + (uintptr_t)(addr) + size); +} + +static int __kprobes patch_text_stop_machine(void *data) +{ + struct patch *patch = data; + + __patch_text(patch->addr, patch->insn); + + return 0; +} + +void __kprobes patch_text(void *addr, unsigned int insn) +{ + struct patch patch = { + .addr = addr, + .insn = insn, + }; + + stop_machine_cpuslocked(patch_text_stop_machine, &patch, NULL); +} diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c new file mode 100644 index 000000000..bc6b246ab --- /dev/null +++ b/arch/arm/kernel/perf_callchain.c @@ -0,0 +1,117 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ARM callchain support + * + * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles + * Copyright (C) 2010 ARM Ltd., Will Deacon <will.deacon@arm.com> + * + * This code is based on the ARM OProfile backtrace code. + */ +#include <linux/perf_event.h> +#include <linux/uaccess.h> + +#include <asm/stacktrace.h> + +/* + * The registers we're interested in are at the end of the variable + * length saved register structure. The fp points at the end of this + * structure so the address of this struct is: + * (struct frame_tail *)(xxx->fp)-1 + * + * This code has been adapted from the ARM OProfile support. + */ +struct frame_tail { + struct frame_tail __user *fp; + unsigned long sp; + unsigned long lr; +} __attribute__((packed)); + +/* + * Get the return address for a single stackframe and return a pointer to the + * next frame tail. + */ +static struct frame_tail __user * +user_backtrace(struct frame_tail __user *tail, + struct perf_callchain_entry_ctx *entry) +{ + struct frame_tail buftail; + unsigned long err; + + if (!access_ok(tail, sizeof(buftail))) + return NULL; + + pagefault_disable(); + err = __copy_from_user_inatomic(&buftail, tail, sizeof(buftail)); + pagefault_enable(); + + if (err) + return NULL; + + perf_callchain_store(entry, buftail.lr); + + /* + * Frame pointers should strictly progress back up the stack + * (towards higher addresses). + */ + if (tail + 1 >= buftail.fp) + return NULL; + + return buftail.fp - 1; +} + +void +perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) +{ + struct frame_tail __user *tail; + + perf_callchain_store(entry, regs->ARM_pc); + + if (!current->mm) + return; + + tail = (struct frame_tail __user *)regs->ARM_fp - 1; + + while ((entry->nr < entry->max_stack) && + tail && !((unsigned long)tail & 0x3)) + tail = user_backtrace(tail, entry); +} + +/* + * Gets called by walk_stackframe() for every stackframe. This will be called + * whist unwinding the stackframe and is like a subroutine return so we use + * the PC. + */ +static int +callchain_trace(struct stackframe *fr, + void *data) +{ + struct perf_callchain_entry_ctx *entry = data; + perf_callchain_store(entry, fr->pc); + return 0; +} + +void +perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) +{ + struct stackframe fr; + + arm_get_current_stackframe(regs, &fr); + walk_stackframe(&fr, callchain_trace, entry); +} + +unsigned long perf_instruction_pointer(struct pt_regs *regs) +{ + return instruction_pointer(regs); +} + +unsigned long perf_misc_flags(struct pt_regs *regs) +{ + int misc = 0; + + if (user_mode(regs)) + misc |= PERF_RECORD_MISC_USER; + else + misc |= PERF_RECORD_MISC_KERNEL; + + return misc; +} diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c new file mode 100644 index 000000000..1ae99deee --- /dev/null +++ b/arch/arm/kernel/perf_event_v6.c @@ -0,0 +1,590 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ARMv6 Performance counter handling code. + * + * Copyright (C) 2009 picoChip Designs, Ltd., Jamie Iles + * + * ARMv6 has 2 configurable performance counters and a single cycle counter. + * They all share a single reset bit but can be written to zero so we can use + * that for a reset. + * + * The counters can't be individually enabled or disabled so when we remove + * one event and replace it with another we could get spurious counts from the + * wrong event. However, we can take advantage of the fact that the + * performance counters can export events to the event bus, and the event bus + * itself can be monitored. This requires that we *don't* export the events to + * the event bus. The procedure for disabling a configurable counter is: + * - change the counter to count the ETMEXTOUT[0] signal (0x20). This + * effectively stops the counter from counting. + * - disable the counter's interrupt generation (each counter has it's + * own interrupt enable bit). + * Once stopped, the counter value can be written as 0 to reset. + * + * To enable a counter: + * - enable the counter's interrupt generation. + * - set the new event type. + * + * Note: the dedicated cycle counter only counts cycles and can't be + * enabled/disabled independently of the others. When we want to disable the + * cycle counter, we have to just disable the interrupt reporting and start + * ignoring that counter. When re-enabling, we have to reset the value and + * enable the interrupt. + */ + +#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K) + +#include <asm/cputype.h> +#include <asm/irq_regs.h> + +#include <linux/of.h> +#include <linux/perf/arm_pmu.h> +#include <linux/platform_device.h> + +enum armv6_perf_types { + ARMV6_PERFCTR_ICACHE_MISS = 0x0, + ARMV6_PERFCTR_IBUF_STALL = 0x1, + ARMV6_PERFCTR_DDEP_STALL = 0x2, + ARMV6_PERFCTR_ITLB_MISS = 0x3, + ARMV6_PERFCTR_DTLB_MISS = 0x4, + ARMV6_PERFCTR_BR_EXEC = 0x5, + ARMV6_PERFCTR_BR_MISPREDICT = 0x6, + ARMV6_PERFCTR_INSTR_EXEC = 0x7, + ARMV6_PERFCTR_DCACHE_HIT = 0x9, + ARMV6_PERFCTR_DCACHE_ACCESS = 0xA, + ARMV6_PERFCTR_DCACHE_MISS = 0xB, + ARMV6_PERFCTR_DCACHE_WBACK = 0xC, + ARMV6_PERFCTR_SW_PC_CHANGE = 0xD, + ARMV6_PERFCTR_MAIN_TLB_MISS = 0xF, + ARMV6_PERFCTR_EXPL_D_ACCESS = 0x10, + ARMV6_PERFCTR_LSU_FULL_STALL = 0x11, + ARMV6_PERFCTR_WBUF_DRAINED = 0x12, + ARMV6_PERFCTR_CPU_CYCLES = 0xFF, + ARMV6_PERFCTR_NOP = 0x20, +}; + +enum armv6_counters { + ARMV6_CYCLE_COUNTER = 0, + ARMV6_COUNTER0, + ARMV6_COUNTER1, +}; + +/* + * The hardware events that we support. We do support cache operations but + * we have harvard caches and no way to combine instruction and data + * accesses/misses in hardware. + */ +static const unsigned armv6_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV6_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV6_PERFCTR_INSTR_EXEC, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6_PERFCTR_BR_EXEC, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV6_PERFCTR_BR_MISPREDICT, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV6_PERFCTR_IBUF_STALL, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV6_PERFCTR_LSU_FULL_STALL, +}; + +static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + /* + * The performance counters don't differentiate between read and write + * accesses/misses so this isn't strictly correct, but it's the best we + * can do. Writes and reads get combined. + */ + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV6_PERFCTR_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_DCACHE_MISS, + + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_ICACHE_MISS, + + /* + * The ARM performance counters can count micro DTLB misses, micro ITLB + * misses and main TLB misses. There isn't an event for TLB misses, so + * use the micro misses here and if users want the main TLB misses they + * can use a raw counter. + */ + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_DTLB_MISS, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6_PERFCTR_ITLB_MISS, +}; + +enum armv6mpcore_perf_types { + ARMV6MPCORE_PERFCTR_ICACHE_MISS = 0x0, + ARMV6MPCORE_PERFCTR_IBUF_STALL = 0x1, + ARMV6MPCORE_PERFCTR_DDEP_STALL = 0x2, + ARMV6MPCORE_PERFCTR_ITLB_MISS = 0x3, + ARMV6MPCORE_PERFCTR_DTLB_MISS = 0x4, + ARMV6MPCORE_PERFCTR_BR_EXEC = 0x5, + ARMV6MPCORE_PERFCTR_BR_NOTPREDICT = 0x6, + ARMV6MPCORE_PERFCTR_BR_MISPREDICT = 0x7, + ARMV6MPCORE_PERFCTR_INSTR_EXEC = 0x8, + ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS = 0xA, + ARMV6MPCORE_PERFCTR_DCACHE_RDMISS = 0xB, + ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS = 0xC, + ARMV6MPCORE_PERFCTR_DCACHE_WRMISS = 0xD, + ARMV6MPCORE_PERFCTR_DCACHE_EVICTION = 0xE, + ARMV6MPCORE_PERFCTR_SW_PC_CHANGE = 0xF, + ARMV6MPCORE_PERFCTR_MAIN_TLB_MISS = 0x10, + ARMV6MPCORE_PERFCTR_EXPL_MEM_ACCESS = 0x11, + ARMV6MPCORE_PERFCTR_LSU_FULL_STALL = 0x12, + ARMV6MPCORE_PERFCTR_WBUF_DRAINED = 0x13, + ARMV6MPCORE_PERFCTR_CPU_CYCLES = 0xFF, +}; + +/* + * The hardware events that we support. We do support cache operations but + * we have harvard caches and no way to combine instruction and data + * accesses/misses in hardware. + */ +static const unsigned armv6mpcore_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV6MPCORE_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_INSTR_EXEC, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV6MPCORE_PERFCTR_BR_EXEC, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV6MPCORE_PERFCTR_BR_MISPREDICT, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV6MPCORE_PERFCTR_IBUF_STALL, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV6MPCORE_PERFCTR_LSU_FULL_STALL, +}; + +static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV6MPCORE_PERFCTR_DCACHE_RDACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DCACHE_RDMISS, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV6MPCORE_PERFCTR_DCACHE_WRACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DCACHE_WRMISS, + + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ICACHE_MISS, + + /* + * The ARM performance counters can count micro DTLB misses, micro ITLB + * misses and main TLB misses. There isn't an event for TLB misses, so + * use the micro misses here and if users want the main TLB misses they + * can use a raw counter. + */ + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_DTLB_MISS, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV6MPCORE_PERFCTR_ITLB_MISS, +}; + +static inline unsigned long +armv6_pmcr_read(void) +{ + u32 val; + asm volatile("mrc p15, 0, %0, c15, c12, 0" : "=r"(val)); + return val; +} + +static inline void +armv6_pmcr_write(unsigned long val) +{ + asm volatile("mcr p15, 0, %0, c15, c12, 0" : : "r"(val)); +} + +#define ARMV6_PMCR_ENABLE (1 << 0) +#define ARMV6_PMCR_CTR01_RESET (1 << 1) +#define ARMV6_PMCR_CCOUNT_RESET (1 << 2) +#define ARMV6_PMCR_CCOUNT_DIV (1 << 3) +#define ARMV6_PMCR_COUNT0_IEN (1 << 4) +#define ARMV6_PMCR_COUNT1_IEN (1 << 5) +#define ARMV6_PMCR_CCOUNT_IEN (1 << 6) +#define ARMV6_PMCR_COUNT0_OVERFLOW (1 << 8) +#define ARMV6_PMCR_COUNT1_OVERFLOW (1 << 9) +#define ARMV6_PMCR_CCOUNT_OVERFLOW (1 << 10) +#define ARMV6_PMCR_EVT_COUNT0_SHIFT 20 +#define ARMV6_PMCR_EVT_COUNT0_MASK (0xFF << ARMV6_PMCR_EVT_COUNT0_SHIFT) +#define ARMV6_PMCR_EVT_COUNT1_SHIFT 12 +#define ARMV6_PMCR_EVT_COUNT1_MASK (0xFF << ARMV6_PMCR_EVT_COUNT1_SHIFT) + +#define ARMV6_PMCR_OVERFLOWED_MASK \ + (ARMV6_PMCR_COUNT0_OVERFLOW | ARMV6_PMCR_COUNT1_OVERFLOW | \ + ARMV6_PMCR_CCOUNT_OVERFLOW) + +static inline int +armv6_pmcr_has_overflowed(unsigned long pmcr) +{ + return pmcr & ARMV6_PMCR_OVERFLOWED_MASK; +} + +static inline int +armv6_pmcr_counter_has_overflowed(unsigned long pmcr, + enum armv6_counters counter) +{ + int ret = 0; + + if (ARMV6_CYCLE_COUNTER == counter) + ret = pmcr & ARMV6_PMCR_CCOUNT_OVERFLOW; + else if (ARMV6_COUNTER0 == counter) + ret = pmcr & ARMV6_PMCR_COUNT0_OVERFLOW; + else if (ARMV6_COUNTER1 == counter) + ret = pmcr & ARMV6_PMCR_COUNT1_OVERFLOW; + else + WARN_ONCE(1, "invalid counter number (%d)\n", counter); + + return ret; +} + +static inline u64 armv6pmu_read_counter(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int counter = hwc->idx; + unsigned long value = 0; + + if (ARMV6_CYCLE_COUNTER == counter) + asm volatile("mrc p15, 0, %0, c15, c12, 1" : "=r"(value)); + else if (ARMV6_COUNTER0 == counter) + asm volatile("mrc p15, 0, %0, c15, c12, 2" : "=r"(value)); + else if (ARMV6_COUNTER1 == counter) + asm volatile("mrc p15, 0, %0, c15, c12, 3" : "=r"(value)); + else + WARN_ONCE(1, "invalid counter number (%d)\n", counter); + + return value; +} + +static inline void armv6pmu_write_counter(struct perf_event *event, u64 value) +{ + struct hw_perf_event *hwc = &event->hw; + int counter = hwc->idx; + + if (ARMV6_CYCLE_COUNTER == counter) + asm volatile("mcr p15, 0, %0, c15, c12, 1" : : "r"(value)); + else if (ARMV6_COUNTER0 == counter) + asm volatile("mcr p15, 0, %0, c15, c12, 2" : : "r"(value)); + else if (ARMV6_COUNTER1 == counter) + asm volatile("mcr p15, 0, %0, c15, c12, 3" : : "r"(value)); + else + WARN_ONCE(1, "invalid counter number (%d)\n", counter); +} + +static void armv6pmu_enable_event(struct perf_event *event) +{ + unsigned long val, mask, evt, flags; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx = hwc->idx; + + if (ARMV6_CYCLE_COUNTER == idx) { + mask = 0; + evt = ARMV6_PMCR_CCOUNT_IEN; + } else if (ARMV6_COUNTER0 == idx) { + mask = ARMV6_PMCR_EVT_COUNT0_MASK; + evt = (hwc->config_base << ARMV6_PMCR_EVT_COUNT0_SHIFT) | + ARMV6_PMCR_COUNT0_IEN; + } else if (ARMV6_COUNTER1 == idx) { + mask = ARMV6_PMCR_EVT_COUNT1_MASK; + evt = (hwc->config_base << ARMV6_PMCR_EVT_COUNT1_SHIFT) | + ARMV6_PMCR_COUNT1_IEN; + } else { + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + /* + * Mask out the current event and set the counter to count the event + * that we're interested in. + */ + raw_spin_lock_irqsave(&events->pmu_lock, flags); + val = armv6_pmcr_read(); + val &= ~mask; + val |= evt; + armv6_pmcr_write(val); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static irqreturn_t +armv6pmu_handle_irq(struct arm_pmu *cpu_pmu) +{ + unsigned long pmcr = armv6_pmcr_read(); + struct perf_sample_data data; + struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events); + struct pt_regs *regs; + int idx; + + if (!armv6_pmcr_has_overflowed(pmcr)) + return IRQ_NONE; + + regs = get_irq_regs(); + + /* + * The interrupts are cleared by writing the overflow flags back to + * the control register. All of the other bits don't have any effect + * if they are rewritten, so write the whole value back. + */ + armv6_pmcr_write(pmcr); + + for (idx = 0; idx < cpu_pmu->num_events; ++idx) { + struct perf_event *event = cpuc->events[idx]; + struct hw_perf_event *hwc; + + /* Ignore if we don't have an event. */ + if (!event) + continue; + + /* + * We have a single interrupt for all counters. Check that + * each counter has overflowed before we process it. + */ + if (!armv6_pmcr_counter_has_overflowed(pmcr, idx)) + continue; + + hwc = &event->hw; + armpmu_event_update(event); + perf_sample_data_init(&data, 0, hwc->last_period); + if (!armpmu_event_set_period(event)) + continue; + + if (perf_event_overflow(event, &data, regs)) + cpu_pmu->disable(event); + } + + /* + * Handle the pending perf events. + * + * Note: this call *must* be run with interrupts disabled. For + * platforms that can have the PMU interrupts raised as an NMI, this + * will not work. + */ + irq_work_run(); + + return IRQ_HANDLED; +} + +static void armv6pmu_start(struct arm_pmu *cpu_pmu) +{ + unsigned long flags, val; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + val = armv6_pmcr_read(); + val |= ARMV6_PMCR_ENABLE; + armv6_pmcr_write(val); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void armv6pmu_stop(struct arm_pmu *cpu_pmu) +{ + unsigned long flags, val; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + val = armv6_pmcr_read(); + val &= ~ARMV6_PMCR_ENABLE; + armv6_pmcr_write(val); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static int +armv6pmu_get_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + /* Always place a cycle counter into the cycle counter. */ + if (ARMV6_PERFCTR_CPU_CYCLES == hwc->config_base) { + if (test_and_set_bit(ARMV6_CYCLE_COUNTER, cpuc->used_mask)) + return -EAGAIN; + + return ARMV6_CYCLE_COUNTER; + } else { + /* + * For anything other than a cycle counter, try and use + * counter0 and counter1. + */ + if (!test_and_set_bit(ARMV6_COUNTER1, cpuc->used_mask)) + return ARMV6_COUNTER1; + + if (!test_and_set_bit(ARMV6_COUNTER0, cpuc->used_mask)) + return ARMV6_COUNTER0; + + /* The counters are all in use. */ + return -EAGAIN; + } +} + +static void armv6pmu_clear_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + clear_bit(event->hw.idx, cpuc->used_mask); +} + +static void armv6pmu_disable_event(struct perf_event *event) +{ + unsigned long val, mask, evt, flags; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx = hwc->idx; + + if (ARMV6_CYCLE_COUNTER == idx) { + mask = ARMV6_PMCR_CCOUNT_IEN; + evt = 0; + } else if (ARMV6_COUNTER0 == idx) { + mask = ARMV6_PMCR_COUNT0_IEN | ARMV6_PMCR_EVT_COUNT0_MASK; + evt = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT0_SHIFT; + } else if (ARMV6_COUNTER1 == idx) { + mask = ARMV6_PMCR_COUNT1_IEN | ARMV6_PMCR_EVT_COUNT1_MASK; + evt = ARMV6_PERFCTR_NOP << ARMV6_PMCR_EVT_COUNT1_SHIFT; + } else { + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + /* + * Mask out the current event and set the counter to count the number + * of ETM bus signal assertion cycles. The external reporting should + * be disabled and so this should never increment. + */ + raw_spin_lock_irqsave(&events->pmu_lock, flags); + val = armv6_pmcr_read(); + val &= ~mask; + val |= evt; + armv6_pmcr_write(val); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void armv6mpcore_pmu_disable_event(struct perf_event *event) +{ + unsigned long val, mask, flags, evt = 0; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx = hwc->idx; + + if (ARMV6_CYCLE_COUNTER == idx) { + mask = ARMV6_PMCR_CCOUNT_IEN; + } else if (ARMV6_COUNTER0 == idx) { + mask = ARMV6_PMCR_COUNT0_IEN; + } else if (ARMV6_COUNTER1 == idx) { + mask = ARMV6_PMCR_COUNT1_IEN; + } else { + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + /* + * Unlike UP ARMv6, we don't have a way of stopping the counters. We + * simply disable the interrupt reporting. + */ + raw_spin_lock_irqsave(&events->pmu_lock, flags); + val = armv6_pmcr_read(); + val &= ~mask; + val |= evt; + armv6_pmcr_write(val); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static int armv6_map_event(struct perf_event *event) +{ + return armpmu_map_event(event, &armv6_perf_map, + &armv6_perf_cache_map, 0xFF); +} + +static void armv6pmu_init(struct arm_pmu *cpu_pmu) +{ + cpu_pmu->handle_irq = armv6pmu_handle_irq; + cpu_pmu->enable = armv6pmu_enable_event; + cpu_pmu->disable = armv6pmu_disable_event; + cpu_pmu->read_counter = armv6pmu_read_counter; + cpu_pmu->write_counter = armv6pmu_write_counter; + cpu_pmu->get_event_idx = armv6pmu_get_event_idx; + cpu_pmu->clear_event_idx = armv6pmu_clear_event_idx; + cpu_pmu->start = armv6pmu_start; + cpu_pmu->stop = armv6pmu_stop; + cpu_pmu->map_event = armv6_map_event; + cpu_pmu->num_events = 3; +} + +static int armv6_1136_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv6pmu_init(cpu_pmu); + cpu_pmu->name = "armv6_1136"; + return 0; +} + +static int armv6_1156_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv6pmu_init(cpu_pmu); + cpu_pmu->name = "armv6_1156"; + return 0; +} + +static int armv6_1176_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv6pmu_init(cpu_pmu); + cpu_pmu->name = "armv6_1176"; + return 0; +} + +/* + * ARMv6mpcore is almost identical to single core ARMv6 with the exception + * that some of the events have different enumerations and that there is no + * *hack* to stop the programmable counters. To stop the counters we simply + * disable the interrupt reporting and update the event. When unthrottling we + * reset the period and enable the interrupt reporting. + */ + +static int armv6mpcore_map_event(struct perf_event *event) +{ + return armpmu_map_event(event, &armv6mpcore_perf_map, + &armv6mpcore_perf_cache_map, 0xFF); +} + +static int armv6mpcore_pmu_init(struct arm_pmu *cpu_pmu) +{ + cpu_pmu->name = "armv6_11mpcore"; + cpu_pmu->handle_irq = armv6pmu_handle_irq; + cpu_pmu->enable = armv6pmu_enable_event; + cpu_pmu->disable = armv6mpcore_pmu_disable_event; + cpu_pmu->read_counter = armv6pmu_read_counter; + cpu_pmu->write_counter = armv6pmu_write_counter; + cpu_pmu->get_event_idx = armv6pmu_get_event_idx; + cpu_pmu->clear_event_idx = armv6pmu_clear_event_idx; + cpu_pmu->start = armv6pmu_start; + cpu_pmu->stop = armv6pmu_stop; + cpu_pmu->map_event = armv6mpcore_map_event; + cpu_pmu->num_events = 3; + + return 0; +} + +static const struct of_device_id armv6_pmu_of_device_ids[] = { + {.compatible = "arm,arm11mpcore-pmu", .data = armv6mpcore_pmu_init}, + {.compatible = "arm,arm1176-pmu", .data = armv6_1176_pmu_init}, + {.compatible = "arm,arm1136-pmu", .data = armv6_1136_pmu_init}, + { /* sentinel value */ } +}; + +static const struct pmu_probe_info armv6_pmu_probe_table[] = { + ARM_PMU_PROBE(ARM_CPU_PART_ARM1136, armv6_1136_pmu_init), + ARM_PMU_PROBE(ARM_CPU_PART_ARM1156, armv6_1156_pmu_init), + ARM_PMU_PROBE(ARM_CPU_PART_ARM1176, armv6_1176_pmu_init), + ARM_PMU_PROBE(ARM_CPU_PART_ARM11MPCORE, armv6mpcore_pmu_init), + { /* sentinel value */ } +}; + +static int armv6_pmu_device_probe(struct platform_device *pdev) +{ + return arm_pmu_device_probe(pdev, armv6_pmu_of_device_ids, + armv6_pmu_probe_table); +} + +static struct platform_driver armv6_pmu_driver = { + .driver = { + .name = "armv6-pmu", + .of_match_table = armv6_pmu_of_device_ids, + }, + .probe = armv6_pmu_device_probe, +}; + +builtin_platform_driver(armv6_pmu_driver); +#endif /* CONFIG_CPU_V6 || CONFIG_CPU_V6K */ diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c new file mode 100644 index 000000000..eb2190477 --- /dev/null +++ b/arch/arm/kernel/perf_event_v7.c @@ -0,0 +1,2047 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ARMv7 Cortex-A8 and Cortex-A9 Performance Events handling code. + * + * ARMv7 support: Jean Pihet <jpihet@mvista.com> + * 2010 (c) MontaVista Software, LLC. + * + * Copied from ARMv6 code, with the low level code inspired + * by the ARMv7 Oprofile code. + * + * Cortex-A8 has up to 4 configurable performance counters and + * a single cycle counter. + * Cortex-A9 has up to 31 configurable performance counters and + * a single cycle counter. + * + * All counters can be enabled/disabled and IRQ masked separately. The cycle + * counter and all 4 performance counters together can be reset separately. + */ + +#ifdef CONFIG_CPU_V7 + +#include <asm/cp15.h> +#include <asm/cputype.h> +#include <asm/irq_regs.h> +#include <asm/vfp.h> +#include "../vfp/vfpinstr.h" + +#include <linux/of.h> +#include <linux/perf/arm_pmu.h> +#include <linux/platform_device.h> + +/* + * Common ARMv7 event types + * + * Note: An implementation may not be able to count all of these events + * but the encodings are considered to be `reserved' in the case that + * they are not available. + */ +#define ARMV7_PERFCTR_PMNC_SW_INCR 0x00 +#define ARMV7_PERFCTR_L1_ICACHE_REFILL 0x01 +#define ARMV7_PERFCTR_ITLB_REFILL 0x02 +#define ARMV7_PERFCTR_L1_DCACHE_REFILL 0x03 +#define ARMV7_PERFCTR_L1_DCACHE_ACCESS 0x04 +#define ARMV7_PERFCTR_DTLB_REFILL 0x05 +#define ARMV7_PERFCTR_MEM_READ 0x06 +#define ARMV7_PERFCTR_MEM_WRITE 0x07 +#define ARMV7_PERFCTR_INSTR_EXECUTED 0x08 +#define ARMV7_PERFCTR_EXC_TAKEN 0x09 +#define ARMV7_PERFCTR_EXC_EXECUTED 0x0A +#define ARMV7_PERFCTR_CID_WRITE 0x0B + +/* + * ARMV7_PERFCTR_PC_WRITE is equivalent to HW_BRANCH_INSTRUCTIONS. + * It counts: + * - all (taken) branch instructions, + * - instructions that explicitly write the PC, + * - exception generating instructions. + */ +#define ARMV7_PERFCTR_PC_WRITE 0x0C +#define ARMV7_PERFCTR_PC_IMM_BRANCH 0x0D +#define ARMV7_PERFCTR_PC_PROC_RETURN 0x0E +#define ARMV7_PERFCTR_MEM_UNALIGNED_ACCESS 0x0F +#define ARMV7_PERFCTR_PC_BRANCH_MIS_PRED 0x10 +#define ARMV7_PERFCTR_CLOCK_CYCLES 0x11 +#define ARMV7_PERFCTR_PC_BRANCH_PRED 0x12 + +/* These events are defined by the PMUv2 supplement (ARM DDI 0457A). */ +#define ARMV7_PERFCTR_MEM_ACCESS 0x13 +#define ARMV7_PERFCTR_L1_ICACHE_ACCESS 0x14 +#define ARMV7_PERFCTR_L1_DCACHE_WB 0x15 +#define ARMV7_PERFCTR_L2_CACHE_ACCESS 0x16 +#define ARMV7_PERFCTR_L2_CACHE_REFILL 0x17 +#define ARMV7_PERFCTR_L2_CACHE_WB 0x18 +#define ARMV7_PERFCTR_BUS_ACCESS 0x19 +#define ARMV7_PERFCTR_MEM_ERROR 0x1A +#define ARMV7_PERFCTR_INSTR_SPEC 0x1B +#define ARMV7_PERFCTR_TTBR_WRITE 0x1C +#define ARMV7_PERFCTR_BUS_CYCLES 0x1D + +#define ARMV7_PERFCTR_CPU_CYCLES 0xFF + +/* ARMv7 Cortex-A8 specific event types */ +#define ARMV7_A8_PERFCTR_L2_CACHE_ACCESS 0x43 +#define ARMV7_A8_PERFCTR_L2_CACHE_REFILL 0x44 +#define ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS 0x50 +#define ARMV7_A8_PERFCTR_STALL_ISIDE 0x56 + +/* ARMv7 Cortex-A9 specific event types */ +#define ARMV7_A9_PERFCTR_INSTR_CORE_RENAME 0x68 +#define ARMV7_A9_PERFCTR_STALL_ICACHE 0x60 +#define ARMV7_A9_PERFCTR_STALL_DISPATCH 0x66 + +/* ARMv7 Cortex-A5 specific event types */ +#define ARMV7_A5_PERFCTR_PREFETCH_LINEFILL 0xc2 +#define ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP 0xc3 + +/* ARMv7 Cortex-A15 specific event types */ +#define ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_READ 0x40 +#define ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_WRITE 0x41 +#define ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_READ 0x42 +#define ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_WRITE 0x43 + +#define ARMV7_A15_PERFCTR_DTLB_REFILL_L1_READ 0x4C +#define ARMV7_A15_PERFCTR_DTLB_REFILL_L1_WRITE 0x4D + +#define ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_READ 0x50 +#define ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_WRITE 0x51 +#define ARMV7_A15_PERFCTR_L2_CACHE_REFILL_READ 0x52 +#define ARMV7_A15_PERFCTR_L2_CACHE_REFILL_WRITE 0x53 + +#define ARMV7_A15_PERFCTR_PC_WRITE_SPEC 0x76 + +/* ARMv7 Cortex-A12 specific event types */ +#define ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ 0x40 +#define ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE 0x41 + +#define ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ 0x50 +#define ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE 0x51 + +#define ARMV7_A12_PERFCTR_PC_WRITE_SPEC 0x76 + +#define ARMV7_A12_PERFCTR_PF_TLB_REFILL 0xe7 + +/* ARMv7 Krait specific event types */ +#define KRAIT_PMRESR0_GROUP0 0xcc +#define KRAIT_PMRESR1_GROUP0 0xd0 +#define KRAIT_PMRESR2_GROUP0 0xd4 +#define KRAIT_VPMRESR0_GROUP0 0xd8 + +#define KRAIT_PERFCTR_L1_ICACHE_ACCESS 0x10011 +#define KRAIT_PERFCTR_L1_ICACHE_MISS 0x10010 + +#define KRAIT_PERFCTR_L1_ITLB_ACCESS 0x12222 +#define KRAIT_PERFCTR_L1_DTLB_ACCESS 0x12210 + +/* ARMv7 Scorpion specific event types */ +#define SCORPION_LPM0_GROUP0 0x4c +#define SCORPION_LPM1_GROUP0 0x50 +#define SCORPION_LPM2_GROUP0 0x54 +#define SCORPION_L2LPM_GROUP0 0x58 +#define SCORPION_VLPM_GROUP0 0x5c + +#define SCORPION_ICACHE_ACCESS 0x10053 +#define SCORPION_ICACHE_MISS 0x10052 + +#define SCORPION_DTLB_ACCESS 0x12013 +#define SCORPION_DTLB_MISS 0x12012 + +#define SCORPION_ITLB_MISS 0x12021 + +/* + * Cortex-A8 HW events mapping + * + * The hardware events that we support. We do support cache operations but + * we have harvard caches and no way to combine instruction and data + * accesses/misses in hardware. + */ +static const unsigned armv7_a8_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV7_A8_PERFCTR_STALL_ISIDE, +}; + +static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + /* + * The performance counters don't differentiate between read and write + * accesses/misses so this isn't strictly correct, but it's the best we + * can do. Writes and reads get combined. + */ + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_A8_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + + [C(LL)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_A8_PERFCTR_L2_CACHE_ACCESS, + [C(LL)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_A8_PERFCTR_L2_CACHE_REFILL, + [C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_A8_PERFCTR_L2_CACHE_ACCESS, + [C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_A8_PERFCTR_L2_CACHE_REFILL, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, +}; + +/* + * Cortex-A9 HW events mapping + */ +static const unsigned armv7_a9_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_A9_PERFCTR_INSTR_CORE_RENAME, + [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = ARMV7_A9_PERFCTR_STALL_ICACHE, + [PERF_COUNT_HW_STALLED_CYCLES_BACKEND] = ARMV7_A9_PERFCTR_STALL_DISPATCH, +}; + +static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + /* + * The performance counters don't differentiate between read and write + * accesses/misses so this isn't strictly correct, but it's the best we + * can do. Writes and reads get combined. + */ + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, +}; + +/* + * Cortex-A5 HW events mapping + */ +static const unsigned armv7_a5_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, +}; + +static const unsigned armv7_a5_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV7_A5_PERFCTR_PREFETCH_LINEFILL, + [C(L1D)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP, + + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + /* + * The prefetch counters don't differentiate between the I side and the + * D side. + */ + [C(L1I)][C(OP_PREFETCH)][C(RESULT_ACCESS)] = ARMV7_A5_PERFCTR_PREFETCH_LINEFILL, + [C(L1I)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV7_A5_PERFCTR_PREFETCH_LINEFILL_DROP, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, +}; + +/* + * Cortex-A15 HW events mapping + */ +static const unsigned armv7_a15_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_A15_PERFCTR_PC_WRITE_SPEC, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_BUS_CYCLES, +}; + +static const unsigned armv7_a15_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_READ, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_READ, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_A15_PERFCTR_L1_DCACHE_ACCESS_WRITE, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_A15_PERFCTR_L1_DCACHE_REFILL_WRITE, + + /* + * Not all performance counters differentiate between read and write + * accesses/misses so we're not always strictly correct, but it's the + * best we can do. Writes and reads get combined in these cases. + */ + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + + [C(LL)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_READ, + [C(LL)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_A15_PERFCTR_L2_CACHE_REFILL_READ, + [C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_A15_PERFCTR_L2_CACHE_ACCESS_WRITE, + [C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_A15_PERFCTR_L2_CACHE_REFILL_WRITE, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_A15_PERFCTR_DTLB_REFILL_L1_READ, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_A15_PERFCTR_DTLB_REFILL_L1_WRITE, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, +}; + +/* + * Cortex-A7 HW events mapping + */ +static const unsigned armv7_a7_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_BUS_CYCLES, +}; + +static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + /* + * The performance counters don't differentiate between read and write + * accesses/misses so this isn't strictly correct, but it's the best we + * can do. Writes and reads get combined. + */ + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + + [C(LL)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_CACHE_ACCESS, + [C(LL)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, + [C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L2_CACHE_ACCESS, + [C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, +}; + +/* + * Cortex-A12 HW events mapping + */ +static const unsigned armv7_a12_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_CACHE_REFERENCES] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [PERF_COUNT_HW_CACHE_MISSES] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_A12_PERFCTR_PC_WRITE_SPEC, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_BUS_CYCLES, +}; + +static const unsigned armv7_a12_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + + /* + * Not all performance counters differentiate between read and write + * accesses/misses so we're not always strictly correct, but it's the + * best we can do. Writes and reads get combined in these cases. + */ + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_ICACHE_REFILL, + + [C(LL)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ, + [C(LL)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, + [C(LL)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE, + [C(LL)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L2_CACHE_REFILL, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_DTLB_REFILL, + [C(DTLB)][C(OP_PREFETCH)][C(RESULT_MISS)] = ARMV7_A12_PERFCTR_PF_TLB_REFILL, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_ITLB_REFILL, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, +}; + +/* + * Krait HW events mapping + */ +static const unsigned krait_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES, +}; + +static const unsigned krait_perf_map_no_branch[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES, +}; + +static const unsigned krait_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + /* + * The performance counters don't differentiate between read and write + * accesses/misses so this isn't strictly correct, but it's the best we + * can do. Writes and reads get combined. + */ + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = KRAIT_PERFCTR_L1_ICACHE_MISS, + + [C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_DTLB_ACCESS, + [C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_DTLB_ACCESS, + + [C(ITLB)][C(OP_READ)][C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_ITLB_ACCESS, + [C(ITLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = KRAIT_PERFCTR_L1_ITLB_ACCESS, + + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, +}; + +/* + * Scorpion HW events mapping + */ +static const unsigned scorpion_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = ARMV7_PERFCTR_CPU_CYCLES, + [PERF_COUNT_HW_INSTRUCTIONS] = ARMV7_PERFCTR_INSTR_EXECUTED, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE, + [PERF_COUNT_HW_BRANCH_MISSES] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [PERF_COUNT_HW_BUS_CYCLES] = ARMV7_PERFCTR_CLOCK_CYCLES, +}; + +static const unsigned scorpion_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + /* + * The performance counters don't differentiate between read and write + * accesses/misses so this isn't strictly correct, but it's the best we + * can do. Writes and reads get combined. + */ + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_L1_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_L1_DCACHE_REFILL, + [C(L1I)][C(OP_READ)][C(RESULT_ACCESS)] = SCORPION_ICACHE_ACCESS, + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = SCORPION_ICACHE_MISS, + /* + * Only ITLB misses and DTLB refills are supported. If users want the + * DTLB refills misses a raw counter must be used. + */ + [C(DTLB)][C(OP_READ)][C(RESULT_ACCESS)] = SCORPION_DTLB_ACCESS, + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = SCORPION_DTLB_MISS, + [C(DTLB)][C(OP_WRITE)][C(RESULT_ACCESS)] = SCORPION_DTLB_ACCESS, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = SCORPION_DTLB_MISS, + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = SCORPION_ITLB_MISS, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = SCORPION_ITLB_MISS, + [C(BPU)][C(OP_READ)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_READ)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_ACCESS)] = ARMV7_PERFCTR_PC_BRANCH_PRED, + [C(BPU)][C(OP_WRITE)][C(RESULT_MISS)] = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED, +}; + +PMU_FORMAT_ATTR(event, "config:0-7"); + +static struct attribute *armv7_pmu_format_attrs[] = { + &format_attr_event.attr, + NULL, +}; + +static struct attribute_group armv7_pmu_format_attr_group = { + .name = "format", + .attrs = armv7_pmu_format_attrs, +}; + +#define ARMV7_EVENT_ATTR_RESOLVE(m) #m +#define ARMV7_EVENT_ATTR(name, config) \ + PMU_EVENT_ATTR_STRING(name, armv7_event_attr_##name, \ + "event=" ARMV7_EVENT_ATTR_RESOLVE(config)) + +ARMV7_EVENT_ATTR(sw_incr, ARMV7_PERFCTR_PMNC_SW_INCR); +ARMV7_EVENT_ATTR(l1i_cache_refill, ARMV7_PERFCTR_L1_ICACHE_REFILL); +ARMV7_EVENT_ATTR(l1i_tlb_refill, ARMV7_PERFCTR_ITLB_REFILL); +ARMV7_EVENT_ATTR(l1d_cache_refill, ARMV7_PERFCTR_L1_DCACHE_REFILL); +ARMV7_EVENT_ATTR(l1d_cache, ARMV7_PERFCTR_L1_DCACHE_ACCESS); +ARMV7_EVENT_ATTR(l1d_tlb_refill, ARMV7_PERFCTR_DTLB_REFILL); +ARMV7_EVENT_ATTR(ld_retired, ARMV7_PERFCTR_MEM_READ); +ARMV7_EVENT_ATTR(st_retired, ARMV7_PERFCTR_MEM_WRITE); +ARMV7_EVENT_ATTR(inst_retired, ARMV7_PERFCTR_INSTR_EXECUTED); +ARMV7_EVENT_ATTR(exc_taken, ARMV7_PERFCTR_EXC_TAKEN); +ARMV7_EVENT_ATTR(exc_return, ARMV7_PERFCTR_EXC_EXECUTED); +ARMV7_EVENT_ATTR(cid_write_retired, ARMV7_PERFCTR_CID_WRITE); +ARMV7_EVENT_ATTR(pc_write_retired, ARMV7_PERFCTR_PC_WRITE); +ARMV7_EVENT_ATTR(br_immed_retired, ARMV7_PERFCTR_PC_IMM_BRANCH); +ARMV7_EVENT_ATTR(br_return_retired, ARMV7_PERFCTR_PC_PROC_RETURN); +ARMV7_EVENT_ATTR(unaligned_ldst_retired, ARMV7_PERFCTR_MEM_UNALIGNED_ACCESS); +ARMV7_EVENT_ATTR(br_mis_pred, ARMV7_PERFCTR_PC_BRANCH_MIS_PRED); +ARMV7_EVENT_ATTR(cpu_cycles, ARMV7_PERFCTR_CLOCK_CYCLES); +ARMV7_EVENT_ATTR(br_pred, ARMV7_PERFCTR_PC_BRANCH_PRED); + +static struct attribute *armv7_pmuv1_event_attrs[] = { + &armv7_event_attr_sw_incr.attr.attr, + &armv7_event_attr_l1i_cache_refill.attr.attr, + &armv7_event_attr_l1i_tlb_refill.attr.attr, + &armv7_event_attr_l1d_cache_refill.attr.attr, + &armv7_event_attr_l1d_cache.attr.attr, + &armv7_event_attr_l1d_tlb_refill.attr.attr, + &armv7_event_attr_ld_retired.attr.attr, + &armv7_event_attr_st_retired.attr.attr, + &armv7_event_attr_inst_retired.attr.attr, + &armv7_event_attr_exc_taken.attr.attr, + &armv7_event_attr_exc_return.attr.attr, + &armv7_event_attr_cid_write_retired.attr.attr, + &armv7_event_attr_pc_write_retired.attr.attr, + &armv7_event_attr_br_immed_retired.attr.attr, + &armv7_event_attr_br_return_retired.attr.attr, + &armv7_event_attr_unaligned_ldst_retired.attr.attr, + &armv7_event_attr_br_mis_pred.attr.attr, + &armv7_event_attr_cpu_cycles.attr.attr, + &armv7_event_attr_br_pred.attr.attr, + NULL, +}; + +static struct attribute_group armv7_pmuv1_events_attr_group = { + .name = "events", + .attrs = armv7_pmuv1_event_attrs, +}; + +ARMV7_EVENT_ATTR(mem_access, ARMV7_PERFCTR_MEM_ACCESS); +ARMV7_EVENT_ATTR(l1i_cache, ARMV7_PERFCTR_L1_ICACHE_ACCESS); +ARMV7_EVENT_ATTR(l1d_cache_wb, ARMV7_PERFCTR_L1_DCACHE_WB); +ARMV7_EVENT_ATTR(l2d_cache, ARMV7_PERFCTR_L2_CACHE_ACCESS); +ARMV7_EVENT_ATTR(l2d_cache_refill, ARMV7_PERFCTR_L2_CACHE_REFILL); +ARMV7_EVENT_ATTR(l2d_cache_wb, ARMV7_PERFCTR_L2_CACHE_WB); +ARMV7_EVENT_ATTR(bus_access, ARMV7_PERFCTR_BUS_ACCESS); +ARMV7_EVENT_ATTR(memory_error, ARMV7_PERFCTR_MEM_ERROR); +ARMV7_EVENT_ATTR(inst_spec, ARMV7_PERFCTR_INSTR_SPEC); +ARMV7_EVENT_ATTR(ttbr_write_retired, ARMV7_PERFCTR_TTBR_WRITE); +ARMV7_EVENT_ATTR(bus_cycles, ARMV7_PERFCTR_BUS_CYCLES); + +static struct attribute *armv7_pmuv2_event_attrs[] = { + &armv7_event_attr_sw_incr.attr.attr, + &armv7_event_attr_l1i_cache_refill.attr.attr, + &armv7_event_attr_l1i_tlb_refill.attr.attr, + &armv7_event_attr_l1d_cache_refill.attr.attr, + &armv7_event_attr_l1d_cache.attr.attr, + &armv7_event_attr_l1d_tlb_refill.attr.attr, + &armv7_event_attr_ld_retired.attr.attr, + &armv7_event_attr_st_retired.attr.attr, + &armv7_event_attr_inst_retired.attr.attr, + &armv7_event_attr_exc_taken.attr.attr, + &armv7_event_attr_exc_return.attr.attr, + &armv7_event_attr_cid_write_retired.attr.attr, + &armv7_event_attr_pc_write_retired.attr.attr, + &armv7_event_attr_br_immed_retired.attr.attr, + &armv7_event_attr_br_return_retired.attr.attr, + &armv7_event_attr_unaligned_ldst_retired.attr.attr, + &armv7_event_attr_br_mis_pred.attr.attr, + &armv7_event_attr_cpu_cycles.attr.attr, + &armv7_event_attr_br_pred.attr.attr, + &armv7_event_attr_mem_access.attr.attr, + &armv7_event_attr_l1i_cache.attr.attr, + &armv7_event_attr_l1d_cache_wb.attr.attr, + &armv7_event_attr_l2d_cache.attr.attr, + &armv7_event_attr_l2d_cache_refill.attr.attr, + &armv7_event_attr_l2d_cache_wb.attr.attr, + &armv7_event_attr_bus_access.attr.attr, + &armv7_event_attr_memory_error.attr.attr, + &armv7_event_attr_inst_spec.attr.attr, + &armv7_event_attr_ttbr_write_retired.attr.attr, + &armv7_event_attr_bus_cycles.attr.attr, + NULL, +}; + +static struct attribute_group armv7_pmuv2_events_attr_group = { + .name = "events", + .attrs = armv7_pmuv2_event_attrs, +}; + +/* + * Perf Events' indices + */ +#define ARMV7_IDX_CYCLE_COUNTER 0 +#define ARMV7_IDX_COUNTER0 1 +#define ARMV7_IDX_COUNTER_LAST(cpu_pmu) \ + (ARMV7_IDX_CYCLE_COUNTER + cpu_pmu->num_events - 1) + +#define ARMV7_MAX_COUNTERS 32 +#define ARMV7_COUNTER_MASK (ARMV7_MAX_COUNTERS - 1) + +/* + * ARMv7 low level PMNC access + */ + +/* + * Perf Event to low level counters mapping + */ +#define ARMV7_IDX_TO_COUNTER(x) \ + (((x) - ARMV7_IDX_COUNTER0) & ARMV7_COUNTER_MASK) + +/* + * Per-CPU PMNC: config reg + */ +#define ARMV7_PMNC_E (1 << 0) /* Enable all counters */ +#define ARMV7_PMNC_P (1 << 1) /* Reset all counters */ +#define ARMV7_PMNC_C (1 << 2) /* Cycle counter reset */ +#define ARMV7_PMNC_D (1 << 3) /* CCNT counts every 64th cpu cycle */ +#define ARMV7_PMNC_X (1 << 4) /* Export to ETM */ +#define ARMV7_PMNC_DP (1 << 5) /* Disable CCNT if non-invasive debug*/ +#define ARMV7_PMNC_N_SHIFT 11 /* Number of counters supported */ +#define ARMV7_PMNC_N_MASK 0x1f +#define ARMV7_PMNC_MASK 0x3f /* Mask for writable bits */ + +/* + * FLAG: counters overflow flag status reg + */ +#define ARMV7_FLAG_MASK 0xffffffff /* Mask for writable bits */ +#define ARMV7_OVERFLOWED_MASK ARMV7_FLAG_MASK + +/* + * PMXEVTYPER: Event selection reg + */ +#define ARMV7_EVTYPE_MASK 0xc80000ff /* Mask for writable bits */ +#define ARMV7_EVTYPE_EVENT 0xff /* Mask for EVENT bits */ + +/* + * Event filters for PMUv2 + */ +#define ARMV7_EXCLUDE_PL1 BIT(31) +#define ARMV7_EXCLUDE_USER BIT(30) +#define ARMV7_INCLUDE_HYP BIT(27) + +/* + * Secure debug enable reg + */ +#define ARMV7_SDER_SUNIDEN BIT(1) /* Permit non-invasive debug */ + +static inline u32 armv7_pmnc_read(void) +{ + u32 val; + asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r"(val)); + return val; +} + +static inline void armv7_pmnc_write(u32 val) +{ + val &= ARMV7_PMNC_MASK; + isb(); + asm volatile("mcr p15, 0, %0, c9, c12, 0" : : "r"(val)); +} + +static inline int armv7_pmnc_has_overflowed(u32 pmnc) +{ + return pmnc & ARMV7_OVERFLOWED_MASK; +} + +static inline int armv7_pmnc_counter_valid(struct arm_pmu *cpu_pmu, int idx) +{ + return idx >= ARMV7_IDX_CYCLE_COUNTER && + idx <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); +} + +static inline int armv7_pmnc_counter_has_overflowed(u32 pmnc, int idx) +{ + return pmnc & BIT(ARMV7_IDX_TO_COUNTER(idx)); +} + +static inline void armv7_pmnc_select_counter(int idx) +{ + u32 counter = ARMV7_IDX_TO_COUNTER(idx); + asm volatile("mcr p15, 0, %0, c9, c12, 5" : : "r" (counter)); + isb(); +} + +static inline u64 armv7pmu_read_counter(struct perf_event *event) +{ + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + u32 value = 0; + + if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) { + pr_err("CPU%u reading wrong counter %d\n", + smp_processor_id(), idx); + } else if (idx == ARMV7_IDX_CYCLE_COUNTER) { + asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (value)); + } else { + armv7_pmnc_select_counter(idx); + asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (value)); + } + + return value; +} + +static inline void armv7pmu_write_counter(struct perf_event *event, u64 value) +{ + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + + if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) { + pr_err("CPU%u writing wrong counter %d\n", + smp_processor_id(), idx); + } else if (idx == ARMV7_IDX_CYCLE_COUNTER) { + asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" ((u32)value)); + } else { + armv7_pmnc_select_counter(idx); + asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" ((u32)value)); + } +} + +static inline void armv7_pmnc_write_evtsel(int idx, u32 val) +{ + armv7_pmnc_select_counter(idx); + val &= ARMV7_EVTYPE_MASK; + asm volatile("mcr p15, 0, %0, c9, c13, 1" : : "r" (val)); +} + +static inline void armv7_pmnc_enable_counter(int idx) +{ + u32 counter = ARMV7_IDX_TO_COUNTER(idx); + asm volatile("mcr p15, 0, %0, c9, c12, 1" : : "r" (BIT(counter))); +} + +static inline void armv7_pmnc_disable_counter(int idx) +{ + u32 counter = ARMV7_IDX_TO_COUNTER(idx); + asm volatile("mcr p15, 0, %0, c9, c12, 2" : : "r" (BIT(counter))); +} + +static inline void armv7_pmnc_enable_intens(int idx) +{ + u32 counter = ARMV7_IDX_TO_COUNTER(idx); + asm volatile("mcr p15, 0, %0, c9, c14, 1" : : "r" (BIT(counter))); +} + +static inline void armv7_pmnc_disable_intens(int idx) +{ + u32 counter = ARMV7_IDX_TO_COUNTER(idx); + asm volatile("mcr p15, 0, %0, c9, c14, 2" : : "r" (BIT(counter))); + isb(); + /* Clear the overflow flag in case an interrupt is pending. */ + asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (BIT(counter))); + isb(); +} + +static inline u32 armv7_pmnc_getreset_flags(void) +{ + u32 val; + + /* Read */ + asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val)); + + /* Write to clear flags */ + val &= ARMV7_FLAG_MASK; + asm volatile("mcr p15, 0, %0, c9, c12, 3" : : "r" (val)); + + return val; +} + +#ifdef DEBUG +static void armv7_pmnc_dump_regs(struct arm_pmu *cpu_pmu) +{ + u32 val; + unsigned int cnt; + + pr_info("PMNC registers dump:\n"); + + asm volatile("mrc p15, 0, %0, c9, c12, 0" : "=r" (val)); + pr_info("PMNC =0x%08x\n", val); + + asm volatile("mrc p15, 0, %0, c9, c12, 1" : "=r" (val)); + pr_info("CNTENS=0x%08x\n", val); + + asm volatile("mrc p15, 0, %0, c9, c14, 1" : "=r" (val)); + pr_info("INTENS=0x%08x\n", val); + + asm volatile("mrc p15, 0, %0, c9, c12, 3" : "=r" (val)); + pr_info("FLAGS =0x%08x\n", val); + + asm volatile("mrc p15, 0, %0, c9, c12, 5" : "=r" (val)); + pr_info("SELECT=0x%08x\n", val); + + asm volatile("mrc p15, 0, %0, c9, c13, 0" : "=r" (val)); + pr_info("CCNT =0x%08x\n", val); + + for (cnt = ARMV7_IDX_COUNTER0; + cnt <= ARMV7_IDX_COUNTER_LAST(cpu_pmu); cnt++) { + armv7_pmnc_select_counter(cnt); + asm volatile("mrc p15, 0, %0, c9, c13, 2" : "=r" (val)); + pr_info("CNT[%d] count =0x%08x\n", + ARMV7_IDX_TO_COUNTER(cnt), val); + asm volatile("mrc p15, 0, %0, c9, c13, 1" : "=r" (val)); + pr_info("CNT[%d] evtsel=0x%08x\n", + ARMV7_IDX_TO_COUNTER(cnt), val); + } +} +#endif + +static void armv7pmu_enable_event(struct perf_event *event) +{ + unsigned long flags; + struct hw_perf_event *hwc = &event->hw; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx = hwc->idx; + + if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) { + pr_err("CPU%u enabling wrong PMNC counter IRQ enable %d\n", + smp_processor_id(), idx); + return; + } + + /* + * Enable counter and interrupt, and set the counter to count + * the event that we're interested in. + */ + raw_spin_lock_irqsave(&events->pmu_lock, flags); + + /* + * Disable counter + */ + armv7_pmnc_disable_counter(idx); + + /* + * Set event (if destined for PMNx counters) + * We only need to set the event for the cycle counter if we + * have the ability to perform event filtering. + */ + if (cpu_pmu->set_event_filter || idx != ARMV7_IDX_CYCLE_COUNTER) + armv7_pmnc_write_evtsel(idx, hwc->config_base); + + /* + * Enable interrupt for this counter + */ + armv7_pmnc_enable_intens(idx); + + /* + * Enable counter + */ + armv7_pmnc_enable_counter(idx); + + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void armv7pmu_disable_event(struct perf_event *event) +{ + unsigned long flags; + struct hw_perf_event *hwc = &event->hw; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx = hwc->idx; + + if (!armv7_pmnc_counter_valid(cpu_pmu, idx)) { + pr_err("CPU%u disabling wrong PMNC counter IRQ enable %d\n", + smp_processor_id(), idx); + return; + } + + /* + * Disable counter and interrupt + */ + raw_spin_lock_irqsave(&events->pmu_lock, flags); + + /* + * Disable counter + */ + armv7_pmnc_disable_counter(idx); + + /* + * Disable interrupt for this counter + */ + armv7_pmnc_disable_intens(idx); + + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static irqreturn_t armv7pmu_handle_irq(struct arm_pmu *cpu_pmu) +{ + u32 pmnc; + struct perf_sample_data data; + struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events); + struct pt_regs *regs; + int idx; + + /* + * Get and reset the IRQ flags + */ + pmnc = armv7_pmnc_getreset_flags(); + + /* + * Did an overflow occur? + */ + if (!armv7_pmnc_has_overflowed(pmnc)) + return IRQ_NONE; + + /* + * Handle the counter(s) overflow(s) + */ + regs = get_irq_regs(); + + for (idx = 0; idx < cpu_pmu->num_events; ++idx) { + struct perf_event *event = cpuc->events[idx]; + struct hw_perf_event *hwc; + + /* Ignore if we don't have an event. */ + if (!event) + continue; + + /* + * We have a single interrupt for all counters. Check that + * each counter has overflowed before we process it. + */ + if (!armv7_pmnc_counter_has_overflowed(pmnc, idx)) + continue; + + hwc = &event->hw; + armpmu_event_update(event); + perf_sample_data_init(&data, 0, hwc->last_period); + if (!armpmu_event_set_period(event)) + continue; + + if (perf_event_overflow(event, &data, regs)) + cpu_pmu->disable(event); + } + + /* + * Handle the pending perf events. + * + * Note: this call *must* be run with interrupts disabled. For + * platforms that can have the PMU interrupts raised as an NMI, this + * will not work. + */ + irq_work_run(); + + return IRQ_HANDLED; +} + +static void armv7pmu_start(struct arm_pmu *cpu_pmu) +{ + unsigned long flags; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + /* Enable all counters */ + armv7_pmnc_write(armv7_pmnc_read() | ARMV7_PMNC_E); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void armv7pmu_stop(struct arm_pmu *cpu_pmu) +{ + unsigned long flags; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + /* Disable all counters */ + armv7_pmnc_write(armv7_pmnc_read() & ~ARMV7_PMNC_E); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static int armv7pmu_get_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + int idx; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + unsigned long evtype = hwc->config_base & ARMV7_EVTYPE_EVENT; + + /* Always place a cycle counter into the cycle counter. */ + if (evtype == ARMV7_PERFCTR_CPU_CYCLES) { + if (test_and_set_bit(ARMV7_IDX_CYCLE_COUNTER, cpuc->used_mask)) + return -EAGAIN; + + return ARMV7_IDX_CYCLE_COUNTER; + } + + /* + * For anything other than a cycle counter, try and use + * the events counters + */ + for (idx = ARMV7_IDX_COUNTER0; idx < cpu_pmu->num_events; ++idx) { + if (!test_and_set_bit(idx, cpuc->used_mask)) + return idx; + } + + /* The counters are all in use. */ + return -EAGAIN; +} + +static void armv7pmu_clear_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + clear_bit(event->hw.idx, cpuc->used_mask); +} + +/* + * Add an event filter to a given event. This will only work for PMUv2 PMUs. + */ +static int armv7pmu_set_event_filter(struct hw_perf_event *event, + struct perf_event_attr *attr) +{ + unsigned long config_base = 0; + + if (attr->exclude_idle) + return -EPERM; + if (attr->exclude_user) + config_base |= ARMV7_EXCLUDE_USER; + if (attr->exclude_kernel) + config_base |= ARMV7_EXCLUDE_PL1; + if (!attr->exclude_hv) + config_base |= ARMV7_INCLUDE_HYP; + + /* + * Install the filter into config_base as this is used to + * construct the event type. + */ + event->config_base = config_base; + + return 0; +} + +static void armv7pmu_reset(void *info) +{ + struct arm_pmu *cpu_pmu = (struct arm_pmu *)info; + u32 idx, nb_cnt = cpu_pmu->num_events, val; + + if (cpu_pmu->secure_access) { + asm volatile("mrc p15, 0, %0, c1, c1, 1" : "=r" (val)); + val |= ARMV7_SDER_SUNIDEN; + asm volatile("mcr p15, 0, %0, c1, c1, 1" : : "r" (val)); + } + + /* The counter and interrupt enable registers are unknown at reset. */ + for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) { + armv7_pmnc_disable_counter(idx); + armv7_pmnc_disable_intens(idx); + } + + /* Initialize & Reset PMNC: C and P bits */ + armv7_pmnc_write(ARMV7_PMNC_P | ARMV7_PMNC_C); +} + +static int armv7_a8_map_event(struct perf_event *event) +{ + return armpmu_map_event(event, &armv7_a8_perf_map, + &armv7_a8_perf_cache_map, 0xFF); +} + +static int armv7_a9_map_event(struct perf_event *event) +{ + return armpmu_map_event(event, &armv7_a9_perf_map, + &armv7_a9_perf_cache_map, 0xFF); +} + +static int armv7_a5_map_event(struct perf_event *event) +{ + return armpmu_map_event(event, &armv7_a5_perf_map, + &armv7_a5_perf_cache_map, 0xFF); +} + +static int armv7_a15_map_event(struct perf_event *event) +{ + return armpmu_map_event(event, &armv7_a15_perf_map, + &armv7_a15_perf_cache_map, 0xFF); +} + +static int armv7_a7_map_event(struct perf_event *event) +{ + return armpmu_map_event(event, &armv7_a7_perf_map, + &armv7_a7_perf_cache_map, 0xFF); +} + +static int armv7_a12_map_event(struct perf_event *event) +{ + return armpmu_map_event(event, &armv7_a12_perf_map, + &armv7_a12_perf_cache_map, 0xFF); +} + +static int krait_map_event(struct perf_event *event) +{ + return armpmu_map_event(event, &krait_perf_map, + &krait_perf_cache_map, 0xFFFFF); +} + +static int krait_map_event_no_branch(struct perf_event *event) +{ + return armpmu_map_event(event, &krait_perf_map_no_branch, + &krait_perf_cache_map, 0xFFFFF); +} + +static int scorpion_map_event(struct perf_event *event) +{ + return armpmu_map_event(event, &scorpion_perf_map, + &scorpion_perf_cache_map, 0xFFFFF); +} + +static void armv7pmu_init(struct arm_pmu *cpu_pmu) +{ + cpu_pmu->handle_irq = armv7pmu_handle_irq; + cpu_pmu->enable = armv7pmu_enable_event; + cpu_pmu->disable = armv7pmu_disable_event; + cpu_pmu->read_counter = armv7pmu_read_counter; + cpu_pmu->write_counter = armv7pmu_write_counter; + cpu_pmu->get_event_idx = armv7pmu_get_event_idx; + cpu_pmu->clear_event_idx = armv7pmu_clear_event_idx; + cpu_pmu->start = armv7pmu_start; + cpu_pmu->stop = armv7pmu_stop; + cpu_pmu->reset = armv7pmu_reset; +}; + +static void armv7_read_num_pmnc_events(void *info) +{ + int *nb_cnt = info; + + /* Read the nb of CNTx counters supported from PMNC */ + *nb_cnt = (armv7_pmnc_read() >> ARMV7_PMNC_N_SHIFT) & ARMV7_PMNC_N_MASK; + + /* Add the CPU cycles counter */ + *nb_cnt += 1; +} + +static int armv7_probe_num_events(struct arm_pmu *arm_pmu) +{ + return smp_call_function_any(&arm_pmu->supported_cpus, + armv7_read_num_pmnc_events, + &arm_pmu->num_events, 1); +} + +static int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv7pmu_init(cpu_pmu); + cpu_pmu->name = "armv7_cortex_a8"; + cpu_pmu->map_event = armv7_a8_map_event; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv1_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; + return armv7_probe_num_events(cpu_pmu); +} + +static int armv7_a9_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv7pmu_init(cpu_pmu); + cpu_pmu->name = "armv7_cortex_a9"; + cpu_pmu->map_event = armv7_a9_map_event; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv1_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; + return armv7_probe_num_events(cpu_pmu); +} + +static int armv7_a5_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv7pmu_init(cpu_pmu); + cpu_pmu->name = "armv7_cortex_a5"; + cpu_pmu->map_event = armv7_a5_map_event; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv1_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; + return armv7_probe_num_events(cpu_pmu); +} + +static int armv7_a15_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv7pmu_init(cpu_pmu); + cpu_pmu->name = "armv7_cortex_a15"; + cpu_pmu->map_event = armv7_a15_map_event; + cpu_pmu->set_event_filter = armv7pmu_set_event_filter; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv2_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; + return armv7_probe_num_events(cpu_pmu); +} + +static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv7pmu_init(cpu_pmu); + cpu_pmu->name = "armv7_cortex_a7"; + cpu_pmu->map_event = armv7_a7_map_event; + cpu_pmu->set_event_filter = armv7pmu_set_event_filter; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv2_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; + return armv7_probe_num_events(cpu_pmu); +} + +static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv7pmu_init(cpu_pmu); + cpu_pmu->name = "armv7_cortex_a12"; + cpu_pmu->map_event = armv7_a12_map_event; + cpu_pmu->set_event_filter = armv7pmu_set_event_filter; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv2_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; + return armv7_probe_num_events(cpu_pmu); +} + +static int armv7_a17_pmu_init(struct arm_pmu *cpu_pmu) +{ + int ret = armv7_a12_pmu_init(cpu_pmu); + cpu_pmu->name = "armv7_cortex_a17"; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = + &armv7_pmuv2_events_attr_group; + cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = + &armv7_pmu_format_attr_group; + return ret; +} + +/* + * Krait Performance Monitor Region Event Selection Register (PMRESRn) + * + * 31 30 24 16 8 0 + * +--------------------------------+ + * PMRESR0 | EN | CC | CC | CC | CC | N = 1, R = 0 + * +--------------------------------+ + * PMRESR1 | EN | CC | CC | CC | CC | N = 1, R = 1 + * +--------------------------------+ + * PMRESR2 | EN | CC | CC | CC | CC | N = 1, R = 2 + * +--------------------------------+ + * VPMRESR0 | EN | CC | CC | CC | CC | N = 2, R = ? + * +--------------------------------+ + * EN | G=3 | G=2 | G=1 | G=0 + * + * Event Encoding: + * + * hwc->config_base = 0xNRCCG + * + * N = prefix, 1 for Krait CPU (PMRESRn), 2 for Venum VFP (VPMRESR) + * R = region register + * CC = class of events the group G is choosing from + * G = group or particular event + * + * Example: 0x12021 is a Krait CPU event in PMRESR2's group 1 with code 2 + * + * A region (R) corresponds to a piece of the CPU (execution unit, instruction + * unit, etc.) while the event code (CC) corresponds to a particular class of + * events (interrupts for example). An event code is broken down into + * groups (G) that can be mapped into the PMU (irq, fiqs, and irq+fiqs for + * example). + */ + +#define KRAIT_EVENT (1 << 16) +#define VENUM_EVENT (2 << 16) +#define KRAIT_EVENT_MASK (KRAIT_EVENT | VENUM_EVENT) +#define PMRESRn_EN BIT(31) + +#define EVENT_REGION(event) (((event) >> 12) & 0xf) /* R */ +#define EVENT_GROUP(event) ((event) & 0xf) /* G */ +#define EVENT_CODE(event) (((event) >> 4) & 0xff) /* CC */ +#define EVENT_VENUM(event) (!!(event & VENUM_EVENT)) /* N=2 */ +#define EVENT_CPU(event) (!!(event & KRAIT_EVENT)) /* N=1 */ + +static u32 krait_read_pmresrn(int n) +{ + u32 val; + + switch (n) { + case 0: + asm volatile("mrc p15, 1, %0, c9, c15, 0" : "=r" (val)); + break; + case 1: + asm volatile("mrc p15, 1, %0, c9, c15, 1" : "=r" (val)); + break; + case 2: + asm volatile("mrc p15, 1, %0, c9, c15, 2" : "=r" (val)); + break; + default: + BUG(); /* Should be validated in krait_pmu_get_event_idx() */ + } + + return val; +} + +static void krait_write_pmresrn(int n, u32 val) +{ + switch (n) { + case 0: + asm volatile("mcr p15, 1, %0, c9, c15, 0" : : "r" (val)); + break; + case 1: + asm volatile("mcr p15, 1, %0, c9, c15, 1" : : "r" (val)); + break; + case 2: + asm volatile("mcr p15, 1, %0, c9, c15, 2" : : "r" (val)); + break; + default: + BUG(); /* Should be validated in krait_pmu_get_event_idx() */ + } +} + +static u32 venum_read_pmresr(void) +{ + u32 val; + asm volatile("mrc p10, 7, %0, c11, c0, 0" : "=r" (val)); + return val; +} + +static void venum_write_pmresr(u32 val) +{ + asm volatile("mcr p10, 7, %0, c11, c0, 0" : : "r" (val)); +} + +static void venum_pre_pmresr(u32 *venum_orig_val, u32 *fp_orig_val) +{ + u32 venum_new_val; + u32 fp_new_val; + + BUG_ON(preemptible()); + /* CPACR Enable CP10 and CP11 access */ + *venum_orig_val = get_copro_access(); + venum_new_val = *venum_orig_val | CPACC_SVC(10) | CPACC_SVC(11); + set_copro_access(venum_new_val); + + /* Enable FPEXC */ + *fp_orig_val = fmrx(FPEXC); + fp_new_val = *fp_orig_val | FPEXC_EN; + fmxr(FPEXC, fp_new_val); +} + +static void venum_post_pmresr(u32 venum_orig_val, u32 fp_orig_val) +{ + BUG_ON(preemptible()); + /* Restore FPEXC */ + fmxr(FPEXC, fp_orig_val); + isb(); + /* Restore CPACR */ + set_copro_access(venum_orig_val); +} + +static u32 krait_get_pmresrn_event(unsigned int region) +{ + static const u32 pmresrn_table[] = { KRAIT_PMRESR0_GROUP0, + KRAIT_PMRESR1_GROUP0, + KRAIT_PMRESR2_GROUP0 }; + return pmresrn_table[region]; +} + +static void krait_evt_setup(int idx, u32 config_base) +{ + u32 val; + u32 mask; + u32 vval, fval; + unsigned int region = EVENT_REGION(config_base); + unsigned int group = EVENT_GROUP(config_base); + unsigned int code = EVENT_CODE(config_base); + unsigned int group_shift; + bool venum_event = EVENT_VENUM(config_base); + + group_shift = group * 8; + mask = 0xff << group_shift; + + /* Configure evtsel for the region and group */ + if (venum_event) + val = KRAIT_VPMRESR0_GROUP0; + else + val = krait_get_pmresrn_event(region); + val += group; + /* Mix in mode-exclusion bits */ + val |= config_base & (ARMV7_EXCLUDE_USER | ARMV7_EXCLUDE_PL1); + armv7_pmnc_write_evtsel(idx, val); + + if (venum_event) { + venum_pre_pmresr(&vval, &fval); + val = venum_read_pmresr(); + val &= ~mask; + val |= code << group_shift; + val |= PMRESRn_EN; + venum_write_pmresr(val); + venum_post_pmresr(vval, fval); + } else { + val = krait_read_pmresrn(region); + val &= ~mask; + val |= code << group_shift; + val |= PMRESRn_EN; + krait_write_pmresrn(region, val); + } +} + +static u32 clear_pmresrn_group(u32 val, int group) +{ + u32 mask; + int group_shift; + + group_shift = group * 8; + mask = 0xff << group_shift; + val &= ~mask; + + /* Don't clear enable bit if entire region isn't disabled */ + if (val & ~PMRESRn_EN) + return val |= PMRESRn_EN; + + return 0; +} + +static void krait_clearpmu(u32 config_base) +{ + u32 val; + u32 vval, fval; + unsigned int region = EVENT_REGION(config_base); + unsigned int group = EVENT_GROUP(config_base); + bool venum_event = EVENT_VENUM(config_base); + + if (venum_event) { + venum_pre_pmresr(&vval, &fval); + val = venum_read_pmresr(); + val = clear_pmresrn_group(val, group); + venum_write_pmresr(val); + venum_post_pmresr(vval, fval); + } else { + val = krait_read_pmresrn(region); + val = clear_pmresrn_group(val, group); + krait_write_pmresrn(region, val); + } +} + +static void krait_pmu_disable_event(struct perf_event *event) +{ + unsigned long flags; + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + /* Disable counter and interrupt */ + raw_spin_lock_irqsave(&events->pmu_lock, flags); + + /* Disable counter */ + armv7_pmnc_disable_counter(idx); + + /* + * Clear pmresr code (if destined for PMNx counters) + */ + if (hwc->config_base & KRAIT_EVENT_MASK) + krait_clearpmu(hwc->config_base); + + /* Disable interrupt for this counter */ + armv7_pmnc_disable_intens(idx); + + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void krait_pmu_enable_event(struct perf_event *event) +{ + unsigned long flags; + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + /* + * Enable counter and interrupt, and set the counter to count + * the event that we're interested in. + */ + raw_spin_lock_irqsave(&events->pmu_lock, flags); + + /* Disable counter */ + armv7_pmnc_disable_counter(idx); + + /* + * Set event (if destined for PMNx counters) + * We set the event for the cycle counter because we + * have the ability to perform event filtering. + */ + if (hwc->config_base & KRAIT_EVENT_MASK) + krait_evt_setup(idx, hwc->config_base); + else + armv7_pmnc_write_evtsel(idx, hwc->config_base); + + /* Enable interrupt for this counter */ + armv7_pmnc_enable_intens(idx); + + /* Enable counter */ + armv7_pmnc_enable_counter(idx); + + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void krait_pmu_reset(void *info) +{ + u32 vval, fval; + struct arm_pmu *cpu_pmu = info; + u32 idx, nb_cnt = cpu_pmu->num_events; + + armv7pmu_reset(info); + + /* Clear all pmresrs */ + krait_write_pmresrn(0, 0); + krait_write_pmresrn(1, 0); + krait_write_pmresrn(2, 0); + + venum_pre_pmresr(&vval, &fval); + venum_write_pmresr(0); + venum_post_pmresr(vval, fval); + + /* Reset PMxEVNCTCR to sane default */ + for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) { + armv7_pmnc_select_counter(idx); + asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0)); + } + +} + +static int krait_event_to_bit(struct perf_event *event, unsigned int region, + unsigned int group) +{ + int bit; + struct hw_perf_event *hwc = &event->hw; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + + if (hwc->config_base & VENUM_EVENT) + bit = KRAIT_VPMRESR0_GROUP0; + else + bit = krait_get_pmresrn_event(region); + bit -= krait_get_pmresrn_event(0); + bit += group; + /* + * Lower bits are reserved for use by the counters (see + * armv7pmu_get_event_idx() for more info) + */ + bit += ARMV7_IDX_COUNTER_LAST(cpu_pmu) + 1; + + return bit; +} + +/* + * We check for column exclusion constraints here. + * Two events cant use the same group within a pmresr register. + */ +static int krait_pmu_get_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + int idx; + int bit = -1; + struct hw_perf_event *hwc = &event->hw; + unsigned int region = EVENT_REGION(hwc->config_base); + unsigned int code = EVENT_CODE(hwc->config_base); + unsigned int group = EVENT_GROUP(hwc->config_base); + bool venum_event = EVENT_VENUM(hwc->config_base); + bool krait_event = EVENT_CPU(hwc->config_base); + + if (venum_event || krait_event) { + /* Ignore invalid events */ + if (group > 3 || region > 2) + return -EINVAL; + if (venum_event && (code & 0xe0)) + return -EINVAL; + + bit = krait_event_to_bit(event, region, group); + if (test_and_set_bit(bit, cpuc->used_mask)) + return -EAGAIN; + } + + idx = armv7pmu_get_event_idx(cpuc, event); + if (idx < 0 && bit >= 0) + clear_bit(bit, cpuc->used_mask); + + return idx; +} + +static void krait_pmu_clear_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + int bit; + struct hw_perf_event *hwc = &event->hw; + unsigned int region = EVENT_REGION(hwc->config_base); + unsigned int group = EVENT_GROUP(hwc->config_base); + bool venum_event = EVENT_VENUM(hwc->config_base); + bool krait_event = EVENT_CPU(hwc->config_base); + + armv7pmu_clear_event_idx(cpuc, event); + if (venum_event || krait_event) { + bit = krait_event_to_bit(event, region, group); + clear_bit(bit, cpuc->used_mask); + } +} + +static int krait_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv7pmu_init(cpu_pmu); + cpu_pmu->name = "armv7_krait"; + /* Some early versions of Krait don't support PC write events */ + if (of_property_read_bool(cpu_pmu->plat_device->dev.of_node, + "qcom,no-pc-write")) + cpu_pmu->map_event = krait_map_event_no_branch; + else + cpu_pmu->map_event = krait_map_event; + cpu_pmu->set_event_filter = armv7pmu_set_event_filter; + cpu_pmu->reset = krait_pmu_reset; + cpu_pmu->enable = krait_pmu_enable_event; + cpu_pmu->disable = krait_pmu_disable_event; + cpu_pmu->get_event_idx = krait_pmu_get_event_idx; + cpu_pmu->clear_event_idx = krait_pmu_clear_event_idx; + return armv7_probe_num_events(cpu_pmu); +} + +/* + * Scorpion Local Performance Monitor Register (LPMn) + * + * 31 30 24 16 8 0 + * +--------------------------------+ + * LPM0 | EN | CC | CC | CC | CC | N = 1, R = 0 + * +--------------------------------+ + * LPM1 | EN | CC | CC | CC | CC | N = 1, R = 1 + * +--------------------------------+ + * LPM2 | EN | CC | CC | CC | CC | N = 1, R = 2 + * +--------------------------------+ + * L2LPM | EN | CC | CC | CC | CC | N = 1, R = 3 + * +--------------------------------+ + * VLPM | EN | CC | CC | CC | CC | N = 2, R = ? + * +--------------------------------+ + * EN | G=3 | G=2 | G=1 | G=0 + * + * + * Event Encoding: + * + * hwc->config_base = 0xNRCCG + * + * N = prefix, 1 for Scorpion CPU (LPMn/L2LPM), 2 for Venum VFP (VLPM) + * R = region register + * CC = class of events the group G is choosing from + * G = group or particular event + * + * Example: 0x12021 is a Scorpion CPU event in LPM2's group 1 with code 2 + * + * A region (R) corresponds to a piece of the CPU (execution unit, instruction + * unit, etc.) while the event code (CC) corresponds to a particular class of + * events (interrupts for example). An event code is broken down into + * groups (G) that can be mapped into the PMU (irq, fiqs, and irq+fiqs for + * example). + */ + +static u32 scorpion_read_pmresrn(int n) +{ + u32 val; + + switch (n) { + case 0: + asm volatile("mrc p15, 0, %0, c15, c0, 0" : "=r" (val)); + break; + case 1: + asm volatile("mrc p15, 1, %0, c15, c0, 0" : "=r" (val)); + break; + case 2: + asm volatile("mrc p15, 2, %0, c15, c0, 0" : "=r" (val)); + break; + case 3: + asm volatile("mrc p15, 3, %0, c15, c2, 0" : "=r" (val)); + break; + default: + BUG(); /* Should be validated in scorpion_pmu_get_event_idx() */ + } + + return val; +} + +static void scorpion_write_pmresrn(int n, u32 val) +{ + switch (n) { + case 0: + asm volatile("mcr p15, 0, %0, c15, c0, 0" : : "r" (val)); + break; + case 1: + asm volatile("mcr p15, 1, %0, c15, c0, 0" : : "r" (val)); + break; + case 2: + asm volatile("mcr p15, 2, %0, c15, c0, 0" : : "r" (val)); + break; + case 3: + asm volatile("mcr p15, 3, %0, c15, c2, 0" : : "r" (val)); + break; + default: + BUG(); /* Should be validated in scorpion_pmu_get_event_idx() */ + } +} + +static u32 scorpion_get_pmresrn_event(unsigned int region) +{ + static const u32 pmresrn_table[] = { SCORPION_LPM0_GROUP0, + SCORPION_LPM1_GROUP0, + SCORPION_LPM2_GROUP0, + SCORPION_L2LPM_GROUP0 }; + return pmresrn_table[region]; +} + +static void scorpion_evt_setup(int idx, u32 config_base) +{ + u32 val; + u32 mask; + u32 vval, fval; + unsigned int region = EVENT_REGION(config_base); + unsigned int group = EVENT_GROUP(config_base); + unsigned int code = EVENT_CODE(config_base); + unsigned int group_shift; + bool venum_event = EVENT_VENUM(config_base); + + group_shift = group * 8; + mask = 0xff << group_shift; + + /* Configure evtsel for the region and group */ + if (venum_event) + val = SCORPION_VLPM_GROUP0; + else + val = scorpion_get_pmresrn_event(region); + val += group; + /* Mix in mode-exclusion bits */ + val |= config_base & (ARMV7_EXCLUDE_USER | ARMV7_EXCLUDE_PL1); + armv7_pmnc_write_evtsel(idx, val); + + asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0)); + + if (venum_event) { + venum_pre_pmresr(&vval, &fval); + val = venum_read_pmresr(); + val &= ~mask; + val |= code << group_shift; + val |= PMRESRn_EN; + venum_write_pmresr(val); + venum_post_pmresr(vval, fval); + } else { + val = scorpion_read_pmresrn(region); + val &= ~mask; + val |= code << group_shift; + val |= PMRESRn_EN; + scorpion_write_pmresrn(region, val); + } +} + +static void scorpion_clearpmu(u32 config_base) +{ + u32 val; + u32 vval, fval; + unsigned int region = EVENT_REGION(config_base); + unsigned int group = EVENT_GROUP(config_base); + bool venum_event = EVENT_VENUM(config_base); + + if (venum_event) { + venum_pre_pmresr(&vval, &fval); + val = venum_read_pmresr(); + val = clear_pmresrn_group(val, group); + venum_write_pmresr(val); + venum_post_pmresr(vval, fval); + } else { + val = scorpion_read_pmresrn(region); + val = clear_pmresrn_group(val, group); + scorpion_write_pmresrn(region, val); + } +} + +static void scorpion_pmu_disable_event(struct perf_event *event) +{ + unsigned long flags; + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + /* Disable counter and interrupt */ + raw_spin_lock_irqsave(&events->pmu_lock, flags); + + /* Disable counter */ + armv7_pmnc_disable_counter(idx); + + /* + * Clear pmresr code (if destined for PMNx counters) + */ + if (hwc->config_base & KRAIT_EVENT_MASK) + scorpion_clearpmu(hwc->config_base); + + /* Disable interrupt for this counter */ + armv7_pmnc_disable_intens(idx); + + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void scorpion_pmu_enable_event(struct perf_event *event) +{ + unsigned long flags; + struct hw_perf_event *hwc = &event->hw; + int idx = hwc->idx; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + /* + * Enable counter and interrupt, and set the counter to count + * the event that we're interested in. + */ + raw_spin_lock_irqsave(&events->pmu_lock, flags); + + /* Disable counter */ + armv7_pmnc_disable_counter(idx); + + /* + * Set event (if destined for PMNx counters) + * We don't set the event for the cycle counter because we + * don't have the ability to perform event filtering. + */ + if (hwc->config_base & KRAIT_EVENT_MASK) + scorpion_evt_setup(idx, hwc->config_base); + else if (idx != ARMV7_IDX_CYCLE_COUNTER) + armv7_pmnc_write_evtsel(idx, hwc->config_base); + + /* Enable interrupt for this counter */ + armv7_pmnc_enable_intens(idx); + + /* Enable counter */ + armv7_pmnc_enable_counter(idx); + + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void scorpion_pmu_reset(void *info) +{ + u32 vval, fval; + struct arm_pmu *cpu_pmu = info; + u32 idx, nb_cnt = cpu_pmu->num_events; + + armv7pmu_reset(info); + + /* Clear all pmresrs */ + scorpion_write_pmresrn(0, 0); + scorpion_write_pmresrn(1, 0); + scorpion_write_pmresrn(2, 0); + scorpion_write_pmresrn(3, 0); + + venum_pre_pmresr(&vval, &fval); + venum_write_pmresr(0); + venum_post_pmresr(vval, fval); + + /* Reset PMxEVNCTCR to sane default */ + for (idx = ARMV7_IDX_CYCLE_COUNTER; idx < nb_cnt; ++idx) { + armv7_pmnc_select_counter(idx); + asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0)); + } +} + +static int scorpion_event_to_bit(struct perf_event *event, unsigned int region, + unsigned int group) +{ + int bit; + struct hw_perf_event *hwc = &event->hw; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + + if (hwc->config_base & VENUM_EVENT) + bit = SCORPION_VLPM_GROUP0; + else + bit = scorpion_get_pmresrn_event(region); + bit -= scorpion_get_pmresrn_event(0); + bit += group; + /* + * Lower bits are reserved for use by the counters (see + * armv7pmu_get_event_idx() for more info) + */ + bit += ARMV7_IDX_COUNTER_LAST(cpu_pmu) + 1; + + return bit; +} + +/* + * We check for column exclusion constraints here. + * Two events cant use the same group within a pmresr register. + */ +static int scorpion_pmu_get_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + int idx; + int bit = -1; + struct hw_perf_event *hwc = &event->hw; + unsigned int region = EVENT_REGION(hwc->config_base); + unsigned int group = EVENT_GROUP(hwc->config_base); + bool venum_event = EVENT_VENUM(hwc->config_base); + bool scorpion_event = EVENT_CPU(hwc->config_base); + + if (venum_event || scorpion_event) { + /* Ignore invalid events */ + if (group > 3 || region > 3) + return -EINVAL; + + bit = scorpion_event_to_bit(event, region, group); + if (test_and_set_bit(bit, cpuc->used_mask)) + return -EAGAIN; + } + + idx = armv7pmu_get_event_idx(cpuc, event); + if (idx < 0 && bit >= 0) + clear_bit(bit, cpuc->used_mask); + + return idx; +} + +static void scorpion_pmu_clear_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + int bit; + struct hw_perf_event *hwc = &event->hw; + unsigned int region = EVENT_REGION(hwc->config_base); + unsigned int group = EVENT_GROUP(hwc->config_base); + bool venum_event = EVENT_VENUM(hwc->config_base); + bool scorpion_event = EVENT_CPU(hwc->config_base); + + armv7pmu_clear_event_idx(cpuc, event); + if (venum_event || scorpion_event) { + bit = scorpion_event_to_bit(event, region, group); + clear_bit(bit, cpuc->used_mask); + } +} + +static int scorpion_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv7pmu_init(cpu_pmu); + cpu_pmu->name = "armv7_scorpion"; + cpu_pmu->map_event = scorpion_map_event; + cpu_pmu->reset = scorpion_pmu_reset; + cpu_pmu->enable = scorpion_pmu_enable_event; + cpu_pmu->disable = scorpion_pmu_disable_event; + cpu_pmu->get_event_idx = scorpion_pmu_get_event_idx; + cpu_pmu->clear_event_idx = scorpion_pmu_clear_event_idx; + return armv7_probe_num_events(cpu_pmu); +} + +static int scorpion_mp_pmu_init(struct arm_pmu *cpu_pmu) +{ + armv7pmu_init(cpu_pmu); + cpu_pmu->name = "armv7_scorpion_mp"; + cpu_pmu->map_event = scorpion_map_event; + cpu_pmu->reset = scorpion_pmu_reset; + cpu_pmu->enable = scorpion_pmu_enable_event; + cpu_pmu->disable = scorpion_pmu_disable_event; + cpu_pmu->get_event_idx = scorpion_pmu_get_event_idx; + cpu_pmu->clear_event_idx = scorpion_pmu_clear_event_idx; + return armv7_probe_num_events(cpu_pmu); +} + +static const struct of_device_id armv7_pmu_of_device_ids[] = { + {.compatible = "arm,cortex-a17-pmu", .data = armv7_a17_pmu_init}, + {.compatible = "arm,cortex-a15-pmu", .data = armv7_a15_pmu_init}, + {.compatible = "arm,cortex-a12-pmu", .data = armv7_a12_pmu_init}, + {.compatible = "arm,cortex-a9-pmu", .data = armv7_a9_pmu_init}, + {.compatible = "arm,cortex-a8-pmu", .data = armv7_a8_pmu_init}, + {.compatible = "arm,cortex-a7-pmu", .data = armv7_a7_pmu_init}, + {.compatible = "arm,cortex-a5-pmu", .data = armv7_a5_pmu_init}, + {.compatible = "qcom,krait-pmu", .data = krait_pmu_init}, + {.compatible = "qcom,scorpion-pmu", .data = scorpion_pmu_init}, + {.compatible = "qcom,scorpion-mp-pmu", .data = scorpion_mp_pmu_init}, + {}, +}; + +static const struct pmu_probe_info armv7_pmu_probe_table[] = { + ARM_PMU_PROBE(ARM_CPU_PART_CORTEX_A8, armv7_a8_pmu_init), + ARM_PMU_PROBE(ARM_CPU_PART_CORTEX_A9, armv7_a9_pmu_init), + { /* sentinel value */ } +}; + + +static int armv7_pmu_device_probe(struct platform_device *pdev) +{ + return arm_pmu_device_probe(pdev, armv7_pmu_of_device_ids, + armv7_pmu_probe_table); +} + +static struct platform_driver armv7_pmu_driver = { + .driver = { + .name = "armv7-pmu", + .of_match_table = armv7_pmu_of_device_ids, + .suppress_bind_attrs = true, + }, + .probe = armv7_pmu_device_probe, +}; + +builtin_platform_driver(armv7_pmu_driver); +#endif /* CONFIG_CPU_V7 */ diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c new file mode 100644 index 000000000..f6cdcacfb --- /dev/null +++ b/arch/arm/kernel/perf_event_xscale.c @@ -0,0 +1,776 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * ARMv5 [xscale] Performance counter handling code. + * + * Copyright (C) 2010, ARM Ltd., Will Deacon <will.deacon@arm.com> + * + * Based on the previous xscale OProfile code. + * + * There are two variants of the xscale PMU that we support: + * - xscale1pmu: 2 event counters and a cycle counter + * - xscale2pmu: 4 event counters and a cycle counter + * The two variants share event definitions, but have different + * PMU structures. + */ + +#ifdef CONFIG_CPU_XSCALE + +#include <asm/cputype.h> +#include <asm/irq_regs.h> + +#include <linux/of.h> +#include <linux/perf/arm_pmu.h> +#include <linux/platform_device.h> + +enum xscale_perf_types { + XSCALE_PERFCTR_ICACHE_MISS = 0x00, + XSCALE_PERFCTR_ICACHE_NO_DELIVER = 0x01, + XSCALE_PERFCTR_DATA_STALL = 0x02, + XSCALE_PERFCTR_ITLB_MISS = 0x03, + XSCALE_PERFCTR_DTLB_MISS = 0x04, + XSCALE_PERFCTR_BRANCH = 0x05, + XSCALE_PERFCTR_BRANCH_MISS = 0x06, + XSCALE_PERFCTR_INSTRUCTION = 0x07, + XSCALE_PERFCTR_DCACHE_FULL_STALL = 0x08, + XSCALE_PERFCTR_DCACHE_FULL_STALL_CONTIG = 0x09, + XSCALE_PERFCTR_DCACHE_ACCESS = 0x0A, + XSCALE_PERFCTR_DCACHE_MISS = 0x0B, + XSCALE_PERFCTR_DCACHE_WRITE_BACK = 0x0C, + XSCALE_PERFCTR_PC_CHANGED = 0x0D, + XSCALE_PERFCTR_BCU_REQUEST = 0x10, + XSCALE_PERFCTR_BCU_FULL = 0x11, + XSCALE_PERFCTR_BCU_DRAIN = 0x12, + XSCALE_PERFCTR_BCU_ECC_NO_ELOG = 0x14, + XSCALE_PERFCTR_BCU_1_BIT_ERR = 0x15, + XSCALE_PERFCTR_RMW = 0x16, + /* XSCALE_PERFCTR_CCNT is not hardware defined */ + XSCALE_PERFCTR_CCNT = 0xFE, + XSCALE_PERFCTR_UNUSED = 0xFF, +}; + +enum xscale_counters { + XSCALE_CYCLE_COUNTER = 0, + XSCALE_COUNTER0, + XSCALE_COUNTER1, + XSCALE_COUNTER2, + XSCALE_COUNTER3, +}; + +static const unsigned xscale_perf_map[PERF_COUNT_HW_MAX] = { + PERF_MAP_ALL_UNSUPPORTED, + [PERF_COUNT_HW_CPU_CYCLES] = XSCALE_PERFCTR_CCNT, + [PERF_COUNT_HW_INSTRUCTIONS] = XSCALE_PERFCTR_INSTRUCTION, + [PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = XSCALE_PERFCTR_BRANCH, + [PERF_COUNT_HW_BRANCH_MISSES] = XSCALE_PERFCTR_BRANCH_MISS, + [PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = XSCALE_PERFCTR_ICACHE_NO_DELIVER, +}; + +static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX] + [PERF_COUNT_HW_CACHE_OP_MAX] + [PERF_COUNT_HW_CACHE_RESULT_MAX] = { + PERF_CACHE_MAP_ALL_UNSUPPORTED, + + [C(L1D)][C(OP_READ)][C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS, + [C(L1D)][C(OP_READ)][C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS, + [C(L1D)][C(OP_WRITE)][C(RESULT_ACCESS)] = XSCALE_PERFCTR_DCACHE_ACCESS, + [C(L1D)][C(OP_WRITE)][C(RESULT_MISS)] = XSCALE_PERFCTR_DCACHE_MISS, + + [C(L1I)][C(OP_READ)][C(RESULT_MISS)] = XSCALE_PERFCTR_ICACHE_MISS, + + [C(DTLB)][C(OP_READ)][C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS, + [C(DTLB)][C(OP_WRITE)][C(RESULT_MISS)] = XSCALE_PERFCTR_DTLB_MISS, + + [C(ITLB)][C(OP_READ)][C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS, + [C(ITLB)][C(OP_WRITE)][C(RESULT_MISS)] = XSCALE_PERFCTR_ITLB_MISS, +}; + +#define XSCALE_PMU_ENABLE 0x001 +#define XSCALE_PMN_RESET 0x002 +#define XSCALE_CCNT_RESET 0x004 +#define XSCALE_PMU_RESET (CCNT_RESET | PMN_RESET) +#define XSCALE_PMU_CNT64 0x008 + +#define XSCALE1_OVERFLOWED_MASK 0x700 +#define XSCALE1_CCOUNT_OVERFLOW 0x400 +#define XSCALE1_COUNT0_OVERFLOW 0x100 +#define XSCALE1_COUNT1_OVERFLOW 0x200 +#define XSCALE1_CCOUNT_INT_EN 0x040 +#define XSCALE1_COUNT0_INT_EN 0x010 +#define XSCALE1_COUNT1_INT_EN 0x020 +#define XSCALE1_COUNT0_EVT_SHFT 12 +#define XSCALE1_COUNT0_EVT_MASK (0xff << XSCALE1_COUNT0_EVT_SHFT) +#define XSCALE1_COUNT1_EVT_SHFT 20 +#define XSCALE1_COUNT1_EVT_MASK (0xff << XSCALE1_COUNT1_EVT_SHFT) + +static inline u32 +xscale1pmu_read_pmnc(void) +{ + u32 val; + asm volatile("mrc p14, 0, %0, c0, c0, 0" : "=r" (val)); + return val; +} + +static inline void +xscale1pmu_write_pmnc(u32 val) +{ + /* upper 4bits and 7, 11 are write-as-0 */ + val &= 0xffff77f; + asm volatile("mcr p14, 0, %0, c0, c0, 0" : : "r" (val)); +} + +static inline int +xscale1_pmnc_counter_has_overflowed(unsigned long pmnc, + enum xscale_counters counter) +{ + int ret = 0; + + switch (counter) { + case XSCALE_CYCLE_COUNTER: + ret = pmnc & XSCALE1_CCOUNT_OVERFLOW; + break; + case XSCALE_COUNTER0: + ret = pmnc & XSCALE1_COUNT0_OVERFLOW; + break; + case XSCALE_COUNTER1: + ret = pmnc & XSCALE1_COUNT1_OVERFLOW; + break; + default: + WARN_ONCE(1, "invalid counter number (%d)\n", counter); + } + + return ret; +} + +static irqreturn_t +xscale1pmu_handle_irq(struct arm_pmu *cpu_pmu) +{ + unsigned long pmnc; + struct perf_sample_data data; + struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events); + struct pt_regs *regs; + int idx; + + /* + * NOTE: there's an A stepping erratum that states if an overflow + * bit already exists and another occurs, the previous + * Overflow bit gets cleared. There's no workaround. + * Fixed in B stepping or later. + */ + pmnc = xscale1pmu_read_pmnc(); + + /* + * Write the value back to clear the overflow flags. Overflow + * flags remain in pmnc for use below. We also disable the PMU + * while we process the interrupt. + */ + xscale1pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE); + + if (!(pmnc & XSCALE1_OVERFLOWED_MASK)) + return IRQ_NONE; + + regs = get_irq_regs(); + + for (idx = 0; idx < cpu_pmu->num_events; ++idx) { + struct perf_event *event = cpuc->events[idx]; + struct hw_perf_event *hwc; + + if (!event) + continue; + + if (!xscale1_pmnc_counter_has_overflowed(pmnc, idx)) + continue; + + hwc = &event->hw; + armpmu_event_update(event); + perf_sample_data_init(&data, 0, hwc->last_period); + if (!armpmu_event_set_period(event)) + continue; + + if (perf_event_overflow(event, &data, regs)) + cpu_pmu->disable(event); + } + + irq_work_run(); + + /* + * Re-enable the PMU. + */ + pmnc = xscale1pmu_read_pmnc() | XSCALE_PMU_ENABLE; + xscale1pmu_write_pmnc(pmnc); + + return IRQ_HANDLED; +} + +static void xscale1pmu_enable_event(struct perf_event *event) +{ + unsigned long val, mask, evt, flags; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx = hwc->idx; + + switch (idx) { + case XSCALE_CYCLE_COUNTER: + mask = 0; + evt = XSCALE1_CCOUNT_INT_EN; + break; + case XSCALE_COUNTER0: + mask = XSCALE1_COUNT0_EVT_MASK; + evt = (hwc->config_base << XSCALE1_COUNT0_EVT_SHFT) | + XSCALE1_COUNT0_INT_EN; + break; + case XSCALE_COUNTER1: + mask = XSCALE1_COUNT1_EVT_MASK; + evt = (hwc->config_base << XSCALE1_COUNT1_EVT_SHFT) | + XSCALE1_COUNT1_INT_EN; + break; + default: + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + val = xscale1pmu_read_pmnc(); + val &= ~mask; + val |= evt; + xscale1pmu_write_pmnc(val); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void xscale1pmu_disable_event(struct perf_event *event) +{ + unsigned long val, mask, evt, flags; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx = hwc->idx; + + switch (idx) { + case XSCALE_CYCLE_COUNTER: + mask = XSCALE1_CCOUNT_INT_EN; + evt = 0; + break; + case XSCALE_COUNTER0: + mask = XSCALE1_COUNT0_INT_EN | XSCALE1_COUNT0_EVT_MASK; + evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT0_EVT_SHFT; + break; + case XSCALE_COUNTER1: + mask = XSCALE1_COUNT1_INT_EN | XSCALE1_COUNT1_EVT_MASK; + evt = XSCALE_PERFCTR_UNUSED << XSCALE1_COUNT1_EVT_SHFT; + break; + default: + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + val = xscale1pmu_read_pmnc(); + val &= ~mask; + val |= evt; + xscale1pmu_write_pmnc(val); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static int +xscale1pmu_get_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + if (XSCALE_PERFCTR_CCNT == hwc->config_base) { + if (test_and_set_bit(XSCALE_CYCLE_COUNTER, cpuc->used_mask)) + return -EAGAIN; + + return XSCALE_CYCLE_COUNTER; + } else { + if (!test_and_set_bit(XSCALE_COUNTER1, cpuc->used_mask)) + return XSCALE_COUNTER1; + + if (!test_and_set_bit(XSCALE_COUNTER0, cpuc->used_mask)) + return XSCALE_COUNTER0; + + return -EAGAIN; + } +} + +static void xscalepmu_clear_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + clear_bit(event->hw.idx, cpuc->used_mask); +} + +static void xscale1pmu_start(struct arm_pmu *cpu_pmu) +{ + unsigned long flags, val; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + val = xscale1pmu_read_pmnc(); + val |= XSCALE_PMU_ENABLE; + xscale1pmu_write_pmnc(val); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void xscale1pmu_stop(struct arm_pmu *cpu_pmu) +{ + unsigned long flags, val; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + val = xscale1pmu_read_pmnc(); + val &= ~XSCALE_PMU_ENABLE; + xscale1pmu_write_pmnc(val); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static inline u64 xscale1pmu_read_counter(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int counter = hwc->idx; + u32 val = 0; + + switch (counter) { + case XSCALE_CYCLE_COUNTER: + asm volatile("mrc p14, 0, %0, c1, c0, 0" : "=r" (val)); + break; + case XSCALE_COUNTER0: + asm volatile("mrc p14, 0, %0, c2, c0, 0" : "=r" (val)); + break; + case XSCALE_COUNTER1: + asm volatile("mrc p14, 0, %0, c3, c0, 0" : "=r" (val)); + break; + } + + return val; +} + +static inline void xscale1pmu_write_counter(struct perf_event *event, u64 val) +{ + struct hw_perf_event *hwc = &event->hw; + int counter = hwc->idx; + + switch (counter) { + case XSCALE_CYCLE_COUNTER: + asm volatile("mcr p14, 0, %0, c1, c0, 0" : : "r" (val)); + break; + case XSCALE_COUNTER0: + asm volatile("mcr p14, 0, %0, c2, c0, 0" : : "r" (val)); + break; + case XSCALE_COUNTER1: + asm volatile("mcr p14, 0, %0, c3, c0, 0" : : "r" (val)); + break; + } +} + +static int xscale_map_event(struct perf_event *event) +{ + return armpmu_map_event(event, &xscale_perf_map, + &xscale_perf_cache_map, 0xFF); +} + +static int xscale1pmu_init(struct arm_pmu *cpu_pmu) +{ + cpu_pmu->name = "armv5_xscale1"; + cpu_pmu->handle_irq = xscale1pmu_handle_irq; + cpu_pmu->enable = xscale1pmu_enable_event; + cpu_pmu->disable = xscale1pmu_disable_event; + cpu_pmu->read_counter = xscale1pmu_read_counter; + cpu_pmu->write_counter = xscale1pmu_write_counter; + cpu_pmu->get_event_idx = xscale1pmu_get_event_idx; + cpu_pmu->clear_event_idx = xscalepmu_clear_event_idx; + cpu_pmu->start = xscale1pmu_start; + cpu_pmu->stop = xscale1pmu_stop; + cpu_pmu->map_event = xscale_map_event; + cpu_pmu->num_events = 3; + + return 0; +} + +#define XSCALE2_OVERFLOWED_MASK 0x01f +#define XSCALE2_CCOUNT_OVERFLOW 0x001 +#define XSCALE2_COUNT0_OVERFLOW 0x002 +#define XSCALE2_COUNT1_OVERFLOW 0x004 +#define XSCALE2_COUNT2_OVERFLOW 0x008 +#define XSCALE2_COUNT3_OVERFLOW 0x010 +#define XSCALE2_CCOUNT_INT_EN 0x001 +#define XSCALE2_COUNT0_INT_EN 0x002 +#define XSCALE2_COUNT1_INT_EN 0x004 +#define XSCALE2_COUNT2_INT_EN 0x008 +#define XSCALE2_COUNT3_INT_EN 0x010 +#define XSCALE2_COUNT0_EVT_SHFT 0 +#define XSCALE2_COUNT0_EVT_MASK (0xff << XSCALE2_COUNT0_EVT_SHFT) +#define XSCALE2_COUNT1_EVT_SHFT 8 +#define XSCALE2_COUNT1_EVT_MASK (0xff << XSCALE2_COUNT1_EVT_SHFT) +#define XSCALE2_COUNT2_EVT_SHFT 16 +#define XSCALE2_COUNT2_EVT_MASK (0xff << XSCALE2_COUNT2_EVT_SHFT) +#define XSCALE2_COUNT3_EVT_SHFT 24 +#define XSCALE2_COUNT3_EVT_MASK (0xff << XSCALE2_COUNT3_EVT_SHFT) + +static inline u32 +xscale2pmu_read_pmnc(void) +{ + u32 val; + asm volatile("mrc p14, 0, %0, c0, c1, 0" : "=r" (val)); + /* bits 1-2 and 4-23 are read-unpredictable */ + return val & 0xff000009; +} + +static inline void +xscale2pmu_write_pmnc(u32 val) +{ + /* bits 4-23 are write-as-0, 24-31 are write ignored */ + val &= 0xf; + asm volatile("mcr p14, 0, %0, c0, c1, 0" : : "r" (val)); +} + +static inline u32 +xscale2pmu_read_overflow_flags(void) +{ + u32 val; + asm volatile("mrc p14, 0, %0, c5, c1, 0" : "=r" (val)); + return val; +} + +static inline void +xscale2pmu_write_overflow_flags(u32 val) +{ + asm volatile("mcr p14, 0, %0, c5, c1, 0" : : "r" (val)); +} + +static inline u32 +xscale2pmu_read_event_select(void) +{ + u32 val; + asm volatile("mrc p14, 0, %0, c8, c1, 0" : "=r" (val)); + return val; +} + +static inline void +xscale2pmu_write_event_select(u32 val) +{ + asm volatile("mcr p14, 0, %0, c8, c1, 0" : : "r"(val)); +} + +static inline u32 +xscale2pmu_read_int_enable(void) +{ + u32 val; + asm volatile("mrc p14, 0, %0, c4, c1, 0" : "=r" (val)); + return val; +} + +static void +xscale2pmu_write_int_enable(u32 val) +{ + asm volatile("mcr p14, 0, %0, c4, c1, 0" : : "r" (val)); +} + +static inline int +xscale2_pmnc_counter_has_overflowed(unsigned long of_flags, + enum xscale_counters counter) +{ + int ret = 0; + + switch (counter) { + case XSCALE_CYCLE_COUNTER: + ret = of_flags & XSCALE2_CCOUNT_OVERFLOW; + break; + case XSCALE_COUNTER0: + ret = of_flags & XSCALE2_COUNT0_OVERFLOW; + break; + case XSCALE_COUNTER1: + ret = of_flags & XSCALE2_COUNT1_OVERFLOW; + break; + case XSCALE_COUNTER2: + ret = of_flags & XSCALE2_COUNT2_OVERFLOW; + break; + case XSCALE_COUNTER3: + ret = of_flags & XSCALE2_COUNT3_OVERFLOW; + break; + default: + WARN_ONCE(1, "invalid counter number (%d)\n", counter); + } + + return ret; +} + +static irqreturn_t +xscale2pmu_handle_irq(struct arm_pmu *cpu_pmu) +{ + unsigned long pmnc, of_flags; + struct perf_sample_data data; + struct pmu_hw_events *cpuc = this_cpu_ptr(cpu_pmu->hw_events); + struct pt_regs *regs; + int idx; + + /* Disable the PMU. */ + pmnc = xscale2pmu_read_pmnc(); + xscale2pmu_write_pmnc(pmnc & ~XSCALE_PMU_ENABLE); + + /* Check the overflow flag register. */ + of_flags = xscale2pmu_read_overflow_flags(); + if (!(of_flags & XSCALE2_OVERFLOWED_MASK)) + return IRQ_NONE; + + /* Clear the overflow bits. */ + xscale2pmu_write_overflow_flags(of_flags); + + regs = get_irq_regs(); + + for (idx = 0; idx < cpu_pmu->num_events; ++idx) { + struct perf_event *event = cpuc->events[idx]; + struct hw_perf_event *hwc; + + if (!event) + continue; + + if (!xscale2_pmnc_counter_has_overflowed(of_flags, idx)) + continue; + + hwc = &event->hw; + armpmu_event_update(event); + perf_sample_data_init(&data, 0, hwc->last_period); + if (!armpmu_event_set_period(event)) + continue; + + if (perf_event_overflow(event, &data, regs)) + cpu_pmu->disable(event); + } + + irq_work_run(); + + /* + * Re-enable the PMU. + */ + pmnc = xscale2pmu_read_pmnc() | XSCALE_PMU_ENABLE; + xscale2pmu_write_pmnc(pmnc); + + return IRQ_HANDLED; +} + +static void xscale2pmu_enable_event(struct perf_event *event) +{ + unsigned long flags, ien, evtsel; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx = hwc->idx; + + ien = xscale2pmu_read_int_enable(); + evtsel = xscale2pmu_read_event_select(); + + switch (idx) { + case XSCALE_CYCLE_COUNTER: + ien |= XSCALE2_CCOUNT_INT_EN; + break; + case XSCALE_COUNTER0: + ien |= XSCALE2_COUNT0_INT_EN; + evtsel &= ~XSCALE2_COUNT0_EVT_MASK; + evtsel |= hwc->config_base << XSCALE2_COUNT0_EVT_SHFT; + break; + case XSCALE_COUNTER1: + ien |= XSCALE2_COUNT1_INT_EN; + evtsel &= ~XSCALE2_COUNT1_EVT_MASK; + evtsel |= hwc->config_base << XSCALE2_COUNT1_EVT_SHFT; + break; + case XSCALE_COUNTER2: + ien |= XSCALE2_COUNT2_INT_EN; + evtsel &= ~XSCALE2_COUNT2_EVT_MASK; + evtsel |= hwc->config_base << XSCALE2_COUNT2_EVT_SHFT; + break; + case XSCALE_COUNTER3: + ien |= XSCALE2_COUNT3_INT_EN; + evtsel &= ~XSCALE2_COUNT3_EVT_MASK; + evtsel |= hwc->config_base << XSCALE2_COUNT3_EVT_SHFT; + break; + default: + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + xscale2pmu_write_event_select(evtsel); + xscale2pmu_write_int_enable(ien); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void xscale2pmu_disable_event(struct perf_event *event) +{ + unsigned long flags, ien, evtsel, of_flags; + struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu); + struct hw_perf_event *hwc = &event->hw; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + int idx = hwc->idx; + + ien = xscale2pmu_read_int_enable(); + evtsel = xscale2pmu_read_event_select(); + + switch (idx) { + case XSCALE_CYCLE_COUNTER: + ien &= ~XSCALE2_CCOUNT_INT_EN; + of_flags = XSCALE2_CCOUNT_OVERFLOW; + break; + case XSCALE_COUNTER0: + ien &= ~XSCALE2_COUNT0_INT_EN; + evtsel &= ~XSCALE2_COUNT0_EVT_MASK; + evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT0_EVT_SHFT; + of_flags = XSCALE2_COUNT0_OVERFLOW; + break; + case XSCALE_COUNTER1: + ien &= ~XSCALE2_COUNT1_INT_EN; + evtsel &= ~XSCALE2_COUNT1_EVT_MASK; + evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT1_EVT_SHFT; + of_flags = XSCALE2_COUNT1_OVERFLOW; + break; + case XSCALE_COUNTER2: + ien &= ~XSCALE2_COUNT2_INT_EN; + evtsel &= ~XSCALE2_COUNT2_EVT_MASK; + evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT2_EVT_SHFT; + of_flags = XSCALE2_COUNT2_OVERFLOW; + break; + case XSCALE_COUNTER3: + ien &= ~XSCALE2_COUNT3_INT_EN; + evtsel &= ~XSCALE2_COUNT3_EVT_MASK; + evtsel |= XSCALE_PERFCTR_UNUSED << XSCALE2_COUNT3_EVT_SHFT; + of_flags = XSCALE2_COUNT3_OVERFLOW; + break; + default: + WARN_ONCE(1, "invalid counter number (%d)\n", idx); + return; + } + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + xscale2pmu_write_event_select(evtsel); + xscale2pmu_write_int_enable(ien); + xscale2pmu_write_overflow_flags(of_flags); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static int +xscale2pmu_get_event_idx(struct pmu_hw_events *cpuc, + struct perf_event *event) +{ + int idx = xscale1pmu_get_event_idx(cpuc, event); + if (idx >= 0) + goto out; + + if (!test_and_set_bit(XSCALE_COUNTER3, cpuc->used_mask)) + idx = XSCALE_COUNTER3; + else if (!test_and_set_bit(XSCALE_COUNTER2, cpuc->used_mask)) + idx = XSCALE_COUNTER2; +out: + return idx; +} + +static void xscale2pmu_start(struct arm_pmu *cpu_pmu) +{ + unsigned long flags, val; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + val = xscale2pmu_read_pmnc() & ~XSCALE_PMU_CNT64; + val |= XSCALE_PMU_ENABLE; + xscale2pmu_write_pmnc(val); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static void xscale2pmu_stop(struct arm_pmu *cpu_pmu) +{ + unsigned long flags, val; + struct pmu_hw_events *events = this_cpu_ptr(cpu_pmu->hw_events); + + raw_spin_lock_irqsave(&events->pmu_lock, flags); + val = xscale2pmu_read_pmnc(); + val &= ~XSCALE_PMU_ENABLE; + xscale2pmu_write_pmnc(val); + raw_spin_unlock_irqrestore(&events->pmu_lock, flags); +} + +static inline u64 xscale2pmu_read_counter(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + int counter = hwc->idx; + u32 val = 0; + + switch (counter) { + case XSCALE_CYCLE_COUNTER: + asm volatile("mrc p14, 0, %0, c1, c1, 0" : "=r" (val)); + break; + case XSCALE_COUNTER0: + asm volatile("mrc p14, 0, %0, c0, c2, 0" : "=r" (val)); + break; + case XSCALE_COUNTER1: + asm volatile("mrc p14, 0, %0, c1, c2, 0" : "=r" (val)); + break; + case XSCALE_COUNTER2: + asm volatile("mrc p14, 0, %0, c2, c2, 0" : "=r" (val)); + break; + case XSCALE_COUNTER3: + asm volatile("mrc p14, 0, %0, c3, c2, 0" : "=r" (val)); + break; + } + + return val; +} + +static inline void xscale2pmu_write_counter(struct perf_event *event, u64 val) +{ + struct hw_perf_event *hwc = &event->hw; + int counter = hwc->idx; + + switch (counter) { + case XSCALE_CYCLE_COUNTER: + asm volatile("mcr p14, 0, %0, c1, c1, 0" : : "r" (val)); + break; + case XSCALE_COUNTER0: + asm volatile("mcr p14, 0, %0, c0, c2, 0" : : "r" (val)); + break; + case XSCALE_COUNTER1: + asm volatile("mcr p14, 0, %0, c1, c2, 0" : : "r" (val)); + break; + case XSCALE_COUNTER2: + asm volatile("mcr p14, 0, %0, c2, c2, 0" : : "r" (val)); + break; + case XSCALE_COUNTER3: + asm volatile("mcr p14, 0, %0, c3, c2, 0" : : "r" (val)); + break; + } +} + +static int xscale2pmu_init(struct arm_pmu *cpu_pmu) +{ + cpu_pmu->name = "armv5_xscale2"; + cpu_pmu->handle_irq = xscale2pmu_handle_irq; + cpu_pmu->enable = xscale2pmu_enable_event; + cpu_pmu->disable = xscale2pmu_disable_event; + cpu_pmu->read_counter = xscale2pmu_read_counter; + cpu_pmu->write_counter = xscale2pmu_write_counter; + cpu_pmu->get_event_idx = xscale2pmu_get_event_idx; + cpu_pmu->clear_event_idx = xscalepmu_clear_event_idx; + cpu_pmu->start = xscale2pmu_start; + cpu_pmu->stop = xscale2pmu_stop; + cpu_pmu->map_event = xscale_map_event; + cpu_pmu->num_events = 5; + + return 0; +} + +static const struct pmu_probe_info xscale_pmu_probe_table[] = { + XSCALE_PMU_PROBE(ARM_CPU_XSCALE_ARCH_V1, xscale1pmu_init), + XSCALE_PMU_PROBE(ARM_CPU_XSCALE_ARCH_V2, xscale2pmu_init), + { /* sentinel value */ } +}; + +static int xscale_pmu_device_probe(struct platform_device *pdev) +{ + return arm_pmu_device_probe(pdev, NULL, xscale_pmu_probe_table); +} + +static struct platform_driver xscale_pmu_driver = { + .driver = { + .name = "xscale-pmu", + }, + .probe = xscale_pmu_device_probe, +}; + +builtin_platform_driver(xscale_pmu_driver); +#endif /* CONFIG_CPU_XSCALE */ diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c new file mode 100644 index 000000000..0529f9039 --- /dev/null +++ b/arch/arm/kernel/perf_regs.c @@ -0,0 +1,39 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/errno.h> +#include <linux/kernel.h> +#include <linux/perf_event.h> +#include <linux/bug.h> +#include <linux/sched/task_stack.h> +#include <asm/perf_regs.h> +#include <asm/ptrace.h> + +u64 perf_reg_value(struct pt_regs *regs, int idx) +{ + if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM_MAX)) + return 0; + + return regs->uregs[idx]; +} + +#define REG_RESERVED (~((1ULL << PERF_REG_ARM_MAX) - 1)) + +int perf_reg_validate(u64 mask) +{ + if (!mask || mask & REG_RESERVED) + return -EINVAL; + + return 0; +} + +u64 perf_reg_abi(struct task_struct *task) +{ + return PERF_SAMPLE_REGS_ABI_32; +} + +void perf_get_regs_user(struct perf_regs *regs_user, + struct pt_regs *regs) +{ + regs_user->regs = task_pt_regs(current); + regs_user->abi = perf_reg_abi(current); +} diff --git a/arch/arm/kernel/phys2virt.S b/arch/arm/kernel/phys2virt.S new file mode 100644 index 000000000..fb53db78f --- /dev/null +++ b/arch/arm/kernel/phys2virt.S @@ -0,0 +1,238 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (C) 1994-2002 Russell King + * Copyright (c) 2003, 2020 ARM Limited + * All Rights Reserved + */ + +#include <linux/init.h> +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/page.h> + +#ifdef __ARMEB__ +#define LOW_OFFSET 0x4 +#define HIGH_OFFSET 0x0 +#else +#define LOW_OFFSET 0x0 +#define HIGH_OFFSET 0x4 +#endif + +/* + * __fixup_pv_table - patch the stub instructions with the delta between + * PHYS_OFFSET and PAGE_OFFSET, which is assumed to be + * 2 MiB aligned. + * + * Called from head.S, which expects the following registers to be preserved: + * r1 = machine no, r2 = atags or dtb, + * r8 = phys_offset, r9 = cpuid, r10 = procinfo + */ + __HEAD +ENTRY(__fixup_pv_table) + mov r0, r8, lsr #PAGE_SHIFT @ convert to PFN + str_l r0, __pv_phys_pfn_offset, r3 + + adr_l r0, __pv_offset + subs r3, r8, #PAGE_OFFSET @ PHYS_OFFSET - PAGE_OFFSET + mvn ip, #0 + strcc ip, [r0, #HIGH_OFFSET] @ save to __pv_offset high bits + str r3, [r0, #LOW_OFFSET] @ save to __pv_offset low bits + + mov r0, r3, lsr #21 @ constant for add/sub instructions + teq r3, r0, lsl #21 @ must be 2 MiB aligned + bne 0f + + adr_l r4, __pv_table_begin + adr_l r5, __pv_table_end + b __fixup_a_pv_table + +0: mov r0, r0 @ deadloop on error + b 0b +ENDPROC(__fixup_pv_table) + + .text +__fixup_a_pv_table: + adr_l r6, __pv_offset + ldr r0, [r6, #HIGH_OFFSET] @ pv_offset high word + ldr r6, [r6, #LOW_OFFSET] @ pv_offset low word + cmn r0, #1 +#ifdef CONFIG_THUMB2_KERNEL + @ + @ The Thumb-2 versions of the patchable sequences are + @ + @ phys-to-virt: movw <reg>, #offset<31:21> + @ lsl <reg>, #21 + @ sub <VA>, <PA>, <reg> + @ + @ virt-to-phys (non-LPAE): movw <reg>, #offset<31:21> + @ lsl <reg>, #21 + @ add <PA>, <VA>, <reg> + @ + @ virt-to-phys (LPAE): movw <reg>, #offset<31:21> + @ lsl <reg>, #21 + @ adds <PAlo>, <VA>, <reg> + @ mov <PAhi>, #offset<39:32> + @ adc <PAhi>, <PAhi>, #0 + @ + @ In the non-LPAE case, all patchable instructions are MOVW + @ instructions, where we need to patch in the offset into the + @ second halfword of the opcode (the 16-bit immediate is encoded + @ as imm4:i:imm3:imm8) + @ + @ 15 11 10 9 4 3 0 15 14 12 11 8 7 0 + @ +-----------+---+-------------+------++---+------+----+------+ + @ MOVW | 1 1 1 1 0 | i | 1 0 0 1 0 0 | imm4 || 0 | imm3 | Rd | imm8 | + @ +-----------+---+-------------+------++---+------+----+------+ + @ + @ In the LPAE case, we also need to patch in the high word of the + @ offset into the immediate field of the MOV instruction, or patch it + @ to a MVN instruction if the offset is negative. In this case, we + @ need to inspect the first halfword of the opcode, to check whether + @ it is MOVW or MOV/MVN, and to perform the MOV to MVN patching if + @ needed. The encoding of the immediate is rather complex for values + @ of i:imm3 != 0b0000, but fortunately, we never need more than 8 lower + @ order bits, which can be patched into imm8 directly (and i:imm3 + @ cleared) + @ + @ 15 11 10 9 5 0 15 14 12 11 8 7 0 + @ +-----------+---+---------------------++---+------+----+------+ + @ MOV | 1 1 1 1 0 | i | 0 0 0 1 0 0 1 1 1 1 || 0 | imm3 | Rd | imm8 | + @ MVN | 1 1 1 1 0 | i | 0 0 0 1 1 0 1 1 1 1 || 0 | imm3 | Rd | imm8 | + @ +-----------+---+---------------------++---+------+----+------+ + @ + moveq r0, #0x200000 @ set bit 21, mov to mvn instruction + lsrs r3, r6, #29 @ isolate top 3 bits of displacement + ubfx r6, r6, #21, #8 @ put bits 28:21 into the MOVW imm8 field + bfi r6, r3, #12, #3 @ put bits 31:29 into the MOVW imm3 field + b .Lnext +.Lloop: add r7, r4 + adds r4, #4 @ clears Z flag +#ifdef CONFIG_ARM_LPAE + ldrh ip, [r7] +ARM_BE8(rev16 ip, ip) + tst ip, #0x200 @ MOVW has bit 9 set, MVN has it clear + bne 0f @ skip to MOVW handling (Z flag is clear) + bic ip, #0x20 @ clear bit 5 (MVN -> MOV) + orr ip, ip, r0, lsr #16 @ MOV -> MVN if offset < 0 +ARM_BE8(rev16 ip, ip) + strh ip, [r7] + @ Z flag is set +0: +#endif + ldrh ip, [r7, #2] +ARM_BE8(rev16 ip, ip) + and ip, #0xf00 @ clear everything except Rd field + orreq ip, r0 @ Z flag set -> MOV/MVN -> patch in high bits + orrne ip, r6 @ Z flag clear -> MOVW -> patch in low bits +ARM_BE8(rev16 ip, ip) + strh ip, [r7, #2] +#else +#ifdef CONFIG_CPU_ENDIAN_BE8 +@ in BE8, we load data in BE, but instructions still in LE +#define PV_BIT24 0x00000001 +#define PV_IMM8_MASK 0xff000000 +#define PV_IMMR_MSB 0x00080000 +#else +#define PV_BIT24 0x01000000 +#define PV_IMM8_MASK 0x000000ff +#define PV_IMMR_MSB 0x00000800 +#endif + + @ + @ The ARM versions of the patchable sequences are + @ + @ phys-to-virt: sub <VA>, <PA>, #offset<31:24>, lsl #24 + @ sub <VA>, <PA>, #offset<23:16>, lsl #16 + @ + @ virt-to-phys (non-LPAE): add <PA>, <VA>, #offset<31:24>, lsl #24 + @ add <PA>, <VA>, #offset<23:16>, lsl #16 + @ + @ virt-to-phys (LPAE): movw <reg>, #offset<31:20> + @ adds <PAlo>, <VA>, <reg>, lsl #20 + @ mov <PAhi>, #offset<39:32> + @ adc <PAhi>, <PAhi>, #0 + @ + @ In the non-LPAE case, all patchable instructions are ADD or SUB + @ instructions, where we need to patch in the offset into the + @ immediate field of the opcode, which is emitted with the correct + @ rotation value. (The effective value of the immediate is imm12<7:0> + @ rotated right by [2 * imm12<11:8>] bits) + @ + @ 31 28 27 23 22 20 19 16 15 12 11 0 + @ +------+-----------------+------+------+-------+ + @ ADD | cond | 0 0 1 0 1 0 0 0 | Rn | Rd | imm12 | + @ SUB | cond | 0 0 1 0 0 1 0 0 | Rn | Rd | imm12 | + @ MOV | cond | 0 0 1 1 1 0 1 0 | Rn | Rd | imm12 | + @ MVN | cond | 0 0 1 1 1 1 1 0 | Rn | Rd | imm12 | + @ +------+-----------------+------+------+-------+ + @ + @ In the LPAE case, we use a MOVW instruction to carry the low offset + @ word, and patch in the high word of the offset into the immediate + @ field of the subsequent MOV instruction, or patch it to a MVN + @ instruction if the offset is negative. We can distinguish MOVW + @ instructions based on bits 23:22 of the opcode, and ADD/SUB can be + @ distinguished from MOV/MVN (all using the encodings above) using + @ bit 24. + @ + @ 31 28 27 23 22 20 19 16 15 12 11 0 + @ +------+-----------------+------+------+-------+ + @ MOVW | cond | 0 0 1 1 0 0 0 0 | imm4 | Rd | imm12 | + @ +------+-----------------+------+------+-------+ + @ + moveq r0, #0x400000 @ set bit 22, mov to mvn instruction + mov r3, r6, lsr #16 @ put offset bits 31-16 into r3 + mov r6, r6, lsr #24 @ put offset bits 31-24 into r6 + and r3, r3, #0xf0 @ only keep offset bits 23-20 in r3 + b .Lnext +.Lloop: ldr ip, [r7, r4] +#ifdef CONFIG_ARM_LPAE + tst ip, #PV_BIT24 @ ADD/SUB have bit 24 clear + beq 1f +ARM_BE8(rev ip, ip) + tst ip, #0xc00000 @ MOVW has bits 23:22 clear + bic ip, ip, #0x400000 @ clear bit 22 + bfc ip, #0, #12 @ clear imm12 field of MOV[W] instruction + orreq ip, ip, r6, lsl #4 @ MOVW -> mask in offset bits 31-24 + orreq ip, ip, r3, lsr #4 @ MOVW -> mask in offset bits 23-20 + orrne ip, ip, r0 @ MOV -> mask in offset bits 7-0 (or bit 22) +ARM_BE8(rev ip, ip) + b 2f +1: +#endif + tst ip, #PV_IMMR_MSB @ rotation value >= 16 ? + bic ip, ip, #PV_IMM8_MASK + orreq ip, ip, r6 ARM_BE8(, lsl #24) @ mask in offset bits 31-24 + orrne ip, ip, r3 ARM_BE8(, lsl #24) @ mask in offset bits 23-20 +2: + str ip, [r7, r4] + add r4, r4, #4 +#endif + +.Lnext: + cmp r4, r5 + ldrcc r7, [r4] @ use branch for delay slot + bcc .Lloop + ret lr +ENDPROC(__fixup_a_pv_table) + +ENTRY(fixup_pv_table) + stmfd sp!, {r4 - r7, lr} + mov r4, r0 @ r0 = table start + add r5, r0, r1 @ r1 = table size + bl __fixup_a_pv_table + ldmfd sp!, {r4 - r7, pc} +ENDPROC(fixup_pv_table) + + .data + .align 2 + .globl __pv_phys_pfn_offset + .type __pv_phys_pfn_offset, %object +__pv_phys_pfn_offset: + .word 0 + .size __pv_phys_pfn_offset, . -__pv_phys_pfn_offset + + .globl __pv_offset + .type __pv_offset, %object +__pv_offset: + .quad 0 + .size __pv_offset, . -__pv_offset diff --git a/arch/arm/kernel/pj4-cp0.c b/arch/arm/kernel/pj4-cp0.c new file mode 100644 index 000000000..1d1fb22f4 --- /dev/null +++ b/arch/arm/kernel/pj4-cp0.c @@ -0,0 +1,134 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/pj4-cp0.c + * + * PJ4 iWMMXt coprocessor context switching and handling + * + * Copyright (c) 2010 Marvell International Inc. + */ + +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/io.h> +#include <asm/thread_notify.h> +#include <asm/cputype.h> + +static int iwmmxt_do(struct notifier_block *self, unsigned long cmd, void *t) +{ + struct thread_info *thread = t; + + switch (cmd) { + case THREAD_NOTIFY_FLUSH: + /* + * flush_thread() zeroes thread->fpstate, so no need + * to do anything here. + * + * FALLTHROUGH: Ensure we don't try to overwrite our newly + * initialised state information on the first fault. + */ + + case THREAD_NOTIFY_EXIT: + iwmmxt_task_release(thread); + break; + + case THREAD_NOTIFY_SWITCH: + iwmmxt_task_switch(thread); + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block __maybe_unused iwmmxt_notifier_block = { + .notifier_call = iwmmxt_do, +}; + + +static u32 __init pj4_cp_access_read(void) +{ + u32 value; + + __asm__ __volatile__ ( + "mrc p15, 0, %0, c1, c0, 2\n\t" + : "=r" (value)); + return value; +} + +static void __init pj4_cp_access_write(u32 value) +{ + u32 temp; + + __asm__ __volatile__ ( + "mcr p15, 0, %1, c1, c0, 2\n\t" +#ifdef CONFIG_THUMB2_KERNEL + "isb\n\t" +#else + "mrc p15, 0, %0, c1, c0, 2\n\t" + "mov %0, %0\n\t" + "sub pc, pc, #4\n\t" +#endif + : "=r" (temp) : "r" (value)); +} + +static int __init pj4_get_iwmmxt_version(void) +{ + u32 cp_access, wcid; + + cp_access = pj4_cp_access_read(); + pj4_cp_access_write(cp_access | 0xf); + + /* check if coprocessor 0 and 1 are available */ + if ((pj4_cp_access_read() & 0xf) != 0xf) { + pj4_cp_access_write(cp_access); + return -ENODEV; + } + + /* read iWMMXt coprocessor id register p1, c0 */ + __asm__ __volatile__ ("mrc p1, 0, %0, c0, c0, 0\n" : "=r" (wcid)); + + pj4_cp_access_write(cp_access); + + /* iWMMXt v1 */ + if ((wcid & 0xffffff00) == 0x56051000) + return 1; + /* iWMMXt v2 */ + if ((wcid & 0xffffff00) == 0x56052000) + return 2; + + return -EINVAL; +} + +/* + * Disable CP0/CP1 on boot, and let call_fpe() and the iWMMXt lazy + * switch code handle iWMMXt context switching. + */ +static int __init pj4_cp0_init(void) +{ + u32 __maybe_unused cp_access; + int vers; + + if (!cpu_is_pj4()) + return 0; + + vers = pj4_get_iwmmxt_version(); + if (vers < 0) + return 0; + +#ifndef CONFIG_IWMMXT + pr_info("PJ4 iWMMXt coprocessor detected, but kernel support is missing.\n"); +#else + cp_access = pj4_cp_access_read() & ~0xf; + pj4_cp_access_write(cp_access); + + pr_info("PJ4 iWMMXt v%d coprocessor enabled.\n", vers); + elf_hwcap |= HWCAP_IWMMXT; + thread_register_notifier(&iwmmxt_notifier_block); +#endif + + return 0; +} + +late_initcall(pj4_cp0_init); diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c new file mode 100644 index 000000000..a2b31d91a --- /dev/null +++ b/arch/arm/kernel/process.c @@ -0,0 +1,444 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/process.c + * + * Copyright (C) 1996-2000 Russell King - Converted to ARM. + * Original Copyright (C) 1995 Linus Torvalds + */ +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/sched/debug.h> +#include <linux/sched/task.h> +#include <linux/sched/task_stack.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/stddef.h> +#include <linux/unistd.h> +#include <linux/user.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/elfcore.h> +#include <linux/pm.h> +#include <linux/tick.h> +#include <linux/utsname.h> +#include <linux/uaccess.h> +#include <linux/random.h> +#include <linux/hw_breakpoint.h> +#include <linux/leds.h> + +#include <asm/processor.h> +#include <asm/thread_notify.h> +#include <asm/stacktrace.h> +#include <asm/system_misc.h> +#include <asm/mach/time.h> +#include <asm/tls.h> +#include <asm/vdso.h> + +#include "signal.h" + +#if defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) || defined(CONFIG_SMP) +DEFINE_PER_CPU(struct task_struct *, __entry_task); +#endif + +#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK) +#include <linux/stackprotector.h> +unsigned long __stack_chk_guard __read_mostly; +EXPORT_SYMBOL(__stack_chk_guard); +#endif + +#ifndef CONFIG_CURRENT_POINTER_IN_TPIDRURO +asmlinkage struct task_struct *__current; +EXPORT_SYMBOL(__current); +#endif + +static const char *processor_modes[] __maybe_unused = { + "USER_26", "FIQ_26" , "IRQ_26" , "SVC_26" , "UK4_26" , "UK5_26" , "UK6_26" , "UK7_26" , + "UK8_26" , "UK9_26" , "UK10_26", "UK11_26", "UK12_26", "UK13_26", "UK14_26", "UK15_26", + "USER_32", "FIQ_32" , "IRQ_32" , "SVC_32" , "UK4_32" , "UK5_32" , "MON_32" , "ABT_32" , + "UK8_32" , "UK9_32" , "HYP_32", "UND_32" , "UK12_32", "UK13_32", "UK14_32", "SYS_32" +}; + +static const char *isa_modes[] __maybe_unused = { + "ARM" , "Thumb" , "Jazelle", "ThumbEE" +}; + +/* + * This is our default idle handler. + */ + +void (*arm_pm_idle)(void); + +/* + * Called from the core idle loop. + */ + +void arch_cpu_idle(void) +{ + if (arm_pm_idle) + arm_pm_idle(); + else + cpu_do_idle(); + raw_local_irq_enable(); +} + +void arch_cpu_idle_prepare(void) +{ + local_fiq_enable(); +} + +void arch_cpu_idle_enter(void) +{ + ledtrig_cpu(CPU_LED_IDLE_START); +#ifdef CONFIG_PL310_ERRATA_769419 + wmb(); +#endif +} + +void arch_cpu_idle_exit(void) +{ + ledtrig_cpu(CPU_LED_IDLE_END); +} + +void __show_regs_alloc_free(struct pt_regs *regs) +{ + int i; + + /* check for r0 - r12 only */ + for (i = 0; i < 13; i++) { + pr_alert("Register r%d information:", i); + mem_dump_obj((void *)regs->uregs[i]); + } +} + +void __show_regs(struct pt_regs *regs) +{ + unsigned long flags; + char buf[64]; +#ifndef CONFIG_CPU_V7M + unsigned int domain; +#ifdef CONFIG_CPU_SW_DOMAIN_PAN + /* + * Get the domain register for the parent context. In user + * mode, we don't save the DACR, so lets use what it should + * be. For other modes, we place it after the pt_regs struct. + */ + if (user_mode(regs)) { + domain = DACR_UACCESS_ENABLE; + } else { + domain = to_svc_pt_regs(regs)->dacr; + } +#else + domain = get_domain(); +#endif +#endif + + show_regs_print_info(KERN_DEFAULT); + + printk("PC is at %pS\n", (void *)instruction_pointer(regs)); + printk("LR is at %pS\n", (void *)regs->ARM_lr); + printk("pc : [<%08lx>] lr : [<%08lx>] psr: %08lx\n", + regs->ARM_pc, regs->ARM_lr, regs->ARM_cpsr); + printk("sp : %08lx ip : %08lx fp : %08lx\n", + regs->ARM_sp, regs->ARM_ip, regs->ARM_fp); + printk("r10: %08lx r9 : %08lx r8 : %08lx\n", + regs->ARM_r10, regs->ARM_r9, + regs->ARM_r8); + printk("r7 : %08lx r6 : %08lx r5 : %08lx r4 : %08lx\n", + regs->ARM_r7, regs->ARM_r6, + regs->ARM_r5, regs->ARM_r4); + printk("r3 : %08lx r2 : %08lx r1 : %08lx r0 : %08lx\n", + regs->ARM_r3, regs->ARM_r2, + regs->ARM_r1, regs->ARM_r0); + + flags = regs->ARM_cpsr; + buf[0] = flags & PSR_N_BIT ? 'N' : 'n'; + buf[1] = flags & PSR_Z_BIT ? 'Z' : 'z'; + buf[2] = flags & PSR_C_BIT ? 'C' : 'c'; + buf[3] = flags & PSR_V_BIT ? 'V' : 'v'; + buf[4] = '\0'; + +#ifndef CONFIG_CPU_V7M + { + const char *segment; + + if ((domain & domain_mask(DOMAIN_USER)) == + domain_val(DOMAIN_USER, DOMAIN_NOACCESS)) + segment = "none"; + else + segment = "user"; + + printk("Flags: %s IRQs o%s FIQs o%s Mode %s ISA %s Segment %s\n", + buf, interrupts_enabled(regs) ? "n" : "ff", + fast_interrupts_enabled(regs) ? "n" : "ff", + processor_modes[processor_mode(regs)], + isa_modes[isa_mode(regs)], segment); + } +#else + printk("xPSR: %08lx\n", regs->ARM_cpsr); +#endif + +#ifdef CONFIG_CPU_CP15 + { + unsigned int ctrl; + + buf[0] = '\0'; +#ifdef CONFIG_CPU_CP15_MMU + { + unsigned int transbase; + asm("mrc p15, 0, %0, c2, c0\n\t" + : "=r" (transbase)); + snprintf(buf, sizeof(buf), " Table: %08x DAC: %08x", + transbase, domain); + } +#endif + asm("mrc p15, 0, %0, c1, c0\n" : "=r" (ctrl)); + + printk("Control: %08x%s\n", ctrl, buf); + } +#endif +} + +void show_regs(struct pt_regs * regs) +{ + __show_regs(regs); + dump_backtrace(regs, NULL, KERN_DEFAULT); +} + +ATOMIC_NOTIFIER_HEAD(thread_notify_head); + +EXPORT_SYMBOL_GPL(thread_notify_head); + +/* + * Free current thread data structures etc.. + */ +void exit_thread(struct task_struct *tsk) +{ + thread_notify(THREAD_NOTIFY_EXIT, task_thread_info(tsk)); +} + +void flush_thread(void) +{ + struct thread_info *thread = current_thread_info(); + struct task_struct *tsk = current; + + flush_ptrace_hw_breakpoint(tsk); + + memset(thread->used_cp, 0, sizeof(thread->used_cp)); + memset(&tsk->thread.debug, 0, sizeof(struct debug_info)); + memset(&thread->fpstate, 0, sizeof(union fp_state)); + + flush_tls(); + + thread_notify(THREAD_NOTIFY_FLUSH, thread); +} + +asmlinkage void ret_from_fork(void) __asm__("ret_from_fork"); + +int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) +{ + unsigned long clone_flags = args->flags; + unsigned long stack_start = args->stack; + unsigned long tls = args->tls; + struct thread_info *thread = task_thread_info(p); + struct pt_regs *childregs = task_pt_regs(p); + + memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save)); + +#ifdef CONFIG_CPU_USE_DOMAINS + /* + * Copy the initial value of the domain access control register + * from the current thread: thread->addr_limit will have been + * copied from the current thread via setup_thread_stack() in + * kernel/fork.c + */ + thread->cpu_domain = get_domain(); +#endif + + if (likely(!args->fn)) { + *childregs = *current_pt_regs(); + childregs->ARM_r0 = 0; + if (stack_start) + childregs->ARM_sp = stack_start; + } else { + memset(childregs, 0, sizeof(struct pt_regs)); + thread->cpu_context.r4 = (unsigned long)args->fn_arg; + thread->cpu_context.r5 = (unsigned long)args->fn; + childregs->ARM_cpsr = SVC_MODE; + } + thread->cpu_context.pc = (unsigned long)ret_from_fork; + thread->cpu_context.sp = (unsigned long)childregs; + + clear_ptrace_hw_breakpoint(p); + + if (clone_flags & CLONE_SETTLS) + thread->tp_value[0] = tls; + thread->tp_value[1] = get_tpuser(); + + thread_notify(THREAD_NOTIFY_COPY, thread); + + return 0; +} + +unsigned long __get_wchan(struct task_struct *p) +{ + struct stackframe frame; + unsigned long stack_page; + int count = 0; + + frame.fp = thread_saved_fp(p); + frame.sp = thread_saved_sp(p); + frame.lr = 0; /* recovered from the stack */ + frame.pc = thread_saved_pc(p); + stack_page = (unsigned long)task_stack_page(p); + do { + if (frame.sp < stack_page || + frame.sp >= stack_page + THREAD_SIZE || + unwind_frame(&frame) < 0) + return 0; + if (!in_sched_functions(frame.pc)) + return frame.pc; + } while (count ++ < 16); + return 0; +} + +#ifdef CONFIG_MMU +#ifdef CONFIG_KUSER_HELPERS +/* + * The vectors page is always readable from user space for the + * atomic helpers. Insert it into the gate_vma so that it is visible + * through ptrace and /proc/<pid>/mem. + */ +static struct vm_area_struct gate_vma; + +static int __init gate_vma_init(void) +{ + vma_init(&gate_vma, NULL); + gate_vma.vm_page_prot = PAGE_READONLY_EXEC; + gate_vma.vm_start = 0xffff0000; + gate_vma.vm_end = 0xffff0000 + PAGE_SIZE; + gate_vma.vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYEXEC; + return 0; +} +arch_initcall(gate_vma_init); + +struct vm_area_struct *get_gate_vma(struct mm_struct *mm) +{ + return &gate_vma; +} + +int in_gate_area(struct mm_struct *mm, unsigned long addr) +{ + return (addr >= gate_vma.vm_start) && (addr < gate_vma.vm_end); +} + +int in_gate_area_no_mm(unsigned long addr) +{ + return in_gate_area(NULL, addr); +} +#define is_gate_vma(vma) ((vma) == &gate_vma) +#else +#define is_gate_vma(vma) 0 +#endif + +const char *arch_vma_name(struct vm_area_struct *vma) +{ + return is_gate_vma(vma) ? "[vectors]" : NULL; +} + +/* If possible, provide a placement hint at a random offset from the + * stack for the sigpage and vdso pages. + */ +static unsigned long sigpage_addr(const struct mm_struct *mm, + unsigned int npages) +{ + unsigned long offset; + unsigned long first; + unsigned long last; + unsigned long addr; + unsigned int slots; + + first = PAGE_ALIGN(mm->start_stack); + + last = TASK_SIZE - (npages << PAGE_SHIFT); + + /* No room after stack? */ + if (first > last) + return 0; + + /* Just enough room? */ + if (first == last) + return first; + + slots = ((last - first) >> PAGE_SHIFT) + 1; + + offset = prandom_u32_max(slots); + + addr = first + (offset << PAGE_SHIFT); + + return addr; +} + +static struct page *signal_page; +extern struct page *get_signal_page(void); + +static int sigpage_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + current->mm->context.sigpage = new_vma->vm_start; + return 0; +} + +static const struct vm_special_mapping sigpage_mapping = { + .name = "[sigpage]", + .pages = &signal_page, + .mremap = sigpage_mremap, +}; + +int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp) +{ + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long npages; + unsigned long addr; + unsigned long hint; + int ret = 0; + + if (!signal_page) + signal_page = get_signal_page(); + if (!signal_page) + return -ENOMEM; + + npages = 1; /* for sigpage */ + npages += vdso_total_pages; + + if (mmap_write_lock_killable(mm)) + return -EINTR; + hint = sigpage_addr(mm, npages); + addr = get_unmapped_area(NULL, hint, npages << PAGE_SHIFT, 0, 0); + if (IS_ERR_VALUE(addr)) { + ret = addr; + goto up_fail; + } + + vma = _install_special_mapping(mm, addr, PAGE_SIZE, + VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, + &sigpage_mapping); + + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto up_fail; + } + + mm->context.sigpage = addr; + + /* Unlike the sigpage, failure to install the vdso is unlikely + * to be fatal to the process, so no error check needed + * here. + */ + arm_install_vdso(mm, addr + PAGE_SIZE); + + up_fail: + mmap_write_unlock(mm); + return ret; +} +#endif diff --git a/arch/arm/kernel/psci_smp.c b/arch/arm/kernel/psci_smp.c new file mode 100644 index 000000000..d4392e177 --- /dev/null +++ b/arch/arm/kernel/psci_smp.c @@ -0,0 +1,123 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * + * Copyright (C) 2012 ARM Limited + * + * Author: Will Deacon <will.deacon@arm.com> + */ + +#include <linux/init.h> +#include <linux/smp.h> +#include <linux/of.h> +#include <linux/delay.h> +#include <linux/psci.h> + +#include <uapi/linux/psci.h> + +#include <asm/psci.h> +#include <asm/smp_plat.h> + +/* + * psci_smp assumes that the following is true about PSCI: + * + * cpu_suspend Suspend the execution on a CPU + * @state we don't currently describe affinity levels, so just pass 0. + * @entry_point the first instruction to be executed on return + * returns 0 success, < 0 on failure + * + * cpu_off Power down a CPU + * @state we don't currently describe affinity levels, so just pass 0. + * no return on successful call + * + * cpu_on Power up a CPU + * @cpuid cpuid of target CPU, as from MPIDR + * @entry_point the first instruction to be executed on return + * returns 0 success, < 0 on failure + * + * migrate Migrate the context to a different CPU + * @cpuid cpuid of target CPU, as from MPIDR + * returns 0 success, < 0 on failure + * + */ + +extern void secondary_startup(void); + +static int psci_boot_secondary(unsigned int cpu, struct task_struct *idle) +{ + if (psci_ops.cpu_on) + return psci_ops.cpu_on(cpu_logical_map(cpu), + virt_to_idmap(&secondary_startup)); + return -ENODEV; +} + +#ifdef CONFIG_HOTPLUG_CPU +static int psci_cpu_disable(unsigned int cpu) +{ + /* Fail early if we don't have CPU_OFF support */ + if (!psci_ops.cpu_off) + return -EOPNOTSUPP; + + /* Trusted OS will deny CPU_OFF */ + if (psci_tos_resident_on(cpu)) + return -EPERM; + + return 0; +} + +static void psci_cpu_die(unsigned int cpu) +{ + u32 state = PSCI_POWER_STATE_TYPE_POWER_DOWN << + PSCI_0_2_POWER_STATE_TYPE_SHIFT; + + if (psci_ops.cpu_off) + psci_ops.cpu_off(state); + + /* We should never return */ + panic("psci: cpu %d failed to shutdown\n", cpu); +} + +static int psci_cpu_kill(unsigned int cpu) +{ + int err, i; + + if (!psci_ops.affinity_info) + return 1; + /* + * cpu_kill could race with cpu_die and we can + * potentially end up declaring this cpu undead + * while it is dying. So, try again a few times. + */ + + for (i = 0; i < 10; i++) { + err = psci_ops.affinity_info(cpu_logical_map(cpu), 0); + if (err == PSCI_0_2_AFFINITY_LEVEL_OFF) { + pr_info("CPU%d killed.\n", cpu); + return 1; + } + + msleep(10); + pr_info("Retrying again to check for CPU kill\n"); + } + + pr_warn("CPU%d may not have shut down cleanly (AFFINITY_INFO reports %d)\n", + cpu, err); + /* Make platform_cpu_kill() fail. */ + return 0; +} + +#endif + +bool __init psci_smp_available(void) +{ + /* is cpu_on available at least? */ + return (psci_ops.cpu_on != NULL); +} + +const struct smp_operations psci_smp_ops __initconst = { + .smp_boot_secondary = psci_boot_secondary, +#ifdef CONFIG_HOTPLUG_CPU + .cpu_disable = psci_cpu_disable, + .cpu_die = psci_cpu_die, + .cpu_kill = psci_cpu_kill, +#endif +}; diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c new file mode 100644 index 000000000..cef106913 --- /dev/null +++ b/arch/arm/kernel/ptrace.c @@ -0,0 +1,900 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/ptrace.c + * + * By Ross Biro 1/23/92 + * edited by Linus Torvalds + * ARM modifications Copyright (C) 2000 Russell King + */ +#include <linux/kernel.h> +#include <linux/sched/signal.h> +#include <linux/sched/task_stack.h> +#include <linux/mm.h> +#include <linux/elf.h> +#include <linux/smp.h> +#include <linux/ptrace.h> +#include <linux/user.h> +#include <linux/security.h> +#include <linux/init.h> +#include <linux/signal.h> +#include <linux/uaccess.h> +#include <linux/perf_event.h> +#include <linux/hw_breakpoint.h> +#include <linux/regset.h> +#include <linux/audit.h> +#include <linux/unistd.h> + +#include <asm/syscall.h> +#include <asm/traps.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/syscalls.h> + +#define REG_PC 15 +#define REG_PSR 16 +/* + * does not yet catch signals sent when the child dies. + * in exit.c or in signal.c. + */ + +#if 0 +/* + * Breakpoint SWI instruction: SWI &9F0001 + */ +#define BREAKINST_ARM 0xef9f0001 +#define BREAKINST_THUMB 0xdf00 /* fill this in later */ +#else +/* + * New breakpoints - use an undefined instruction. The ARM architecture + * reference manual guarantees that the following instruction space + * will produce an undefined instruction exception on all CPUs: + * + * ARM: xxxx 0111 1111 xxxx xxxx xxxx 1111 xxxx + * Thumb: 1101 1110 xxxx xxxx + */ +#define BREAKINST_ARM 0xe7f001f0 +#define BREAKINST_THUMB 0xde01 +#endif + +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) \ + {.name = #r, .offset = offsetof(struct pt_regs, ARM_##r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} + +static const struct pt_regs_offset regoffset_table[] = { + 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(fp), + REG_OFFSET_NAME(ip), + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(lr), + REG_OFFSET_NAME(pc), + REG_OFFSET_NAME(cpsr), + REG_OFFSET_NAME(ORIG_r0), + REG_OFFSET_END, +}; + +/** + * regs_query_register_offset() - query register offset from its name + * @name: the name of a register + * + * regs_query_register_offset() returns the offset of a register in struct + * pt_regs from its name. If the name is invalid, this returns -EINVAL; + */ +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; +} + +/** + * regs_query_register_name() - query register name from its offset + * @offset: the offset of a register in struct pt_regs. + * + * regs_query_register_name() returns the name of a register from its + * offset in struct pt_regs. If the @offset is invalid, this returns NULL; + */ +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; +} + +/** + * regs_within_kernel_stack() - check the address in the stack + * @regs: pt_regs which contains kernel stack pointer. + * @addr: address which is checked. + * + * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). + * If @addr is within the kernel stack, it returns true. If not, returns false. + */ +bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) +{ + return ((addr & ~(THREAD_SIZE - 1)) == + (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))); +} + +/** + * regs_get_kernel_stack_nth() - get Nth entry of the stack + * @regs: pt_regs which contains kernel stack pointer. + * @n: stack entry number. + * + * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which + * is specified by @regs. If the @n th entry is NOT in the kernel stack, + * this returns 0. + */ +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; +} + +/* + * this routine will get a word off of the processes privileged stack. + * the offset is how far from the base addr as stored in the THREAD. + * this routine assumes that all the privileged stacks are in our + * data space. + */ +static inline long get_user_reg(struct task_struct *task, int offset) +{ + return task_pt_regs(task)->uregs[offset]; +} + +/* + * this routine will put a word on the processes privileged stack. + * the offset is how far from the base addr as stored in the THREAD. + * this routine assumes that all the privileged stacks are in our + * data space. + */ +static inline int +put_user_reg(struct task_struct *task, int offset, long data) +{ + struct pt_regs newregs, *regs = task_pt_regs(task); + int ret = -EINVAL; + + newregs = *regs; + newregs.uregs[offset] = data; + + if (valid_user_regs(&newregs)) { + regs->uregs[offset] = data; + ret = 0; + } + + return ret; +} + +/* + * Called by kernel/ptrace.c when detaching.. + */ +void ptrace_disable(struct task_struct *child) +{ + /* Nothing to do. */ +} + +/* + * Handle hitting a breakpoint. + */ +void ptrace_break(struct pt_regs *regs) +{ + force_sig_fault(SIGTRAP, TRAP_BRKPT, + (void __user *)instruction_pointer(regs)); +} + +static int break_trap(struct pt_regs *regs, unsigned int instr) +{ + ptrace_break(regs); + return 0; +} + +static struct undef_hook arm_break_hook = { + .instr_mask = 0x0fffffff, + .instr_val = 0x07f001f0, + .cpsr_mask = PSR_T_BIT, + .cpsr_val = 0, + .fn = break_trap, +}; + +static struct undef_hook thumb_break_hook = { + .instr_mask = 0xffffffff, + .instr_val = 0x0000de01, + .cpsr_mask = PSR_T_BIT, + .cpsr_val = PSR_T_BIT, + .fn = break_trap, +}; + +static struct undef_hook thumb2_break_hook = { + .instr_mask = 0xffffffff, + .instr_val = 0xf7f0a000, + .cpsr_mask = PSR_T_BIT, + .cpsr_val = PSR_T_BIT, + .fn = break_trap, +}; + +static int __init ptrace_break_init(void) +{ + register_undef_hook(&arm_break_hook); + register_undef_hook(&thumb_break_hook); + register_undef_hook(&thumb2_break_hook); + return 0; +} + +core_initcall(ptrace_break_init); + +/* + * Read the word at offset "off" into the "struct user". We + * actually access the pt_regs stored on the kernel stack. + */ +static int ptrace_read_user(struct task_struct *tsk, unsigned long off, + unsigned long __user *ret) +{ + unsigned long tmp; + + if (off & 3) + return -EIO; + + tmp = 0; + if (off == PT_TEXT_ADDR) + tmp = tsk->mm->start_code; + else if (off == PT_DATA_ADDR) + tmp = tsk->mm->start_data; + else if (off == PT_TEXT_END_ADDR) + tmp = tsk->mm->end_code; + else if (off < sizeof(struct pt_regs)) + tmp = get_user_reg(tsk, off >> 2); + else if (off >= sizeof(struct user)) + return -EIO; + + return put_user(tmp, ret); +} + +/* + * Write the word at offset "off" into "struct user". We + * actually access the pt_regs stored on the kernel stack. + */ +static int ptrace_write_user(struct task_struct *tsk, unsigned long off, + unsigned long val) +{ + if (off & 3 || off >= sizeof(struct user)) + return -EIO; + + if (off >= sizeof(struct pt_regs)) + return 0; + + return put_user_reg(tsk, off >> 2, val); +} + +#ifdef CONFIG_IWMMXT + +/* + * Get the child iWMMXt state. + */ +static int ptrace_getwmmxregs(struct task_struct *tsk, void __user *ufp) +{ + struct thread_info *thread = task_thread_info(tsk); + + if (!test_ti_thread_flag(thread, TIF_USING_IWMMXT)) + return -ENODATA; + iwmmxt_task_disable(thread); /* force it to ram */ + return copy_to_user(ufp, &thread->fpstate.iwmmxt, IWMMXT_SIZE) + ? -EFAULT : 0; +} + +/* + * Set the child iWMMXt state. + */ +static int ptrace_setwmmxregs(struct task_struct *tsk, void __user *ufp) +{ + struct thread_info *thread = task_thread_info(tsk); + + if (!test_ti_thread_flag(thread, TIF_USING_IWMMXT)) + return -EACCES; + iwmmxt_task_release(thread); /* force a reload */ + return copy_from_user(&thread->fpstate.iwmmxt, ufp, IWMMXT_SIZE) + ? -EFAULT : 0; +} + +#endif + +#ifdef CONFIG_HAVE_HW_BREAKPOINT +/* + * Convert a virtual register number into an index for a thread_info + * breakpoint array. Breakpoints are identified using positive numbers + * whilst watchpoints are negative. The registers are laid out as pairs + * of (address, control), each pair mapping to a unique hw_breakpoint struct. + * Register 0 is reserved for describing resource information. + */ +static int ptrace_hbp_num_to_idx(long num) +{ + if (num < 0) + num = (ARM_MAX_BRP << 1) - num; + return (num - 1) >> 1; +} + +/* + * Returns the virtual register number for the address of the + * breakpoint at index idx. + */ +static long ptrace_hbp_idx_to_num(int idx) +{ + long mid = ARM_MAX_BRP << 1; + long num = (idx << 1) + 1; + return num > mid ? mid - num : num; +} + +/* + * Handle hitting a HW-breakpoint. + */ +static void ptrace_hbptriggered(struct perf_event *bp, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp); + long num; + int i; + + for (i = 0; i < ARM_MAX_HBP_SLOTS; ++i) + if (current->thread.debug.hbp[i] == bp) + break; + + num = (i == ARM_MAX_HBP_SLOTS) ? 0 : ptrace_hbp_idx_to_num(i); + + force_sig_ptrace_errno_trap((int)num, (void __user *)(bkpt->trigger)); +} + +/* + * Set ptrace breakpoint pointers to zero for this task. + * This is required in order to prevent child processes from unregistering + * breakpoints held by their parent. + */ +void clear_ptrace_hw_breakpoint(struct task_struct *tsk) +{ + memset(tsk->thread.debug.hbp, 0, sizeof(tsk->thread.debug.hbp)); +} + +/* + * Unregister breakpoints from this task and reset the pointers in + * the thread_struct. + */ +void flush_ptrace_hw_breakpoint(struct task_struct *tsk) +{ + int i; + struct thread_struct *t = &tsk->thread; + + for (i = 0; i < ARM_MAX_HBP_SLOTS; i++) { + if (t->debug.hbp[i]) { + unregister_hw_breakpoint(t->debug.hbp[i]); + t->debug.hbp[i] = NULL; + } + } +} + +static u32 ptrace_get_hbp_resource_info(void) +{ + u8 num_brps, num_wrps, debug_arch, wp_len; + u32 reg = 0; + + num_brps = hw_breakpoint_slots(TYPE_INST); + num_wrps = hw_breakpoint_slots(TYPE_DATA); + debug_arch = arch_get_debug_arch(); + wp_len = arch_get_max_wp_len(); + + reg |= debug_arch; + reg <<= 8; + reg |= wp_len; + reg <<= 8; + reg |= num_wrps; + reg <<= 8; + reg |= num_brps; + + return reg; +} + +static struct perf_event *ptrace_hbp_create(struct task_struct *tsk, int type) +{ + struct perf_event_attr attr; + + ptrace_breakpoint_init(&attr); + + /* Initialise fields to sane defaults. */ + attr.bp_addr = 0; + attr.bp_len = HW_BREAKPOINT_LEN_4; + attr.bp_type = type; + attr.disabled = 1; + + return register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL, + tsk); +} + +static int ptrace_gethbpregs(struct task_struct *tsk, long num, + unsigned long __user *data) +{ + u32 reg; + int idx, ret = 0; + struct perf_event *bp; + struct arch_hw_breakpoint_ctrl arch_ctrl; + + if (num == 0) { + reg = ptrace_get_hbp_resource_info(); + } else { + idx = ptrace_hbp_num_to_idx(num); + if (idx < 0 || idx >= ARM_MAX_HBP_SLOTS) { + ret = -EINVAL; + goto out; + } + + bp = tsk->thread.debug.hbp[idx]; + if (!bp) { + reg = 0; + goto put; + } + + arch_ctrl = counter_arch_bp(bp)->ctrl; + + /* + * Fix up the len because we may have adjusted it + * to compensate for an unaligned address. + */ + while (!(arch_ctrl.len & 0x1)) + arch_ctrl.len >>= 1; + + if (num & 0x1) + reg = bp->attr.bp_addr; + else + reg = encode_ctrl_reg(arch_ctrl); + } + +put: + if (put_user(reg, data)) + ret = -EFAULT; + +out: + return ret; +} + +static int ptrace_sethbpregs(struct task_struct *tsk, long num, + unsigned long __user *data) +{ + int idx, gen_len, gen_type, implied_type, ret = 0; + u32 user_val; + struct perf_event *bp; + struct arch_hw_breakpoint_ctrl ctrl; + struct perf_event_attr attr; + + if (num == 0) + goto out; + else if (num < 0) + implied_type = HW_BREAKPOINT_RW; + else + implied_type = HW_BREAKPOINT_X; + + idx = ptrace_hbp_num_to_idx(num); + if (idx < 0 || idx >= ARM_MAX_HBP_SLOTS) { + ret = -EINVAL; + goto out; + } + + if (get_user(user_val, data)) { + ret = -EFAULT; + goto out; + } + + bp = tsk->thread.debug.hbp[idx]; + if (!bp) { + bp = ptrace_hbp_create(tsk, implied_type); + if (IS_ERR(bp)) { + ret = PTR_ERR(bp); + goto out; + } + tsk->thread.debug.hbp[idx] = bp; + } + + attr = bp->attr; + + if (num & 0x1) { + /* Address */ + attr.bp_addr = user_val; + } else { + /* Control */ + decode_ctrl_reg(user_val, &ctrl); + ret = arch_bp_generic_fields(ctrl, &gen_len, &gen_type); + if (ret) + goto out; + + if ((gen_type & implied_type) != gen_type) { + ret = -EINVAL; + goto out; + } + + attr.bp_len = gen_len; + attr.bp_type = gen_type; + attr.disabled = !ctrl.enabled; + } + + ret = modify_user_hw_breakpoint(bp, &attr); +out: + return ret; +} +#endif + +/* regset get/set implementations */ + +static int gpr_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + return membuf_write(&to, task_pt_regs(target), sizeof(struct pt_regs)); +} + +static int gpr_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct pt_regs newregs = *task_pt_regs(target); + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &newregs, + 0, sizeof(newregs)); + if (ret) + return ret; + + if (!valid_user_regs(&newregs)) + return -EINVAL; + + *task_pt_regs(target) = newregs; + return 0; +} + +static int fpa_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + return membuf_write(&to, &task_thread_info(target)->fpstate, + sizeof(struct user_fp)); +} + +static int fpa_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + struct thread_info *thread = task_thread_info(target); + + thread->used_cp[1] = thread->used_cp[2] = 1; + + return user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &thread->fpstate, + 0, sizeof(struct user_fp)); +} + +#ifdef CONFIG_VFP +/* + * VFP register get/set implementations. + * + * With respect to the kernel, struct user_fp is divided into three chunks: + * 16 or 32 real VFP registers (d0-d15 or d0-31) + * These are transferred to/from the real registers in the task's + * vfp_hard_struct. The number of registers depends on the kernel + * configuration. + * + * 16 or 0 fake VFP registers (d16-d31 or empty) + * i.e., the user_vfp structure has space for 32 registers even if + * the kernel doesn't have them all. + * + * vfp_get() reads this chunk as zero where applicable + * vfp_set() ignores this chunk + * + * 1 word for the FPSCR + */ +static int vfp_get(struct task_struct *target, + const struct user_regset *regset, + struct membuf to) +{ + struct thread_info *thread = task_thread_info(target); + struct vfp_hard_struct const *vfp = &thread->vfpstate.hard; + const size_t user_fpscr_offset = offsetof(struct user_vfp, fpscr); + + vfp_sync_hwstate(thread); + + membuf_write(&to, vfp->fpregs, sizeof(vfp->fpregs)); + membuf_zero(&to, user_fpscr_offset - sizeof(vfp->fpregs)); + return membuf_store(&to, vfp->fpscr); +} + +/* + * For vfp_set() a read-modify-write is done on the VFP registers, + * in order to avoid writing back a half-modified set of registers on + * failure. + */ +static int vfp_set(struct task_struct *target, + const struct user_regset *regset, + unsigned int pos, unsigned int count, + const void *kbuf, const void __user *ubuf) +{ + int ret; + struct thread_info *thread = task_thread_info(target); + struct vfp_hard_struct new_vfp; + const size_t user_fpregs_offset = offsetof(struct user_vfp, fpregs); + const size_t user_fpscr_offset = offsetof(struct user_vfp, fpscr); + + vfp_sync_hwstate(thread); + new_vfp = thread->vfpstate.hard; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &new_vfp.fpregs, + user_fpregs_offset, + user_fpregs_offset + sizeof(new_vfp.fpregs)); + if (ret) + return ret; + + ret = user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, + user_fpregs_offset + sizeof(new_vfp.fpregs), + user_fpscr_offset); + if (ret) + return ret; + + ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, + &new_vfp.fpscr, + user_fpscr_offset, + user_fpscr_offset + sizeof(new_vfp.fpscr)); + if (ret) + return ret; + + thread->vfpstate.hard = new_vfp; + vfp_flush_hwstate(thread); + + return 0; +} +#endif /* CONFIG_VFP */ + +enum arm_regset { + REGSET_GPR, + REGSET_FPR, +#ifdef CONFIG_VFP + REGSET_VFP, +#endif +}; + +static const struct user_regset arm_regsets[] = { + [REGSET_GPR] = { + .core_note_type = NT_PRSTATUS, + .n = ELF_NGREG, + .size = sizeof(u32), + .align = sizeof(u32), + .regset_get = gpr_get, + .set = gpr_set + }, + [REGSET_FPR] = { + /* + * For the FPA regs in fpstate, the real fields are a mixture + * of sizes, so pretend that the registers are word-sized: + */ + .core_note_type = NT_PRFPREG, + .n = sizeof(struct user_fp) / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .regset_get = fpa_get, + .set = fpa_set + }, +#ifdef CONFIG_VFP + [REGSET_VFP] = { + /* + * Pretend that the VFP regs are word-sized, since the FPSCR is + * a single word dangling at the end of struct user_vfp: + */ + .core_note_type = NT_ARM_VFP, + .n = ARM_VFPREGS_SIZE / sizeof(u32), + .size = sizeof(u32), + .align = sizeof(u32), + .regset_get = vfp_get, + .set = vfp_set + }, +#endif /* CONFIG_VFP */ +}; + +static const struct user_regset_view user_arm_view = { + .name = "arm", .e_machine = ELF_ARCH, .ei_osabi = ELF_OSABI, + .regsets = arm_regsets, .n = ARRAY_SIZE(arm_regsets) +}; + +const struct user_regset_view *task_user_regset_view(struct task_struct *task) +{ + return &user_arm_view; +} + +long arch_ptrace(struct task_struct *child, long request, + unsigned long addr, unsigned long data) +{ + int ret; + unsigned long __user *datap = (unsigned long __user *) data; + + switch (request) { + case PTRACE_PEEKUSR: + ret = ptrace_read_user(child, addr, datap); + break; + + case PTRACE_POKEUSR: + ret = ptrace_write_user(child, addr, data); + break; + + case PTRACE_GETREGS: + ret = copy_regset_to_user(child, + &user_arm_view, REGSET_GPR, + 0, sizeof(struct pt_regs), + datap); + break; + + case PTRACE_SETREGS: + ret = copy_regset_from_user(child, + &user_arm_view, REGSET_GPR, + 0, sizeof(struct pt_regs), + datap); + break; + + case PTRACE_GETFPREGS: + ret = copy_regset_to_user(child, + &user_arm_view, REGSET_FPR, + 0, sizeof(union fp_state), + datap); + break; + + case PTRACE_SETFPREGS: + ret = copy_regset_from_user(child, + &user_arm_view, REGSET_FPR, + 0, sizeof(union fp_state), + datap); + break; + +#ifdef CONFIG_IWMMXT + case PTRACE_GETWMMXREGS: + ret = ptrace_getwmmxregs(child, datap); + break; + + case PTRACE_SETWMMXREGS: + ret = ptrace_setwmmxregs(child, datap); + break; +#endif + + case PTRACE_GET_THREAD_AREA: + ret = put_user(task_thread_info(child)->tp_value[0], + datap); + break; + + case PTRACE_SET_SYSCALL: + if (data != -1) + data &= __NR_SYSCALL_MASK; + task_thread_info(child)->abi_syscall = data; + ret = 0; + break; + +#ifdef CONFIG_VFP + case PTRACE_GETVFPREGS: + ret = copy_regset_to_user(child, + &user_arm_view, REGSET_VFP, + 0, ARM_VFPREGS_SIZE, + datap); + break; + + case PTRACE_SETVFPREGS: + ret = copy_regset_from_user(child, + &user_arm_view, REGSET_VFP, + 0, ARM_VFPREGS_SIZE, + datap); + break; +#endif + +#ifdef CONFIG_HAVE_HW_BREAKPOINT + case PTRACE_GETHBPREGS: + ret = ptrace_gethbpregs(child, addr, + (unsigned long __user *)data); + break; + case PTRACE_SETHBPREGS: + ret = ptrace_sethbpregs(child, addr, + (unsigned long __user *)data); + break; +#endif + + default: + ret = ptrace_request(child, request, addr, data); + break; + } + + return ret; +} + +enum ptrace_syscall_dir { + PTRACE_SYSCALL_ENTER = 0, + PTRACE_SYSCALL_EXIT, +}; + +static void report_syscall(struct pt_regs *regs, enum ptrace_syscall_dir dir) +{ + unsigned long ip; + + /* + * IP is used to denote syscall entry/exit: + * IP = 0 -> entry, =1 -> exit + */ + ip = regs->ARM_ip; + regs->ARM_ip = dir; + + if (dir == PTRACE_SYSCALL_EXIT) + ptrace_report_syscall_exit(regs, 0); + else if (ptrace_report_syscall_entry(regs)) + current_thread_info()->abi_syscall = -1; + + regs->ARM_ip = ip; +} + +asmlinkage int syscall_trace_enter(struct pt_regs *regs) +{ + int scno; + + if (test_thread_flag(TIF_SYSCALL_TRACE)) + report_syscall(regs, PTRACE_SYSCALL_ENTER); + + /* Do seccomp after ptrace; syscall may have changed. */ +#ifdef CONFIG_HAVE_ARCH_SECCOMP_FILTER + if (secure_computing() == -1) + return -1; +#else + /* XXX: remove this once OABI gets fixed */ + secure_computing_strict(syscall_get_nr(current, regs)); +#endif + + /* Tracer or seccomp may have changed syscall. */ + scno = syscall_get_nr(current, regs); + + if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) + trace_sys_enter(regs, scno); + + audit_syscall_entry(scno, regs->ARM_r0, regs->ARM_r1, regs->ARM_r2, + regs->ARM_r3); + + return scno; +} + +asmlinkage void syscall_trace_exit(struct pt_regs *regs) +{ + /* + * Audit the syscall before anything else, as a debugger may + * come in and change the current registers. + */ + audit_syscall_exit(regs); + + /* + * Note that we haven't updated the ->syscall field for the + * current thread. This isn't a problem because it will have + * been set on syscall entry and there hasn't been an opportunity + * for a PTRACE_SET_SYSCALL since then. + */ + if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) + trace_sys_exit(regs, regs_return_value(regs)); + + if (test_thread_flag(TIF_SYSCALL_TRACE)) + report_syscall(regs, PTRACE_SYSCALL_EXIT); +} diff --git a/arch/arm/kernel/reboot.c b/arch/arm/kernel/reboot.c new file mode 100644 index 000000000..3f0d5c3da --- /dev/null +++ b/arch/arm/kernel/reboot.c @@ -0,0 +1,147 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 1996-2000 Russell King - Converted to ARM. + * Original Copyright (C) 1995 Linus Torvalds + */ +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/reboot.h> + +#include <asm/cacheflush.h> +#include <asm/idmap.h> +#include <asm/virt.h> +#include <asm/system_misc.h> + +#include "reboot.h" + +typedef void (*phys_reset_t)(unsigned long, bool); + +/* + * Function pointers to optional machine specific functions + */ +void (*pm_power_off)(void); +EXPORT_SYMBOL(pm_power_off); + +/* + * A temporary stack to use for CPU reset. This is static so that we + * don't clobber it with the identity mapping. When running with this + * stack, any references to the current task *will not work* so you + * should really do as little as possible before jumping to your reset + * code. + */ +static u64 soft_restart_stack[16]; + +static void __soft_restart(void *addr) +{ + phys_reset_t phys_reset; + + /* Take out a flat memory mapping. */ + setup_mm_for_reboot(); + + /* Clean and invalidate caches */ + flush_cache_all(); + + /* Turn off caching */ + cpu_proc_fin(); + + /* Push out any further dirty data, and ensure cache is empty */ + flush_cache_all(); + + /* Switch to the identity mapping. */ + phys_reset = (phys_reset_t)virt_to_idmap(cpu_reset); + + /* original stub should be restored by kvm */ + phys_reset((unsigned long)addr, is_hyp_mode_available()); + + /* Should never get here. */ + BUG(); +} + +void _soft_restart(unsigned long addr, bool disable_l2) +{ + u64 *stack = soft_restart_stack + ARRAY_SIZE(soft_restart_stack); + + /* Disable interrupts first */ + raw_local_irq_disable(); + local_fiq_disable(); + + /* Disable the L2 if we're the last man standing. */ + if (disable_l2) + outer_disable(); + + /* Change to the new stack and continue with the reset. */ + call_with_stack(__soft_restart, (void *)addr, (void *)stack); + + /* Should never get here. */ + BUG(); +} + +void soft_restart(unsigned long addr) +{ + _soft_restart(addr, num_online_cpus() == 1); +} + +/* + * Called by kexec, immediately prior to machine_kexec(). + * + * This must completely disable all secondary CPUs; simply causing those CPUs + * to execute e.g. a RAM-based pin loop is not sufficient. This allows the + * kexec'd kernel to use any and all RAM as it sees fit, without having to + * avoid any code or data used by any SW CPU pin loop. The CPU hotplug + * functionality embodied in smp_shutdown_nonboot_cpus() to achieve this. + */ +void machine_shutdown(void) +{ + smp_shutdown_nonboot_cpus(reboot_cpu); +} + +/* + * Halting simply requires that the secondary CPUs stop performing any + * activity (executing tasks, handling interrupts). smp_send_stop() + * achieves this. + */ +void machine_halt(void) +{ + local_irq_disable(); + smp_send_stop(); + while (1); +} + +/* + * Power-off simply requires that the secondary CPUs stop performing any + * activity (executing tasks, handling interrupts). smp_send_stop() + * achieves this. When the system power is turned off, it will take all CPUs + * with it. + */ +void machine_power_off(void) +{ + local_irq_disable(); + smp_send_stop(); + do_kernel_power_off(); +} + +/* + * Restart requires that the secondary CPUs stop performing any activity + * while the primary CPU resets the system. Systems with a single CPU can + * use soft_restart() as their machine descriptor's .restart hook, since that + * will cause the only available CPU to reset. Systems with multiple CPUs must + * provide a HW restart implementation, to ensure that all CPUs reset at once. + * This is required so that any code running after reset on the primary CPU + * doesn't have to co-ordinate with other CPUs to ensure they aren't still + * executing pre-reset code, and using RAM that the primary CPU's code wishes + * to use. Implementing such co-ordination would be essentially impossible. + */ +void machine_restart(char *cmd) +{ + local_irq_disable(); + smp_send_stop(); + + do_kernel_restart(cmd); + + /* Give a grace period for failure to restart of 1s */ + mdelay(1000); + + /* Whoops - the platform was unable to reboot. Tell the user! */ + printk("Reboot failed -- System halted\n"); + while (1); +} diff --git a/arch/arm/kernel/reboot.h b/arch/arm/kernel/reboot.h new file mode 100644 index 000000000..189ab81b7 --- /dev/null +++ b/arch/arm/kernel/reboot.h @@ -0,0 +1,8 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef REBOOT_H +#define REBOOT_H + +extern void call_with_stack(void (*fn)(void *), void *arg, void *sp); +extern void _soft_restart(unsigned long addr, bool disable_l2); + +#endif diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S new file mode 100644 index 000000000..218d52436 --- /dev/null +++ b/arch/arm/kernel/relocate_kernel.S @@ -0,0 +1,78 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * relocate_kernel.S - put the kernel image in place to boot + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/asm-offsets.h> +#include <asm/kexec.h> + + .align 3 /* not needed for this code, but keeps fncpy() happy */ + +ENTRY(relocate_new_kernel) + + adr r7, relocate_new_kernel_end + ldr r0, [r7, #KEXEC_INDIR_PAGE] + ldr r1, [r7, #KEXEC_START_ADDR] + + /* + * If there is no indirection page (we are doing crashdumps) + * skip any relocation. + */ + cmp r0, #0 + beq 2f + +0: /* top, read another word for the indirection page */ + ldr r3, [r0],#4 + + /* Is it a destination page. Put destination address to r4 */ + tst r3,#1 + beq 1f + bic r4,r3,#1 + b 0b +1: + /* Is it an indirection page */ + tst r3,#2 + beq 1f + bic r0,r3,#2 + b 0b +1: + + /* are we done ? */ + tst r3,#4 + beq 1f + b 2f + +1: + /* is it source ? */ + tst r3,#8 + beq 0b + bic r3,r3,#8 + mov r6,#1024 +9: + ldr r5,[r3],#4 + str r5,[r4],#4 + subs r6,r6,#1 + bne 9b + b 0b + +2: + /* Jump to relocated kernel */ + mov lr, r1 + mov r0, #0 + ldr r1, [r7, #KEXEC_MACH_TYPE] + ldr r2, [r7, #KEXEC_R2] + ARM( ret lr ) + THUMB( bx lr ) + +ENDPROC(relocate_new_kernel) + + .align 3 +relocate_new_kernel_end: + + .globl relocate_new_kernel_size +relocate_new_kernel_size: + .long relocate_new_kernel_end - relocate_new_kernel + + diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c new file mode 100644 index 000000000..38f1ea9c7 --- /dev/null +++ b/arch/arm/kernel/return_address.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * arch/arm/kernel/return_address.c + * + * Copyright (C) 2009 Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de> + * for Pengutronix + */ +#include <linux/export.h> +#include <linux/ftrace.h> +#include <linux/sched.h> + +#include <asm/stacktrace.h> + +struct return_address_data { + unsigned int level; + void *addr; +}; + +static int save_return_addr(struct stackframe *frame, void *d) +{ + struct return_address_data *data = d; + + if (!data->level) { + data->addr = (void *)frame->pc; + + return 1; + } else { + --data->level; + return 0; + } +} + +void *return_address(unsigned int level) +{ + struct return_address_data data; + struct stackframe frame; + + data.level = level + 2; + data.addr = NULL; + + frame.fp = (unsigned long)__builtin_frame_address(0); + frame.sp = current_stack_pointer; + frame.lr = (unsigned long)__builtin_return_address(0); +here: + frame.pc = (unsigned long)&&here; +#ifdef CONFIG_KRETPROBES + frame.kr_cur = NULL; + frame.tsk = current; +#endif + frame.ex_frame = false; + + walk_stackframe(&frame, save_return_addr, &data); + + if (!data.level) + return data.addr; + else + return NULL; +} + +EXPORT_SYMBOL_GPL(return_address); diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c new file mode 100644 index 000000000..cb88c6e69 --- /dev/null +++ b/arch/arm/kernel/setup.c @@ -0,0 +1,1350 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/setup.c + * + * Copyright (C) 1995-2001 Russell King + */ +#include <linux/efi.h> +#include <linux/export.h> +#include <linux/kernel.h> +#include <linux/stddef.h> +#include <linux/ioport.h> +#include <linux/delay.h> +#include <linux/utsname.h> +#include <linux/initrd.h> +#include <linux/console.h> +#include <linux/seq_file.h> +#include <linux/screen_info.h> +#include <linux/of_platform.h> +#include <linux/init.h> +#include <linux/kexec.h> +#include <linux/libfdt.h> +#include <linux/of_fdt.h> +#include <linux/cpu.h> +#include <linux/interrupt.h> +#include <linux/smp.h> +#include <linux/proc_fs.h> +#include <linux/memblock.h> +#include <linux/bug.h> +#include <linux/compiler.h> +#include <linux/sort.h> +#include <linux/psci.h> + +#include <asm/unified.h> +#include <asm/cp15.h> +#include <asm/cpu.h> +#include <asm/cputype.h> +#include <asm/efi.h> +#include <asm/elf.h> +#include <asm/early_ioremap.h> +#include <asm/fixmap.h> +#include <asm/procinfo.h> +#include <asm/psci.h> +#include <asm/sections.h> +#include <asm/setup.h> +#include <asm/smp_plat.h> +#include <asm/mach-types.h> +#include <asm/cacheflush.h> +#include <asm/cachetype.h> +#include <asm/tlbflush.h> +#include <asm/xen/hypervisor.h> + +#include <asm/prom.h> +#include <asm/mach/arch.h> +#include <asm/mach/irq.h> +#include <asm/mach/time.h> +#include <asm/system_info.h> +#include <asm/system_misc.h> +#include <asm/traps.h> +#include <asm/unwind.h> +#include <asm/memblock.h> +#include <asm/virt.h> +#include <asm/kasan.h> + +#include "atags.h" + + +#if defined(CONFIG_FPE_NWFPE) || defined(CONFIG_FPE_FASTFPE) +char fpe_type[8]; + +static int __init fpe_setup(char *line) +{ + memcpy(fpe_type, line, 8); + return 1; +} + +__setup("fpe=", fpe_setup); +#endif + +extern void init_default_cache_policy(unsigned long); +extern void paging_init(const struct machine_desc *desc); +extern void early_mm_init(const struct machine_desc *); +extern void adjust_lowmem_bounds(void); +extern enum reboot_mode reboot_mode; +extern void setup_dma_zone(const struct machine_desc *desc); + +unsigned int processor_id; +EXPORT_SYMBOL(processor_id); +unsigned int __machine_arch_type __read_mostly; +EXPORT_SYMBOL(__machine_arch_type); +unsigned int cacheid __read_mostly; +EXPORT_SYMBOL(cacheid); + +unsigned int __atags_pointer __initdata; + +unsigned int system_rev; +EXPORT_SYMBOL(system_rev); + +const char *system_serial; +EXPORT_SYMBOL(system_serial); + +unsigned int system_serial_low; +EXPORT_SYMBOL(system_serial_low); + +unsigned int system_serial_high; +EXPORT_SYMBOL(system_serial_high); + +unsigned int elf_hwcap __read_mostly; +EXPORT_SYMBOL(elf_hwcap); + +unsigned int elf_hwcap2 __read_mostly; +EXPORT_SYMBOL(elf_hwcap2); + + +#ifdef MULTI_CPU +struct processor processor __ro_after_init; +#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR) +struct processor *cpu_vtable[NR_CPUS] = { + [0] = &processor, +}; +#endif +#endif +#ifdef MULTI_TLB +struct cpu_tlb_fns cpu_tlb __ro_after_init; +#endif +#ifdef MULTI_USER +struct cpu_user_fns cpu_user __ro_after_init; +#endif +#ifdef MULTI_CACHE +struct cpu_cache_fns cpu_cache __ro_after_init; +#endif +#ifdef CONFIG_OUTER_CACHE +struct outer_cache_fns outer_cache __ro_after_init; +EXPORT_SYMBOL(outer_cache); +#endif + +/* + * Cached cpu_architecture() result for use by assembler code. + * C code should use the cpu_architecture() function instead of accessing this + * variable directly. + */ +int __cpu_architecture __read_mostly = CPU_ARCH_UNKNOWN; + +struct stack { + u32 irq[4]; + u32 abt[4]; + u32 und[4]; + u32 fiq[4]; +} ____cacheline_aligned; + +#ifndef CONFIG_CPU_V7M +static struct stack stacks[NR_CPUS]; +#endif + +char elf_platform[ELF_PLATFORM_SIZE]; +EXPORT_SYMBOL(elf_platform); + +static const char *cpu_name; +static const char *machine_name; +static char __initdata cmd_line[COMMAND_LINE_SIZE]; +const struct machine_desc *machine_desc __initdata; + +static union { char c[4]; unsigned long l; } endian_test __initdata = { { 'l', '?', '?', 'b' } }; +#define ENDIANNESS ((char)endian_test.l) + +DEFINE_PER_CPU(struct cpuinfo_arm, cpu_data); + +/* + * Standard memory resources + */ +static struct resource mem_res[] = { + { + .name = "Video RAM", + .start = 0, + .end = 0, + .flags = IORESOURCE_MEM + }, + { + .name = "Kernel code", + .start = 0, + .end = 0, + .flags = IORESOURCE_SYSTEM_RAM + }, + { + .name = "Kernel data", + .start = 0, + .end = 0, + .flags = IORESOURCE_SYSTEM_RAM + } +}; + +#define video_ram mem_res[0] +#define kernel_code mem_res[1] +#define kernel_data mem_res[2] + +static struct resource io_res[] = { + { + .name = "reserved", + .start = 0x3bc, + .end = 0x3be, + .flags = IORESOURCE_IO | IORESOURCE_BUSY + }, + { + .name = "reserved", + .start = 0x378, + .end = 0x37f, + .flags = IORESOURCE_IO | IORESOURCE_BUSY + }, + { + .name = "reserved", + .start = 0x278, + .end = 0x27f, + .flags = IORESOURCE_IO | IORESOURCE_BUSY + } +}; + +#define lp0 io_res[0] +#define lp1 io_res[1] +#define lp2 io_res[2] + +static const char *proc_arch[] = { + "undefined/unknown", + "3", + "4", + "4T", + "5", + "5T", + "5TE", + "5TEJ", + "6TEJ", + "7", + "7M", + "?(12)", + "?(13)", + "?(14)", + "?(15)", + "?(16)", + "?(17)", +}; + +#ifdef CONFIG_CPU_V7M +static int __get_cpu_architecture(void) +{ + return CPU_ARCH_ARMv7M; +} +#else +static int __get_cpu_architecture(void) +{ + int cpu_arch; + + if ((read_cpuid_id() & 0x0008f000) == 0) { + cpu_arch = CPU_ARCH_UNKNOWN; + } else if ((read_cpuid_id() & 0x0008f000) == 0x00007000) { + cpu_arch = (read_cpuid_id() & (1 << 23)) ? CPU_ARCH_ARMv4T : CPU_ARCH_ARMv3; + } else if ((read_cpuid_id() & 0x00080000) == 0x00000000) { + cpu_arch = (read_cpuid_id() >> 16) & 7; + if (cpu_arch) + cpu_arch += CPU_ARCH_ARMv3; + } else if ((read_cpuid_id() & 0x000f0000) == 0x000f0000) { + /* Revised CPUID format. Read the Memory Model Feature + * Register 0 and check for VMSAv7 or PMSAv7 */ + unsigned int mmfr0 = read_cpuid_ext(CPUID_EXT_MMFR0); + if ((mmfr0 & 0x0000000f) >= 0x00000003 || + (mmfr0 & 0x000000f0) >= 0x00000030) + cpu_arch = CPU_ARCH_ARMv7; + else if ((mmfr0 & 0x0000000f) == 0x00000002 || + (mmfr0 & 0x000000f0) == 0x00000020) + cpu_arch = CPU_ARCH_ARMv6; + else + cpu_arch = CPU_ARCH_UNKNOWN; + } else + cpu_arch = CPU_ARCH_UNKNOWN; + + return cpu_arch; +} +#endif + +int __pure cpu_architecture(void) +{ + BUG_ON(__cpu_architecture == CPU_ARCH_UNKNOWN); + + return __cpu_architecture; +} + +static int cpu_has_aliasing_icache(unsigned int arch) +{ + int aliasing_icache; + unsigned int id_reg, num_sets, line_size; + + /* PIPT caches never alias. */ + if (icache_is_pipt()) + return 0; + + /* arch specifies the register format */ + switch (arch) { + case CPU_ARCH_ARMv7: + set_csselr(CSSELR_ICACHE | CSSELR_L1); + isb(); + id_reg = read_ccsidr(); + line_size = 4 << ((id_reg & 0x7) + 2); + num_sets = ((id_reg >> 13) & 0x7fff) + 1; + aliasing_icache = (line_size * num_sets) > PAGE_SIZE; + break; + case CPU_ARCH_ARMv6: + aliasing_icache = read_cpuid_cachetype() & (1 << 11); + break; + default: + /* I-cache aliases will be handled by D-cache aliasing code */ + aliasing_icache = 0; + } + + return aliasing_icache; +} + +static void __init cacheid_init(void) +{ + unsigned int arch = cpu_architecture(); + + if (arch >= CPU_ARCH_ARMv6) { + unsigned int cachetype = read_cpuid_cachetype(); + + if ((arch == CPU_ARCH_ARMv7M) && !(cachetype & 0xf000f)) { + cacheid = 0; + } else if ((cachetype & (7 << 29)) == 4 << 29) { + /* ARMv7 register format */ + arch = CPU_ARCH_ARMv7; + cacheid = CACHEID_VIPT_NONALIASING; + switch (cachetype & (3 << 14)) { + case (1 << 14): + cacheid |= CACHEID_ASID_TAGGED; + break; + case (3 << 14): + cacheid |= CACHEID_PIPT; + break; + } + } else { + arch = CPU_ARCH_ARMv6; + if (cachetype & (1 << 23)) + cacheid = CACHEID_VIPT_ALIASING; + else + cacheid = CACHEID_VIPT_NONALIASING; + } + if (cpu_has_aliasing_icache(arch)) + cacheid |= CACHEID_VIPT_I_ALIASING; + } else { + cacheid = CACHEID_VIVT; + } + + pr_info("CPU: %s data cache, %s instruction cache\n", + cache_is_vivt() ? "VIVT" : + cache_is_vipt_aliasing() ? "VIPT aliasing" : + cache_is_vipt_nonaliasing() ? "PIPT / VIPT nonaliasing" : "unknown", + cache_is_vivt() ? "VIVT" : + icache_is_vivt_asid_tagged() ? "VIVT ASID tagged" : + icache_is_vipt_aliasing() ? "VIPT aliasing" : + icache_is_pipt() ? "PIPT" : + cache_is_vipt_nonaliasing() ? "VIPT nonaliasing" : "unknown"); +} + +/* + * These functions re-use the assembly code in head.S, which + * already provide the required functionality. + */ +extern struct proc_info_list *lookup_processor_type(unsigned int); + +void __init early_print(const char *str, ...) +{ + extern void printascii(const char *); + char buf[256]; + va_list ap; + + va_start(ap, str); + vsnprintf(buf, sizeof(buf), str, ap); + va_end(ap); + +#ifdef CONFIG_DEBUG_LL + printascii(buf); +#endif + printk("%s", buf); +} + +#ifdef CONFIG_ARM_PATCH_IDIV + +static inline u32 __attribute_const__ sdiv_instruction(void) +{ + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { + /* "sdiv r0, r0, r1" */ + u32 insn = __opcode_thumb32_compose(0xfb90, 0xf0f1); + return __opcode_to_mem_thumb32(insn); + } + + /* "sdiv r0, r0, r1" */ + return __opcode_to_mem_arm(0xe710f110); +} + +static inline u32 __attribute_const__ udiv_instruction(void) +{ + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { + /* "udiv r0, r0, r1" */ + u32 insn = __opcode_thumb32_compose(0xfbb0, 0xf0f1); + return __opcode_to_mem_thumb32(insn); + } + + /* "udiv r0, r0, r1" */ + return __opcode_to_mem_arm(0xe730f110); +} + +static inline u32 __attribute_const__ bx_lr_instruction(void) +{ + if (IS_ENABLED(CONFIG_THUMB2_KERNEL)) { + /* "bx lr; nop" */ + u32 insn = __opcode_thumb32_compose(0x4770, 0x46c0); + return __opcode_to_mem_thumb32(insn); + } + + /* "bx lr" */ + return __opcode_to_mem_arm(0xe12fff1e); +} + +static void __init patch_aeabi_idiv(void) +{ + extern void __aeabi_uidiv(void); + extern void __aeabi_idiv(void); + uintptr_t fn_addr; + unsigned int mask; + + mask = IS_ENABLED(CONFIG_THUMB2_KERNEL) ? HWCAP_IDIVT : HWCAP_IDIVA; + if (!(elf_hwcap & mask)) + return; + + pr_info("CPU: div instructions available: patching division code\n"); + + fn_addr = ((uintptr_t)&__aeabi_uidiv) & ~1; + asm ("" : "+g" (fn_addr)); + ((u32 *)fn_addr)[0] = udiv_instruction(); + ((u32 *)fn_addr)[1] = bx_lr_instruction(); + flush_icache_range(fn_addr, fn_addr + 8); + + fn_addr = ((uintptr_t)&__aeabi_idiv) & ~1; + asm ("" : "+g" (fn_addr)); + ((u32 *)fn_addr)[0] = sdiv_instruction(); + ((u32 *)fn_addr)[1] = bx_lr_instruction(); + flush_icache_range(fn_addr, fn_addr + 8); +} + +#else +static inline void patch_aeabi_idiv(void) { } +#endif + +static void __init cpuid_init_hwcaps(void) +{ + int block; + u32 isar5; + + if (cpu_architecture() < CPU_ARCH_ARMv7) + return; + + block = cpuid_feature_extract(CPUID_EXT_ISAR0, 24); + if (block >= 2) + elf_hwcap |= HWCAP_IDIVA; + if (block >= 1) + elf_hwcap |= HWCAP_IDIVT; + + /* LPAE implies atomic ldrd/strd instructions */ + block = cpuid_feature_extract(CPUID_EXT_MMFR0, 0); + if (block >= 5) + elf_hwcap |= HWCAP_LPAE; + + /* check for supported v8 Crypto instructions */ + isar5 = read_cpuid_ext(CPUID_EXT_ISAR5); + + block = cpuid_feature_extract_field(isar5, 4); + if (block >= 2) + elf_hwcap2 |= HWCAP2_PMULL; + if (block >= 1) + elf_hwcap2 |= HWCAP2_AES; + + block = cpuid_feature_extract_field(isar5, 8); + if (block >= 1) + elf_hwcap2 |= HWCAP2_SHA1; + + block = cpuid_feature_extract_field(isar5, 12); + if (block >= 1) + elf_hwcap2 |= HWCAP2_SHA2; + + block = cpuid_feature_extract_field(isar5, 16); + if (block >= 1) + elf_hwcap2 |= HWCAP2_CRC32; +} + +static void __init elf_hwcap_fixup(void) +{ + unsigned id = read_cpuid_id(); + + /* + * HWCAP_TLS is available only on 1136 r1p0 and later, + * see also kuser_get_tls_init. + */ + if (read_cpuid_part() == ARM_CPU_PART_ARM1136 && + ((id >> 20) & 3) == 0) { + elf_hwcap &= ~HWCAP_TLS; + return; + } + + /* Verify if CPUID scheme is implemented */ + if ((id & 0x000f0000) != 0x000f0000) + return; + + /* + * If the CPU supports LDREX/STREX and LDREXB/STREXB, + * avoid advertising SWP; it may not be atomic with + * multiprocessing cores. + */ + if (cpuid_feature_extract(CPUID_EXT_ISAR3, 12) > 1 || + (cpuid_feature_extract(CPUID_EXT_ISAR3, 12) == 1 && + cpuid_feature_extract(CPUID_EXT_ISAR4, 20) >= 3)) + elf_hwcap &= ~HWCAP_SWP; +} + +/* + * cpu_init - initialise one CPU. + * + * cpu_init sets up the per-CPU stacks. + */ +void notrace cpu_init(void) +{ +#ifndef CONFIG_CPU_V7M + unsigned int cpu = smp_processor_id(); + struct stack *stk = &stacks[cpu]; + + if (cpu >= NR_CPUS) { + pr_crit("CPU%u: bad primary CPU number\n", cpu); + BUG(); + } + + /* + * This only works on resume and secondary cores. For booting on the + * boot cpu, smp_prepare_boot_cpu is called after percpu area setup. + */ + set_my_cpu_offset(per_cpu_offset(cpu)); + + cpu_proc_init(); + + /* + * Define the placement constraint for the inline asm directive below. + * In Thumb-2, msr with an immediate value is not allowed. + */ +#ifdef CONFIG_THUMB2_KERNEL +#define PLC_l "l" +#define PLC_r "r" +#else +#define PLC_l "I" +#define PLC_r "I" +#endif + + /* + * setup stacks for re-entrant exception handlers + */ + __asm__ ( + "msr cpsr_c, %1\n\t" + "add r14, %0, %2\n\t" + "mov sp, r14\n\t" + "msr cpsr_c, %3\n\t" + "add r14, %0, %4\n\t" + "mov sp, r14\n\t" + "msr cpsr_c, %5\n\t" + "add r14, %0, %6\n\t" + "mov sp, r14\n\t" + "msr cpsr_c, %7\n\t" + "add r14, %0, %8\n\t" + "mov sp, r14\n\t" + "msr cpsr_c, %9" + : + : "r" (stk), + PLC_r (PSR_F_BIT | PSR_I_BIT | IRQ_MODE), + "I" (offsetof(struct stack, irq[0])), + PLC_r (PSR_F_BIT | PSR_I_BIT | ABT_MODE), + "I" (offsetof(struct stack, abt[0])), + PLC_r (PSR_F_BIT | PSR_I_BIT | UND_MODE), + "I" (offsetof(struct stack, und[0])), + PLC_r (PSR_F_BIT | PSR_I_BIT | FIQ_MODE), + "I" (offsetof(struct stack, fiq[0])), + PLC_l (PSR_F_BIT | PSR_I_BIT | SVC_MODE) + : "r14"); +#endif +} + +u32 __cpu_logical_map[NR_CPUS] = { [0 ... NR_CPUS-1] = MPIDR_INVALID }; + +void __init smp_setup_processor_id(void) +{ + int i; + u32 mpidr = is_smp() ? read_cpuid_mpidr() & MPIDR_HWID_BITMASK : 0; + u32 cpu = MPIDR_AFFINITY_LEVEL(mpidr, 0); + + cpu_logical_map(0) = cpu; + for (i = 1; i < nr_cpu_ids; ++i) + cpu_logical_map(i) = i == cpu ? 0 : i; + + /* + * clear __my_cpu_offset on boot CPU to avoid hang caused by + * using percpu variable early, for example, lockdep will + * access percpu variable inside lock_release + */ + set_my_cpu_offset(0); + + pr_info("Booting Linux on physical CPU 0x%x\n", mpidr); +} + +struct mpidr_hash mpidr_hash; +#ifdef CONFIG_SMP +/** + * smp_build_mpidr_hash - Pre-compute shifts required at each affinity + * level in order to build a linear index from an + * MPIDR value. Resulting algorithm is a collision + * free hash carried out through shifting and ORing + */ +static void __init smp_build_mpidr_hash(void) +{ + u32 i, affinity; + u32 fs[3], bits[3], ls, mask = 0; + /* + * Pre-scan the list of MPIDRS and filter out bits that do + * not contribute to affinity levels, ie they never toggle. + */ + for_each_possible_cpu(i) + mask |= (cpu_logical_map(i) ^ cpu_logical_map(0)); + pr_debug("mask of set bits 0x%x\n", mask); + /* + * Find and stash the last and first bit set at all affinity levels to + * check how many bits are required to represent them. + */ + for (i = 0; i < 3; i++) { + affinity = MPIDR_AFFINITY_LEVEL(mask, i); + /* + * Find the MSB bit and LSB bits position + * to determine how many bits are required + * to express the affinity level. + */ + ls = fls(affinity); + fs[i] = affinity ? ffs(affinity) - 1 : 0; + bits[i] = ls - fs[i]; + } + /* + * An index can be created from the MPIDR by isolating the + * significant bits at each affinity level and by shifting + * them in order to compress the 24 bits values space to a + * compressed set of values. This is equivalent to hashing + * the MPIDR through shifting and ORing. It is a collision free + * hash though not minimal since some levels might contain a number + * of CPUs that is not an exact power of 2 and their bit + * representation might contain holes, eg MPIDR[7:0] = {0x2, 0x80}. + */ + mpidr_hash.shift_aff[0] = fs[0]; + mpidr_hash.shift_aff[1] = MPIDR_LEVEL_BITS + fs[1] - bits[0]; + mpidr_hash.shift_aff[2] = 2*MPIDR_LEVEL_BITS + fs[2] - + (bits[1] + bits[0]); + mpidr_hash.mask = mask; + mpidr_hash.bits = bits[2] + bits[1] + bits[0]; + pr_debug("MPIDR hash: aff0[%u] aff1[%u] aff2[%u] mask[0x%x] bits[%u]\n", + mpidr_hash.shift_aff[0], + mpidr_hash.shift_aff[1], + mpidr_hash.shift_aff[2], + mpidr_hash.mask, + mpidr_hash.bits); + /* + * 4x is an arbitrary value used to warn on a hash table much bigger + * than expected on most systems. + */ + if (mpidr_hash_size() > 4 * num_possible_cpus()) + pr_warn("Large number of MPIDR hash buckets detected\n"); + sync_cache_w(&mpidr_hash); +} +#endif + +/* + * locate processor in the list of supported processor types. The linker + * builds this table for us from the entries in arch/arm/mm/proc-*.S + */ +struct proc_info_list *lookup_processor(u32 midr) +{ + struct proc_info_list *list = lookup_processor_type(midr); + + if (!list) { + pr_err("CPU%u: configuration botched (ID %08x), CPU halted\n", + smp_processor_id(), midr); + while (1) + /* can't use cpu_relax() here as it may require MMU setup */; + } + + return list; +} + +static void __init setup_processor(void) +{ + unsigned int midr = read_cpuid_id(); + struct proc_info_list *list = lookup_processor(midr); + + cpu_name = list->cpu_name; + __cpu_architecture = __get_cpu_architecture(); + + init_proc_vtable(list->proc); +#ifdef MULTI_TLB + cpu_tlb = *list->tlb; +#endif +#ifdef MULTI_USER + cpu_user = *list->user; +#endif +#ifdef MULTI_CACHE + cpu_cache = *list->cache; +#endif + + pr_info("CPU: %s [%08x] revision %d (ARMv%s), cr=%08lx\n", + list->cpu_name, midr, midr & 15, + proc_arch[cpu_architecture()], get_cr()); + + snprintf(init_utsname()->machine, __NEW_UTS_LEN + 1, "%s%c", + list->arch_name, ENDIANNESS); + snprintf(elf_platform, ELF_PLATFORM_SIZE, "%s%c", + list->elf_name, ENDIANNESS); + elf_hwcap = list->elf_hwcap; + + cpuid_init_hwcaps(); + patch_aeabi_idiv(); + +#ifndef CONFIG_ARM_THUMB + elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT); +#endif +#ifdef CONFIG_MMU + init_default_cache_policy(list->__cpu_mm_mmu_flags); +#endif + erratum_a15_798181_init(); + + elf_hwcap_fixup(); + + cacheid_init(); + cpu_init(); +} + +void __init dump_machine_table(void) +{ + const struct machine_desc *p; + + early_print("Available machine support:\n\nID (hex)\tNAME\n"); + for_each_machine_desc(p) + early_print("%08x\t%s\n", p->nr, p->name); + + early_print("\nPlease check your kernel config and/or bootloader.\n"); + + while (true) + /* can't use cpu_relax() here as it may require MMU setup */; +} + +int __init arm_add_memory(u64 start, u64 size) +{ + u64 aligned_start; + + /* + * Ensure that start/size are aligned to a page boundary. + * Size is rounded down, start is rounded up. + */ + aligned_start = PAGE_ALIGN(start); + if (aligned_start > start + size) + size = 0; + else + size -= aligned_start - start; + +#ifndef CONFIG_PHYS_ADDR_T_64BIT + if (aligned_start > ULONG_MAX) { + pr_crit("Ignoring memory at 0x%08llx outside 32-bit physical address space\n", + start); + return -EINVAL; + } + + if (aligned_start + size > ULONG_MAX) { + pr_crit("Truncating memory at 0x%08llx to fit in 32-bit physical address space\n", + (long long)start); + /* + * To ensure bank->start + bank->size is representable in + * 32 bits, we use ULONG_MAX as the upper limit rather than 4GB. + * This means we lose a page after masking. + */ + size = ULONG_MAX - aligned_start; + } +#endif + + if (aligned_start < PHYS_OFFSET) { + if (aligned_start + size <= PHYS_OFFSET) { + pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n", + aligned_start, aligned_start + size); + return -EINVAL; + } + + pr_info("Ignoring memory below PHYS_OFFSET: 0x%08llx-0x%08llx\n", + aligned_start, (u64)PHYS_OFFSET); + + size -= PHYS_OFFSET - aligned_start; + aligned_start = PHYS_OFFSET; + } + + start = aligned_start; + size = size & ~(phys_addr_t)(PAGE_SIZE - 1); + + /* + * Check whether this memory region has non-zero size or + * invalid node number. + */ + if (size == 0) + return -EINVAL; + + memblock_add(start, size); + return 0; +} + +/* + * Pick out the memory size. We look for mem=size@start, + * where start and size are "size[KkMm]" + */ + +static int __init early_mem(char *p) +{ + static int usermem __initdata = 0; + u64 size; + u64 start; + char *endp; + + /* + * If the user specifies memory size, we + * blow away any automatically generated + * size. + */ + if (usermem == 0) { + usermem = 1; + memblock_remove(memblock_start_of_DRAM(), + memblock_end_of_DRAM() - memblock_start_of_DRAM()); + } + + start = PHYS_OFFSET; + size = memparse(p, &endp); + if (*endp == '@') + start = memparse(endp + 1, NULL); + + arm_add_memory(start, size); + + return 0; +} +early_param("mem", early_mem); + +static void __init request_standard_resources(const struct machine_desc *mdesc) +{ + phys_addr_t start, end, res_end; + struct resource *res; + u64 i; + + kernel_code.start = virt_to_phys(_text); + kernel_code.end = virt_to_phys(__init_begin - 1); + kernel_data.start = virt_to_phys(_sdata); + kernel_data.end = virt_to_phys(_end - 1); + + for_each_mem_range(i, &start, &end) { + unsigned long boot_alias_start; + + /* + * In memblock, end points to the first byte after the + * range while in resourses, end points to the last byte in + * the range. + */ + res_end = end - 1; + + /* + * Some systems have a special memory alias which is only + * used for booting. We need to advertise this region to + * kexec-tools so they know where bootable RAM is located. + */ + boot_alias_start = phys_to_idmap(start); + if (arm_has_idmap_alias() && boot_alias_start != IDMAP_INVALID_ADDR) { + res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES); + if (!res) + panic("%s: Failed to allocate %zu bytes\n", + __func__, sizeof(*res)); + res->name = "System RAM (boot alias)"; + res->start = boot_alias_start; + res->end = phys_to_idmap(res_end); + res->flags = IORESOURCE_MEM | IORESOURCE_BUSY; + request_resource(&iomem_resource, res); + } + + res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES); + if (!res) + panic("%s: Failed to allocate %zu bytes\n", __func__, + sizeof(*res)); + res->name = "System RAM"; + res->start = start; + res->end = res_end; + res->flags = IORESOURCE_SYSTEM_RAM | IORESOURCE_BUSY; + + request_resource(&iomem_resource, res); + + if (kernel_code.start >= res->start && + kernel_code.end <= res->end) + request_resource(res, &kernel_code); + if (kernel_data.start >= res->start && + kernel_data.end <= res->end) + request_resource(res, &kernel_data); + } + + if (mdesc->video_start) { + video_ram.start = mdesc->video_start; + video_ram.end = mdesc->video_end; + request_resource(&iomem_resource, &video_ram); + } + + /* + * Some machines don't have the possibility of ever + * possessing lp0, lp1 or lp2 + */ + if (mdesc->reserve_lp0) + request_resource(&ioport_resource, &lp0); + if (mdesc->reserve_lp1) + request_resource(&ioport_resource, &lp1); + if (mdesc->reserve_lp2) + request_resource(&ioport_resource, &lp2); +} + +#if defined(CONFIG_VGA_CONSOLE) || defined(CONFIG_DUMMY_CONSOLE) || \ + defined(CONFIG_EFI) +struct screen_info screen_info = { + .orig_video_lines = 30, + .orig_video_cols = 80, + .orig_video_mode = 0, + .orig_video_ega_bx = 0, + .orig_video_isVGA = 1, + .orig_video_points = 8 +}; +#endif + +static int __init customize_machine(void) +{ + /* + * customizes platform devices, or adds new ones + * On DT based machines, we fall back to populating the + * machine from the device tree, if no callback is provided, + * otherwise we would always need an init_machine callback. + */ + if (machine_desc->init_machine) + machine_desc->init_machine(); + + return 0; +} +arch_initcall(customize_machine); + +static int __init init_machine_late(void) +{ + struct device_node *root; + int ret; + + if (machine_desc->init_late) + machine_desc->init_late(); + + root = of_find_node_by_path("/"); + if (root) { + ret = of_property_read_string(root, "serial-number", + &system_serial); + if (ret) + system_serial = NULL; + } + + if (!system_serial) + system_serial = kasprintf(GFP_KERNEL, "%08x%08x", + system_serial_high, + system_serial_low); + + return 0; +} +late_initcall(init_machine_late); + +#ifdef CONFIG_KEXEC +/* + * The crash region must be aligned to 128MB to avoid + * zImage relocating below the reserved region. + */ +#define CRASH_ALIGN (128 << 20) + +static inline unsigned long long get_total_mem(void) +{ + unsigned long total; + + total = max_low_pfn - min_low_pfn; + return total << PAGE_SHIFT; +} + +/** + * reserve_crashkernel() - reserves memory are for crash kernel + * + * This function reserves memory area given in "crashkernel=" kernel command + * line parameter. The memory reserved is used by a dump capture kernel when + * primary kernel is crashing. + */ +static void __init reserve_crashkernel(void) +{ + unsigned long long crash_size, crash_base; + unsigned long long total_mem; + int ret; + + total_mem = get_total_mem(); + ret = parse_crashkernel(boot_command_line, total_mem, + &crash_size, &crash_base); + /* invalid value specified or crashkernel=0 */ + if (ret || !crash_size) + return; + + if (crash_base <= 0) { + unsigned long long crash_max = idmap_to_phys((u32)~0); + unsigned long long lowmem_max = __pa(high_memory - 1) + 1; + if (crash_max > lowmem_max) + crash_max = lowmem_max; + + crash_base = memblock_phys_alloc_range(crash_size, CRASH_ALIGN, + CRASH_ALIGN, crash_max); + if (!crash_base) { + pr_err("crashkernel reservation failed - No suitable area found.\n"); + return; + } + } else { + unsigned long long crash_max = crash_base + crash_size; + unsigned long long start; + + start = memblock_phys_alloc_range(crash_size, SECTION_SIZE, + crash_base, crash_max); + if (!start) { + pr_err("crashkernel reservation failed - memory is in use.\n"); + return; + } + } + + pr_info("Reserving %ldMB of memory at %ldMB for crashkernel (System RAM: %ldMB)\n", + (unsigned long)(crash_size >> 20), + (unsigned long)(crash_base >> 20), + (unsigned long)(total_mem >> 20)); + + /* The crashk resource must always be located in normal mem */ + crashk_res.start = crash_base; + crashk_res.end = crash_base + crash_size - 1; + insert_resource(&iomem_resource, &crashk_res); + + if (arm_has_idmap_alias()) { + /* + * If we have a special RAM alias for use at boot, we + * need to advertise to kexec tools where the alias is. + */ + static struct resource crashk_boot_res = { + .name = "Crash kernel (boot alias)", + .flags = IORESOURCE_BUSY | IORESOURCE_MEM, + }; + + crashk_boot_res.start = phys_to_idmap(crash_base); + crashk_boot_res.end = crashk_boot_res.start + crash_size - 1; + insert_resource(&iomem_resource, &crashk_boot_res); + } +} +#else +static inline void reserve_crashkernel(void) {} +#endif /* CONFIG_KEXEC */ + +void __init hyp_mode_check(void) +{ +#ifdef CONFIG_ARM_VIRT_EXT + sync_boot_mode(); + + if (is_hyp_mode_available()) { + pr_info("CPU: All CPU(s) started in HYP mode.\n"); + pr_info("CPU: Virtualization extensions available.\n"); + } else if (is_hyp_mode_mismatched()) { + pr_warn("CPU: WARNING: CPU(s) started in wrong/inconsistent modes (primary CPU mode 0x%x)\n", + __boot_cpu_mode & MODE_MASK); + pr_warn("CPU: This may indicate a broken bootloader or firmware.\n"); + } else + pr_info("CPU: All CPU(s) started in SVC mode.\n"); +#endif +} + +static void (*__arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd); + +static int arm_restart(struct notifier_block *nb, unsigned long action, + void *data) +{ + __arm_pm_restart(action, data); + return NOTIFY_DONE; +} + +static struct notifier_block arm_restart_nb = { + .notifier_call = arm_restart, + .priority = 128, +}; + +void __init setup_arch(char **cmdline_p) +{ + const struct machine_desc *mdesc = NULL; + void *atags_vaddr = NULL; + + if (__atags_pointer) + atags_vaddr = FDT_VIRT_BASE(__atags_pointer); + + setup_processor(); + if (atags_vaddr) { + mdesc = setup_machine_fdt(atags_vaddr); + if (mdesc) + memblock_reserve(__atags_pointer, + fdt_totalsize(atags_vaddr)); + } + if (!mdesc) + mdesc = setup_machine_tags(atags_vaddr, __machine_arch_type); + if (!mdesc) { + early_print("\nError: invalid dtb and unrecognized/unsupported machine ID\n"); + early_print(" r1=0x%08x, r2=0x%08x\n", __machine_arch_type, + __atags_pointer); + if (__atags_pointer) + early_print(" r2[]=%*ph\n", 16, atags_vaddr); + dump_machine_table(); + } + + machine_desc = mdesc; + machine_name = mdesc->name; + dump_stack_set_arch_desc("%s", mdesc->name); + + if (mdesc->reboot_mode != REBOOT_HARD) + reboot_mode = mdesc->reboot_mode; + + setup_initial_init_mm(_text, _etext, _edata, _end); + + /* populate cmd_line too for later use, preserving boot_command_line */ + strlcpy(cmd_line, boot_command_line, COMMAND_LINE_SIZE); + *cmdline_p = cmd_line; + + early_fixmap_init(); + early_ioremap_init(); + + parse_early_param(); + +#ifdef CONFIG_MMU + early_mm_init(mdesc); +#endif + setup_dma_zone(mdesc); + xen_early_init(); + arm_efi_init(); + /* + * Make sure the calculation for lowmem/highmem is set appropriately + * before reserving/allocating any memory + */ + adjust_lowmem_bounds(); + arm_memblock_init(mdesc); + /* Memory may have been removed so recalculate the bounds. */ + adjust_lowmem_bounds(); + + early_ioremap_reset(); + + paging_init(mdesc); + kasan_init(); + request_standard_resources(mdesc); + + if (mdesc->restart) { + __arm_pm_restart = mdesc->restart; + register_restart_handler(&arm_restart_nb); + } + + unflatten_device_tree(); + + arm_dt_init_cpu_maps(); + psci_dt_init(); +#ifdef CONFIG_SMP + if (is_smp()) { + if (!mdesc->smp_init || !mdesc->smp_init()) { + if (psci_smp_available()) + smp_set_ops(&psci_smp_ops); + else if (mdesc->smp) + smp_set_ops(mdesc->smp); + } + smp_init_cpus(); + smp_build_mpidr_hash(); + } +#endif + + if (!is_smp()) + hyp_mode_check(); + + reserve_crashkernel(); + +#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER + handle_arch_irq = mdesc->handle_irq; +#endif + +#ifdef CONFIG_VT +#if defined(CONFIG_VGA_CONSOLE) + conswitchp = &vga_con; +#endif +#endif + + if (mdesc->init_early) + mdesc->init_early(); +} + + +static int __init topology_init(void) +{ + int cpu; + + for_each_possible_cpu(cpu) { + struct cpuinfo_arm *cpuinfo = &per_cpu(cpu_data, cpu); + cpuinfo->cpu.hotpluggable = platform_can_hotplug_cpu(cpu); + register_cpu(&cpuinfo->cpu, cpu); + } + + return 0; +} +subsys_initcall(topology_init); + +#ifdef CONFIG_HAVE_PROC_CPU +static int __init proc_cpu_init(void) +{ + struct proc_dir_entry *res; + + res = proc_mkdir("cpu", NULL); + if (!res) + return -ENOMEM; + return 0; +} +fs_initcall(proc_cpu_init); +#endif + +static const char *hwcap_str[] = { + "swp", + "half", + "thumb", + "26bit", + "fastmult", + "fpa", + "vfp", + "edsp", + "java", + "iwmmxt", + "crunch", + "thumbee", + "neon", + "vfpv3", + "vfpv3d16", + "tls", + "vfpv4", + "idiva", + "idivt", + "vfpd32", + "lpae", + "evtstrm", + NULL +}; + +static const char *hwcap2_str[] = { + "aes", + "pmull", + "sha1", + "sha2", + "crc32", + NULL +}; + +static int c_show(struct seq_file *m, void *v) +{ + int i, j; + u32 cpuid; + + for_each_online_cpu(i) { + /* + * glibc reads /proc/cpuinfo to determine the number of + * online processors, looking for lines beginning with + * "processor". Give glibc what it expects. + */ + seq_printf(m, "processor\t: %d\n", i); + cpuid = is_smp() ? per_cpu(cpu_data, i).cpuid : read_cpuid_id(); + seq_printf(m, "model name\t: %s rev %d (%s)\n", + cpu_name, cpuid & 15, elf_platform); + +#if defined(CONFIG_SMP) + seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", + per_cpu(cpu_data, i).loops_per_jiffy / (500000UL/HZ), + (per_cpu(cpu_data, i).loops_per_jiffy / (5000UL/HZ)) % 100); +#else + seq_printf(m, "BogoMIPS\t: %lu.%02lu\n", + loops_per_jiffy / (500000/HZ), + (loops_per_jiffy / (5000/HZ)) % 100); +#endif + /* dump out the processor features */ + seq_puts(m, "Features\t: "); + + for (j = 0; hwcap_str[j]; j++) + if (elf_hwcap & (1 << j)) + seq_printf(m, "%s ", hwcap_str[j]); + + for (j = 0; hwcap2_str[j]; j++) + if (elf_hwcap2 & (1 << j)) + seq_printf(m, "%s ", hwcap2_str[j]); + + seq_printf(m, "\nCPU implementer\t: 0x%02x\n", cpuid >> 24); + seq_printf(m, "CPU architecture: %s\n", + proc_arch[cpu_architecture()]); + + if ((cpuid & 0x0008f000) == 0x00000000) { + /* pre-ARM7 */ + seq_printf(m, "CPU part\t: %07x\n", cpuid >> 4); + } else { + if ((cpuid & 0x0008f000) == 0x00007000) { + /* ARM7 */ + seq_printf(m, "CPU variant\t: 0x%02x\n", + (cpuid >> 16) & 127); + } else { + /* post-ARM7 */ + seq_printf(m, "CPU variant\t: 0x%x\n", + (cpuid >> 20) & 15); + } + seq_printf(m, "CPU part\t: 0x%03x\n", + (cpuid >> 4) & 0xfff); + } + seq_printf(m, "CPU revision\t: %d\n\n", cpuid & 15); + } + + seq_printf(m, "Hardware\t: %s\n", machine_name); + seq_printf(m, "Revision\t: %04x\n", system_rev); + seq_printf(m, "Serial\t\t: %s\n", system_serial); + + return 0; +} + +static void *c_start(struct seq_file *m, loff_t *pos) +{ + return *pos < 1 ? (void *)1 : NULL; +} + +static void *c_next(struct seq_file *m, void *v, loff_t *pos) +{ + ++*pos; + return NULL; +} + +static void c_stop(struct seq_file *m, void *v) +{ +} + +const struct seq_operations cpuinfo_op = { + .start = c_start, + .next = c_next, + .stop = c_stop, + .show = c_show +}; diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c new file mode 100644 index 000000000..e07f35925 --- /dev/null +++ b/arch/arm/kernel/signal.c @@ -0,0 +1,716 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/signal.c + * + * Copyright (C) 1995-2009 Russell King + */ +#include <linux/errno.h> +#include <linux/random.h> +#include <linux/signal.h> +#include <linux/personality.h> +#include <linux/uaccess.h> +#include <linux/resume_user_mode.h> +#include <linux/uprobes.h> +#include <linux/syscalls.h> + +#include <asm/elf.h> +#include <asm/cacheflush.h> +#include <asm/traps.h> +#include <asm/unistd.h> +#include <asm/vfp.h> + +#include "signal.h" + +extern const unsigned long sigreturn_codes[17]; + +static unsigned long signal_return_offset; + +#ifdef CONFIG_IWMMXT + +static int preserve_iwmmxt_context(struct iwmmxt_sigframe __user *frame) +{ + char kbuf[sizeof(*frame) + 8]; + struct iwmmxt_sigframe *kframe; + int err = 0; + + /* the iWMMXt context must be 64 bit aligned */ + kframe = (struct iwmmxt_sigframe *)((unsigned long)(kbuf + 8) & ~7); + + if (test_thread_flag(TIF_USING_IWMMXT)) { + kframe->magic = IWMMXT_MAGIC; + kframe->size = IWMMXT_STORAGE_SIZE; + iwmmxt_task_copy(current_thread_info(), &kframe->storage); + } else { + /* + * For bug-compatibility with older kernels, some space + * has to be reserved for iWMMXt even if it's not used. + * Set the magic and size appropriately so that properly + * written userspace can skip it reliably: + */ + *kframe = (struct iwmmxt_sigframe) { + .magic = DUMMY_MAGIC, + .size = IWMMXT_STORAGE_SIZE, + }; + } + + err = __copy_to_user(frame, kframe, sizeof(*kframe)); + + return err; +} + +static int restore_iwmmxt_context(char __user **auxp) +{ + struct iwmmxt_sigframe __user *frame = + (struct iwmmxt_sigframe __user *)*auxp; + char kbuf[sizeof(*frame) + 8]; + struct iwmmxt_sigframe *kframe; + + /* the iWMMXt context must be 64 bit aligned */ + kframe = (struct iwmmxt_sigframe *)((unsigned long)(kbuf + 8) & ~7); + if (__copy_from_user(kframe, frame, sizeof(*frame))) + return -1; + + /* + * For non-iWMMXt threads: a single iwmmxt_sigframe-sized dummy + * block is discarded for compatibility with setup_sigframe() if + * present, but we don't mandate its presence. If some other + * magic is here, it's not for us: + */ + if (!test_thread_flag(TIF_USING_IWMMXT) && + kframe->magic != DUMMY_MAGIC) + return 0; + + if (kframe->size != IWMMXT_STORAGE_SIZE) + return -1; + + if (test_thread_flag(TIF_USING_IWMMXT)) { + if (kframe->magic != IWMMXT_MAGIC) + return -1; + + iwmmxt_task_restore(current_thread_info(), &kframe->storage); + } + + *auxp += IWMMXT_STORAGE_SIZE; + return 0; +} + +#endif + +#ifdef CONFIG_VFP + +static int preserve_vfp_context(struct vfp_sigframe __user *frame) +{ + struct vfp_sigframe kframe; + int err = 0; + + memset(&kframe, 0, sizeof(kframe)); + kframe.magic = VFP_MAGIC; + kframe.size = VFP_STORAGE_SIZE; + + err = vfp_preserve_user_clear_hwstate(&kframe.ufp, &kframe.ufp_exc); + if (err) + return err; + + return __copy_to_user(frame, &kframe, sizeof(kframe)); +} + +static int restore_vfp_context(char __user **auxp) +{ + struct vfp_sigframe frame; + int err; + + err = __copy_from_user(&frame, *auxp, sizeof(frame)); + if (err) + return err; + + if (frame.magic != VFP_MAGIC || frame.size != VFP_STORAGE_SIZE) + return -EINVAL; + + *auxp += sizeof(frame); + return vfp_restore_user_hwstate(&frame.ufp, &frame.ufp_exc); +} + +#endif + +/* + * Do a signal return; undo the signal stack. These are aligned to 64-bit. + */ + +static int restore_sigframe(struct pt_regs *regs, struct sigframe __user *sf) +{ + struct sigcontext context; + char __user *aux; + sigset_t set; + int err; + + err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set)); + if (err == 0) + set_current_blocked(&set); + + err |= __copy_from_user(&context, &sf->uc.uc_mcontext, sizeof(context)); + if (err == 0) { + regs->ARM_r0 = context.arm_r0; + regs->ARM_r1 = context.arm_r1; + regs->ARM_r2 = context.arm_r2; + regs->ARM_r3 = context.arm_r3; + regs->ARM_r4 = context.arm_r4; + regs->ARM_r5 = context.arm_r5; + regs->ARM_r6 = context.arm_r6; + regs->ARM_r7 = context.arm_r7; + regs->ARM_r8 = context.arm_r8; + regs->ARM_r9 = context.arm_r9; + regs->ARM_r10 = context.arm_r10; + regs->ARM_fp = context.arm_fp; + regs->ARM_ip = context.arm_ip; + regs->ARM_sp = context.arm_sp; + regs->ARM_lr = context.arm_lr; + regs->ARM_pc = context.arm_pc; + regs->ARM_cpsr = context.arm_cpsr; + } + + err |= !valid_user_regs(regs); + + aux = (char __user *) sf->uc.uc_regspace; +#ifdef CONFIG_IWMMXT + if (err == 0) + err |= restore_iwmmxt_context(&aux); +#endif +#ifdef CONFIG_VFP + if (err == 0) + err |= restore_vfp_context(&aux); +#endif + + return err; +} + +asmlinkage int sys_sigreturn(struct pt_regs *regs) +{ + struct sigframe __user *frame; + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; + + /* + * Since we stacked the signal on a 64-bit boundary, + * then 'sp' should be word aligned here. If it's + * not, then the user is trying to mess with us. + */ + if (regs->ARM_sp & 7) + goto badframe; + + frame = (struct sigframe __user *)regs->ARM_sp; + + if (!access_ok(frame, sizeof (*frame))) + goto badframe; + + if (restore_sigframe(regs, frame)) + goto badframe; + + return regs->ARM_r0; + +badframe: + force_sig(SIGSEGV); + return 0; +} + +asmlinkage int sys_rt_sigreturn(struct pt_regs *regs) +{ + struct rt_sigframe __user *frame; + + /* Always make any pending restarted system calls return -EINTR */ + current->restart_block.fn = do_no_restart_syscall; + + /* + * Since we stacked the signal on a 64-bit boundary, + * then 'sp' should be word aligned here. If it's + * not, then the user is trying to mess with us. + */ + if (regs->ARM_sp & 7) + goto badframe; + + frame = (struct rt_sigframe __user *)regs->ARM_sp; + + if (!access_ok(frame, sizeof (*frame))) + goto badframe; + + if (restore_sigframe(regs, &frame->sig)) + goto badframe; + + if (restore_altstack(&frame->sig.uc.uc_stack)) + goto badframe; + + return regs->ARM_r0; + +badframe: + force_sig(SIGSEGV); + return 0; +} + +static int +setup_sigframe(struct sigframe __user *sf, struct pt_regs *regs, sigset_t *set) +{ + struct aux_sigframe __user *aux; + struct sigcontext context; + int err = 0; + + context = (struct sigcontext) { + .arm_r0 = regs->ARM_r0, + .arm_r1 = regs->ARM_r1, + .arm_r2 = regs->ARM_r2, + .arm_r3 = regs->ARM_r3, + .arm_r4 = regs->ARM_r4, + .arm_r5 = regs->ARM_r5, + .arm_r6 = regs->ARM_r6, + .arm_r7 = regs->ARM_r7, + .arm_r8 = regs->ARM_r8, + .arm_r9 = regs->ARM_r9, + .arm_r10 = regs->ARM_r10, + .arm_fp = regs->ARM_fp, + .arm_ip = regs->ARM_ip, + .arm_sp = regs->ARM_sp, + .arm_lr = regs->ARM_lr, + .arm_pc = regs->ARM_pc, + .arm_cpsr = regs->ARM_cpsr, + + .trap_no = current->thread.trap_no, + .error_code = current->thread.error_code, + .fault_address = current->thread.address, + .oldmask = set->sig[0], + }; + + err |= __copy_to_user(&sf->uc.uc_mcontext, &context, sizeof(context)); + + err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set)); + + aux = (struct aux_sigframe __user *) sf->uc.uc_regspace; +#ifdef CONFIG_IWMMXT + if (err == 0) + err |= preserve_iwmmxt_context(&aux->iwmmxt); +#endif +#ifdef CONFIG_VFP + if (err == 0) + err |= preserve_vfp_context(&aux->vfp); +#endif + err |= __put_user(0, &aux->end_magic); + + return err; +} + +static inline void __user * +get_sigframe(struct ksignal *ksig, struct pt_regs *regs, int framesize) +{ + unsigned long sp = sigsp(regs->ARM_sp, ksig); + void __user *frame; + + /* + * ATPCS B01 mandates 8-byte alignment + */ + frame = (void __user *)((sp - framesize) & ~7); + + /* + * Check that we can actually write to the signal frame. + */ + if (!access_ok(frame, framesize)) + frame = NULL; + + return frame; +} + +static int +setup_return(struct pt_regs *regs, struct ksignal *ksig, + unsigned long __user *rc, void __user *frame) +{ + unsigned long handler = (unsigned long)ksig->ka.sa.sa_handler; + unsigned long handler_fdpic_GOT = 0; + unsigned long retcode; + unsigned int idx, thumb = 0; + unsigned long cpsr = regs->ARM_cpsr & ~(PSR_f | PSR_E_BIT); + bool fdpic = IS_ENABLED(CONFIG_BINFMT_ELF_FDPIC) && + (current->personality & FDPIC_FUNCPTRS); + + if (fdpic) { + unsigned long __user *fdpic_func_desc = + (unsigned long __user *)handler; + if (__get_user(handler, &fdpic_func_desc[0]) || + __get_user(handler_fdpic_GOT, &fdpic_func_desc[1])) + return 1; + } + + cpsr |= PSR_ENDSTATE; + + /* + * Maybe we need to deliver a 32-bit signal to a 26-bit task. + */ + if (ksig->ka.sa.sa_flags & SA_THIRTYTWO) + cpsr = (cpsr & ~MODE_MASK) | USR_MODE; + +#ifdef CONFIG_ARM_THUMB + if (elf_hwcap & HWCAP_THUMB) { + /* + * The LSB of the handler determines if we're going to + * be using THUMB or ARM mode for this signal handler. + */ + thumb = handler & 1; + + /* + * Clear the If-Then Thumb-2 execution state. ARM spec + * requires this to be all 000s in ARM mode. Snapdragon + * S4/Krait misbehaves on a Thumb=>ARM signal transition + * without this. + * + * We must do this whenever we are running on a Thumb-2 + * capable CPU, which includes ARMv6T2. However, we elect + * to always do this to simplify the code; this field is + * marked UNK/SBZP for older architectures. + */ + cpsr &= ~PSR_IT_MASK; + + if (thumb) { + cpsr |= PSR_T_BIT; + } else + cpsr &= ~PSR_T_BIT; + } +#endif + + if (ksig->ka.sa.sa_flags & SA_RESTORER) { + retcode = (unsigned long)ksig->ka.sa.sa_restorer; + if (fdpic) { + /* + * We need code to load the function descriptor. + * That code follows the standard sigreturn code + * (6 words), and is made of 3 + 2 words for each + * variant. The 4th copied word is the actual FD + * address that the assembly code expects. + */ + idx = 6 + thumb * 3; + if (ksig->ka.sa.sa_flags & SA_SIGINFO) + idx += 5; + if (__put_user(sigreturn_codes[idx], rc ) || + __put_user(sigreturn_codes[idx+1], rc+1) || + __put_user(sigreturn_codes[idx+2], rc+2) || + __put_user(retcode, rc+3)) + return 1; + goto rc_finish; + } + } else { + idx = thumb << 1; + if (ksig->ka.sa.sa_flags & SA_SIGINFO) + idx += 3; + + /* + * Put the sigreturn code on the stack no matter which return + * mechanism we use in order to remain ABI compliant + */ + if (__put_user(sigreturn_codes[idx], rc) || + __put_user(sigreturn_codes[idx+1], rc+1)) + return 1; + +rc_finish: +#ifdef CONFIG_MMU + if (cpsr & MODE32_BIT) { + struct mm_struct *mm = current->mm; + + /* + * 32-bit code can use the signal return page + * except when the MPU has protected the vectors + * page from PL0 + */ + retcode = mm->context.sigpage + signal_return_offset + + (idx << 2) + thumb; + } else +#endif + { + /* + * Ensure that the instruction cache sees + * the return code written onto the stack. + */ + flush_icache_range((unsigned long)rc, + (unsigned long)(rc + 3)); + + retcode = ((unsigned long)rc) + thumb; + } + } + + regs->ARM_r0 = ksig->sig; + regs->ARM_sp = (unsigned long)frame; + regs->ARM_lr = retcode; + regs->ARM_pc = handler; + if (fdpic) + regs->ARM_r9 = handler_fdpic_GOT; + regs->ARM_cpsr = cpsr; + + return 0; +} + +static int +setup_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) +{ + struct sigframe __user *frame = get_sigframe(ksig, regs, sizeof(*frame)); + int err = 0; + + if (!frame) + return 1; + + /* + * Set uc.uc_flags to a value which sc.trap_no would never have. + */ + err = __put_user(0x5ac3c35a, &frame->uc.uc_flags); + + err |= setup_sigframe(frame, regs, set); + if (err == 0) + err = setup_return(regs, ksig, frame->retcode, frame); + + return err; +} + +static int +setup_rt_frame(struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) +{ + struct rt_sigframe __user *frame = get_sigframe(ksig, regs, sizeof(*frame)); + int err = 0; + + if (!frame) + return 1; + + err |= copy_siginfo_to_user(&frame->info, &ksig->info); + + err |= __put_user(0, &frame->sig.uc.uc_flags); + err |= __put_user(NULL, &frame->sig.uc.uc_link); + + err |= __save_altstack(&frame->sig.uc.uc_stack, regs->ARM_sp); + err |= setup_sigframe(&frame->sig, regs, set); + if (err == 0) + err = setup_return(regs, ksig, frame->sig.retcode, frame); + + if (err == 0) { + /* + * For realtime signals we must also set the second and third + * arguments for the signal handler. + * -- Peter Maydell <pmaydell@chiark.greenend.org.uk> 2000-12-06 + */ + regs->ARM_r1 = (unsigned long)&frame->info; + regs->ARM_r2 = (unsigned long)&frame->sig.uc; + } + + return err; +} + +/* + * OK, we're invoking a handler + */ +static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) +{ + sigset_t *oldset = sigmask_to_save(); + int ret; + + /* + * Perform fixup for the pre-signal frame. + */ + rseq_signal_deliver(ksig, regs); + + /* + * Set up the stack frame + */ + if (ksig->ka.sa.sa_flags & SA_SIGINFO) + ret = setup_rt_frame(ksig, oldset, regs); + else + ret = setup_frame(ksig, oldset, regs); + + /* + * Check that the resulting registers are actually sane. + */ + ret |= !valid_user_regs(regs); + + signal_setup_done(ret, ksig, 0); +} + +/* + * Note that 'init' is a special process: it doesn't get signals it doesn't + * want to handle. Thus you cannot kill init even with a SIGKILL even by + * mistake. + * + * Note that we go through the signals twice: once to check the signals that + * the kernel can handle, and then we build all the user-level signal handling + * stack-frames in one go after that. + */ +static int do_signal(struct pt_regs *regs, int syscall) +{ + unsigned int retval = 0, continue_addr = 0, restart_addr = 0; + struct ksignal ksig; + int restart = 0; + + /* + * If we were from a system call, check for system call restarting... + */ + if (syscall) { + continue_addr = regs->ARM_pc; + restart_addr = continue_addr - (thumb_mode(regs) ? 2 : 4); + retval = regs->ARM_r0; + + /* + * Prepare for system call restart. We do this here so that a + * debugger will see the already changed PSW. + */ + switch (retval) { + case -ERESTART_RESTARTBLOCK: + restart -= 2; + fallthrough; + case -ERESTARTNOHAND: + case -ERESTARTSYS: + case -ERESTARTNOINTR: + restart++; + regs->ARM_r0 = regs->ARM_ORIG_r0; + regs->ARM_pc = restart_addr; + break; + } + } + + /* + * Get the signal to deliver. When running under ptrace, at this + * point the debugger may change all our registers ... + */ + /* + * Depending on the signal settings we may need to revert the + * decision to restart the system call. But skip this if a + * debugger has chosen to restart at a different PC. + */ + if (get_signal(&ksig)) { + /* handler */ + if (unlikely(restart) && regs->ARM_pc == restart_addr) { + if (retval == -ERESTARTNOHAND || + retval == -ERESTART_RESTARTBLOCK + || (retval == -ERESTARTSYS + && !(ksig.ka.sa.sa_flags & SA_RESTART))) { + regs->ARM_r0 = -EINTR; + regs->ARM_pc = continue_addr; + } + } + handle_signal(&ksig, regs); + } else { + /* no handler */ + restore_saved_sigmask(); + if (unlikely(restart) && regs->ARM_pc == restart_addr) { + regs->ARM_pc = continue_addr; + return restart; + } + } + return 0; +} + +asmlinkage int +do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall) +{ + /* + * The assembly code enters us with IRQs off, but it hasn't + * informed the tracing code of that for efficiency reasons. + * Update the trace code with the current status. + */ + trace_hardirqs_off(); + do { + if (likely(thread_flags & _TIF_NEED_RESCHED)) { + schedule(); + } else { + if (unlikely(!user_mode(regs))) + return 0; + local_irq_enable(); + if (thread_flags & (_TIF_SIGPENDING | _TIF_NOTIFY_SIGNAL)) { + int restart = do_signal(regs, syscall); + if (unlikely(restart)) { + /* + * Restart without handlers. + * Deal with it without leaving + * the kernel space. + */ + return restart; + } + syscall = 0; + } else if (thread_flags & _TIF_UPROBE) { + uprobe_notify_resume(regs); + } else { + resume_user_mode_work(regs); + } + } + local_irq_disable(); + thread_flags = read_thread_flags(); + } while (thread_flags & _TIF_WORK_MASK); + return 0; +} + +struct page *get_signal_page(void) +{ + unsigned long ptr; + unsigned offset; + struct page *page; + void *addr; + + page = alloc_pages(GFP_KERNEL, 0); + + if (!page) + return NULL; + + addr = page_address(page); + + /* Poison the entire page */ + memset32(addr, __opcode_to_mem_arm(0xe7fddef1), + PAGE_SIZE / sizeof(u32)); + + /* Give the signal return code some randomness */ + offset = 0x200 + (get_random_u16() & 0x7fc); + signal_return_offset = offset; + + /* Copy signal return handlers into the page */ + memcpy(addr + offset, sigreturn_codes, sizeof(sigreturn_codes)); + + /* Flush out all instructions in this page */ + ptr = (unsigned long)addr; + flush_icache_range(ptr, ptr + PAGE_SIZE); + + return page; +} + +#ifdef CONFIG_DEBUG_RSEQ +asmlinkage void do_rseq_syscall(struct pt_regs *regs) +{ + rseq_syscall(regs); +} +#endif + +/* + * Compile-time assertions for siginfo_t offsets. Check NSIG* as well, as + * changes likely come with new fields that should be added below. + */ +static_assert(NSIGILL == 11); +static_assert(NSIGFPE == 15); +static_assert(NSIGSEGV == 9); +static_assert(NSIGBUS == 5); +static_assert(NSIGTRAP == 6); +static_assert(NSIGCHLD == 6); +static_assert(NSIGSYS == 2); +static_assert(sizeof(siginfo_t) == 128); +static_assert(__alignof__(siginfo_t) == 4); +static_assert(offsetof(siginfo_t, si_signo) == 0x00); +static_assert(offsetof(siginfo_t, si_errno) == 0x04); +static_assert(offsetof(siginfo_t, si_code) == 0x08); +static_assert(offsetof(siginfo_t, si_pid) == 0x0c); +static_assert(offsetof(siginfo_t, si_uid) == 0x10); +static_assert(offsetof(siginfo_t, si_tid) == 0x0c); +static_assert(offsetof(siginfo_t, si_overrun) == 0x10); +static_assert(offsetof(siginfo_t, si_status) == 0x14); +static_assert(offsetof(siginfo_t, si_utime) == 0x18); +static_assert(offsetof(siginfo_t, si_stime) == 0x1c); +static_assert(offsetof(siginfo_t, si_value) == 0x14); +static_assert(offsetof(siginfo_t, si_int) == 0x14); +static_assert(offsetof(siginfo_t, si_ptr) == 0x14); +static_assert(offsetof(siginfo_t, si_addr) == 0x0c); +static_assert(offsetof(siginfo_t, si_addr_lsb) == 0x10); +static_assert(offsetof(siginfo_t, si_lower) == 0x14); +static_assert(offsetof(siginfo_t, si_upper) == 0x18); +static_assert(offsetof(siginfo_t, si_pkey) == 0x14); +static_assert(offsetof(siginfo_t, si_perf_data) == 0x10); +static_assert(offsetof(siginfo_t, si_perf_type) == 0x14); +static_assert(offsetof(siginfo_t, si_perf_flags) == 0x18); +static_assert(offsetof(siginfo_t, si_band) == 0x0c); +static_assert(offsetof(siginfo_t, si_fd) == 0x10); +static_assert(offsetof(siginfo_t, si_call_addr) == 0x0c); +static_assert(offsetof(siginfo_t, si_syscall) == 0x10); +static_assert(offsetof(siginfo_t, si_arch) == 0x14); diff --git a/arch/arm/kernel/signal.h b/arch/arm/kernel/signal.h new file mode 100644 index 000000000..cb076d30a --- /dev/null +++ b/arch/arm/kernel/signal.h @@ -0,0 +1,13 @@ +#include <asm/ucontext.h> + +struct sigframe { + struct ucontext uc; + unsigned long retcode[4]; +}; + +struct rt_sigframe { + struct siginfo info; + struct sigframe sig; +}; + +extern struct page *get_signal_page(void); diff --git a/arch/arm/kernel/sigreturn_codes.S b/arch/arm/kernel/sigreturn_codes.S new file mode 100644 index 000000000..7540ec51d --- /dev/null +++ b/arch/arm/kernel/sigreturn_codes.S @@ -0,0 +1,140 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * sigreturn_codes.S - code sinpets for sigreturn syscalls + * + * Created by: Victor Kamensky, 2013-08-13 + * Copyright: (C) 2013 Linaro Limited + */ + +#include <asm/assembler.h> +#include <asm/asm-offsets.h> +#include <asm/unistd.h> + +/* + * For ARM syscalls, we encode the syscall number into the instruction. + * With EABI, the syscall number has to be loaded into r7. As result + * ARM syscall sequence snippet will have move and svc in .arm encoding + * + * For Thumb syscalls, we pass the syscall number via r7. We therefore + * need two 16-bit instructions in .thumb encoding + * + * Please note sigreturn_codes code are not executed in place. Instead + * they just copied by kernel into appropriate places. Code inside of + * arch/arm/kernel/signal.c is very sensitive to layout of these code + * snippets. + */ + +/* + * In CPU_THUMBONLY case kernel arm opcodes are not allowed. + * Note in this case codes skips those instructions but it uses .org + * directive to keep correct layout of sigreturn_codes array. + */ +#ifndef CONFIG_CPU_THUMBONLY +#define ARM_OK(code...) code +#else +#define ARM_OK(code...) +#endif + + .macro arm_slot n + .org sigreturn_codes + 12 * (\n) +ARM_OK( .arm ) + .endm + + .macro thumb_slot n + .org sigreturn_codes + 12 * (\n) + 8 + .thumb + .endm + + .macro arm_fdpic_slot n + .org sigreturn_codes + 24 + 20 * (\n) +ARM_OK( .arm ) + .endm + + .macro thumb_fdpic_slot n + .org sigreturn_codes + 24 + 20 * (\n) + 12 + .thumb + .endm + + +#if __LINUX_ARM_ARCH__ <= 4 + /* + * Note we manually set minimally required arch that supports + * required thumb opcodes for early arch versions. It is OK + * for this file to be used in combination with other + * lower arch variants, since these code snippets are only + * used as input data. + */ + .arch armv4t +#endif + + .section .rodata + .global sigreturn_codes + .type sigreturn_codes, #object + + .align + +sigreturn_codes: + + /* ARM sigreturn syscall code snippet */ + arm_slot 0 +ARM_OK( mov r7, #(__NR_sigreturn - __NR_SYSCALL_BASE) ) +ARM_OK( swi #(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE) ) + + /* Thumb sigreturn syscall code snippet */ + thumb_slot 0 + movs r7, #(__NR_sigreturn - __NR_SYSCALL_BASE) + swi #0 + + /* ARM sigreturn_rt syscall code snippet */ + arm_slot 1 +ARM_OK( mov r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE) ) +ARM_OK( swi #(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE) ) + + /* Thumb sigreturn_rt syscall code snippet */ + thumb_slot 1 + movs r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE) + swi #0 + + /* ARM sigreturn restorer FDPIC bounce code snippet */ + arm_fdpic_slot 0 +ARM_OK( ldr r3, [sp, #SIGFRAME_RC3_OFFSET] ) +ARM_OK( ldmia r3, {r3, r9} ) +#ifdef CONFIG_ARM_THUMB +ARM_OK( bx r3 ) +#else +ARM_OK( ret r3 ) +#endif + + /* Thumb sigreturn restorer FDPIC bounce code snippet */ + thumb_fdpic_slot 0 + ldr r3, [sp, #SIGFRAME_RC3_OFFSET] + ldmia r3, {r2, r3} + mov r9, r3 + bx r2 + + /* ARM sigreturn_rt restorer FDPIC bounce code snippet */ + arm_fdpic_slot 1 +ARM_OK( ldr r3, [sp, #RT_SIGFRAME_RC3_OFFSET] ) +ARM_OK( ldmia r3, {r3, r9} ) +#ifdef CONFIG_ARM_THUMB +ARM_OK( bx r3 ) +#else +ARM_OK( ret r3 ) +#endif + + /* Thumb sigreturn_rt restorer FDPIC bounce code snippet */ + thumb_fdpic_slot 1 + ldr r3, [sp, #RT_SIGFRAME_RC3_OFFSET] + ldmia r3, {r2, r3} + mov r9, r3 + bx r2 + + /* + * Note on additional space: setup_return in signal.c + * always copies the same number of words regardless whether + * it is thumb case or not, so we need one additional padding + * word after the last entry. + */ + .space 4 + + .size sigreturn_codes, . - sigreturn_codes diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S new file mode 100644 index 000000000..a86a1d4f3 --- /dev/null +++ b/arch/arm/kernel/sleep.S @@ -0,0 +1,194 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/linkage.h> +#include <linux/threads.h> +#include <asm/asm-offsets.h> +#include <asm/assembler.h> +#include <asm/glue-cache.h> +#include <asm/glue-proc.h> + .text + +/* + * Implementation of MPIDR hash algorithm through shifting + * and OR'ing. + * + * @dst: register containing hash result + * @rs0: register containing affinity level 0 bit shift + * @rs1: register containing affinity level 1 bit shift + * @rs2: register containing affinity level 2 bit shift + * @mpidr: register containing MPIDR value + * @mask: register containing MPIDR mask + * + * Pseudo C-code: + * + *u32 dst; + * + *compute_mpidr_hash(u32 rs0, u32 rs1, u32 rs2, u32 mpidr, u32 mask) { + * u32 aff0, aff1, aff2; + * u32 mpidr_masked = mpidr & mask; + * aff0 = mpidr_masked & 0xff; + * aff1 = mpidr_masked & 0xff00; + * aff2 = mpidr_masked & 0xff0000; + * dst = (aff0 >> rs0 | aff1 >> rs1 | aff2 >> rs2); + *} + * Input registers: rs0, rs1, rs2, mpidr, mask + * Output register: dst + * Note: input and output registers must be disjoint register sets + (eg: a macro instance with mpidr = r1 and dst = r1 is invalid) + */ + .macro compute_mpidr_hash dst, rs0, rs1, rs2, mpidr, mask + and \mpidr, \mpidr, \mask @ mask out MPIDR bits + and \dst, \mpidr, #0xff @ mask=aff0 + ARM( mov \dst, \dst, lsr \rs0 ) @ dst=aff0>>rs0 + THUMB( lsr \dst, \dst, \rs0 ) + and \mask, \mpidr, #0xff00 @ mask = aff1 + ARM( orr \dst, \dst, \mask, lsr \rs1 ) @ dst|=(aff1>>rs1) + THUMB( lsr \mask, \mask, \rs1 ) + THUMB( orr \dst, \dst, \mask ) + and \mask, \mpidr, #0xff0000 @ mask = aff2 + ARM( orr \dst, \dst, \mask, lsr \rs2 ) @ dst|=(aff2>>rs2) + THUMB( lsr \mask, \mask, \rs2 ) + THUMB( orr \dst, \dst, \mask ) + .endm + +/* + * Save CPU state for a suspend. This saves the CPU general purpose + * registers, and allocates space on the kernel stack to save the CPU + * specific registers and some other data for resume. + * r0 = suspend function arg0 + * r1 = suspend function + * r2 = MPIDR value the resuming CPU will use + */ +ENTRY(__cpu_suspend) + stmfd sp!, {r4 - r11, lr} +#ifdef MULTI_CPU + ldr r10, =processor + ldr r4, [r10, #CPU_SLEEP_SIZE] @ size of CPU sleep state +#else + ldr r4, =cpu_suspend_size +#endif + mov r5, sp @ current virtual SP +#ifdef CONFIG_VMAP_STACK + @ Run the suspend code from the overflow stack so we don't have to rely + @ on vmalloc-to-phys conversions anywhere in the arch suspend code. + @ The original SP value captured in R5 will be restored on the way out. + ldr_this_cpu sp, overflow_stack_ptr, r6, r7 +#endif + add r4, r4, #12 @ Space for pgd, virt sp, phys resume fn + sub sp, sp, r4 @ allocate CPU state on stack + ldr r3, =sleep_save_sp + stmfd sp!, {r0, r1} @ save suspend func arg and pointer + ldr r3, [r3, #SLEEP_SAVE_SP_VIRT] + ALT_SMP(W(nop)) @ don't use adr_l inside ALT_SMP() + ALT_UP_B(1f) + adr_l r0, mpidr_hash + /* This ldmia relies on the memory layout of the mpidr_hash struct */ + ldmia r0, {r1, r6-r8} @ r1 = mpidr mask (r6,r7,r8) = l[0,1,2] shifts + compute_mpidr_hash r0, r6, r7, r8, r2, r1 + add r3, r3, r0, lsl #2 +1: mov r2, r5 @ virtual SP + mov r1, r4 @ size of save block + add r0, sp, #8 @ pointer to save block + bl __cpu_suspend_save + badr lr, cpu_suspend_abort + ldmfd sp!, {r0, pc} @ call suspend fn +ENDPROC(__cpu_suspend) + .ltorg + +cpu_suspend_abort: + ldmia sp!, {r1 - r3} @ pop phys pgd, virt SP, phys resume fn + teq r0, #0 + moveq r0, #1 @ force non-zero value + mov sp, r2 + ldmfd sp!, {r4 - r11, pc} +ENDPROC(cpu_suspend_abort) + +/* + * r0 = control register value + */ + .align 5 + .pushsection .idmap.text,"ax" +ENTRY(cpu_resume_mmu) + ldr r3, =cpu_resume_after_mmu + instr_sync + mcr p15, 0, r0, c1, c0, 0 @ turn on MMU, I-cache, etc + mrc p15, 0, r0, c0, c0, 0 @ read id reg + instr_sync + mov r0, r0 + mov r0, r0 + ret r3 @ jump to virtual address +ENDPROC(cpu_resume_mmu) + .popsection +cpu_resume_after_mmu: +#if defined(CONFIG_VMAP_STACK) && !defined(CONFIG_ARM_LPAE) + @ Before using the vmap'ed stack, we have to switch to swapper_pg_dir + @ as the ID map does not cover the vmalloc region. + mrc p15, 0, ip, c2, c0, 1 @ read TTBR1 + mcr p15, 0, ip, c2, c0, 0 @ set TTBR0 + instr_sync +#endif + bl cpu_init @ restore the und/abt/irq banked regs + mov r0, #0 @ return zero on success + ldmfd sp!, {r4 - r11, pc} +ENDPROC(cpu_resume_after_mmu) + + .text + .align + +#ifdef CONFIG_MCPM + .arm +THUMB( .thumb ) +ENTRY(cpu_resume_no_hyp) +ARM_BE8(setend be) @ ensure we are in BE mode + b no_hyp +#endif + +#ifdef CONFIG_MMU + .arm +ENTRY(cpu_resume_arm) + THUMB( badr r9, 1f ) @ Kernel is entered in ARM. + THUMB( bx r9 ) @ If this is a Thumb-2 kernel, + THUMB( .thumb ) @ switch to Thumb now. + THUMB(1: ) +#endif + +ENTRY(cpu_resume) +ARM_BE8(setend be) @ ensure we are in BE mode +#ifdef CONFIG_ARM_VIRT_EXT + bl __hyp_stub_install_secondary +#endif + safe_svcmode_maskall r1 +no_hyp: + mov r1, #0 + ALT_SMP(mrc p15, 0, r0, c0, c0, 5) + ALT_UP_B(1f) + adr_l r2, mpidr_hash @ r2 = struct mpidr_hash phys address + + /* + * This ldmia relies on the memory layout of the mpidr_hash + * struct mpidr_hash. + */ + ldmia r2, { r3-r6 } @ r3 = mpidr mask (r4,r5,r6) = l[0,1,2] shifts + compute_mpidr_hash r1, r4, r5, r6, r0, r3 +1: + ldr_l r0, sleep_save_sp + SLEEP_SAVE_SP_PHYS + ldr r0, [r0, r1, lsl #2] + + @ load phys pgd, stack, resume fn + ARM( ldmia r0!, {r1, sp, pc} ) +THUMB( ldmia r0!, {r1, r2, r3} ) +THUMB( mov sp, r2 ) +THUMB( bx r3 ) +ENDPROC(cpu_resume) + +#ifdef CONFIG_MMU +ENDPROC(cpu_resume_arm) +#endif +#ifdef CONFIG_MCPM +ENDPROC(cpu_resume_no_hyp) +#endif + + .data + .align 2 + .type sleep_save_sp, #object +ENTRY(sleep_save_sp) + .space SLEEP_SAVE_SP_SZ @ struct sleep_save_sp diff --git a/arch/arm/kernel/smccc-call.S b/arch/arm/kernel/smccc-call.S new file mode 100644 index 000000000..931df62a7 --- /dev/null +++ b/arch/arm/kernel/smccc-call.S @@ -0,0 +1,64 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * Copyright (c) 2015, Linaro Limited + */ +#include <linux/linkage.h> +#include <linux/arm-smccc.h> + +#include <asm/asm-offsets.h> +#include <asm/opcodes-sec.h> +#include <asm/opcodes-virt.h> +#include <asm/unwind.h> + + /* + * Wrap c macros in asm macros to delay expansion until after the + * SMCCC asm macro is expanded. + */ + .macro SMCCC_SMC + __SMC(0) + .endm + + .macro SMCCC_HVC + __HVC(0) + .endm + + .macro SMCCC instr +UNWIND( .fnstart) + mov r12, sp + push {r4-r7} +UNWIND( .save {r4-r7}) + ldm r12, {r4-r7} + \instr + ldr r4, [sp, #36] + cmp r4, #0 + beq 1f // No quirk structure + ldr r5, [r4, #ARM_SMCCC_QUIRK_ID_OFFS] + cmp r5, #ARM_SMCCC_QUIRK_QCOM_A6 + bne 1f // No quirk present + str r6, [r4, #ARM_SMCCC_QUIRK_STATE_OFFS] +1: pop {r4-r7} + ldr r12, [sp, #(4 * 4)] + stm r12, {r0-r3} + bx lr +UNWIND( .fnend) + .endm + +/* + * void smccc_smc(unsigned long a0, unsigned long a1, unsigned long a2, + * unsigned long a3, unsigned long a4, unsigned long a5, + * unsigned long a6, unsigned long a7, struct arm_smccc_res *res, + * struct arm_smccc_quirk *quirk) + */ +ENTRY(__arm_smccc_smc) + SMCCC SMCCC_SMC +ENDPROC(__arm_smccc_smc) + +/* + * void smccc_hvc(unsigned long a0, unsigned long a1, unsigned long a2, + * unsigned long a3, unsigned long a4, unsigned long a5, + * unsigned long a6, unsigned long a7, struct arm_smccc_res *res, + * struct arm_smccc_quirk *quirk) + */ +ENTRY(__arm_smccc_hvc) + SMCCC SMCCC_HVC +ENDPROC(__arm_smccc_hvc) diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c new file mode 100644 index 000000000..978db2d96 --- /dev/null +++ b/arch/arm/kernel/smp.c @@ -0,0 +1,856 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/smp.c + * + * Copyright (C) 2002 ARM Limited, All Rights Reserved. + */ +#include <linux/module.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/spinlock.h> +#include <linux/sched/mm.h> +#include <linux/sched/hotplug.h> +#include <linux/sched/task_stack.h> +#include <linux/interrupt.h> +#include <linux/cache.h> +#include <linux/profile.h> +#include <linux/errno.h> +#include <linux/mm.h> +#include <linux/err.h> +#include <linux/cpu.h> +#include <linux/seq_file.h> +#include <linux/irq.h> +#include <linux/nmi.h> +#include <linux/percpu.h> +#include <linux/clockchips.h> +#include <linux/completion.h> +#include <linux/cpufreq.h> +#include <linux/irq_work.h> +#include <linux/kernel_stat.h> + +#include <linux/atomic.h> +#include <asm/bugs.h> +#include <asm/smp.h> +#include <asm/cacheflush.h> +#include <asm/cpu.h> +#include <asm/cputype.h> +#include <asm/exception.h> +#include <asm/idmap.h> +#include <asm/topology.h> +#include <asm/mmu_context.h> +#include <asm/procinfo.h> +#include <asm/processor.h> +#include <asm/sections.h> +#include <asm/tlbflush.h> +#include <asm/ptrace.h> +#include <asm/smp_plat.h> +#include <asm/virt.h> +#include <asm/mach/arch.h> +#include <asm/mpu.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/ipi.h> + +/* + * as from 2.5, kernels no longer have an init_tasks structure + * so we need some other way of telling a new secondary core + * where to place its SVC stack + */ +struct secondary_data secondary_data; + +enum ipi_msg_type { + IPI_WAKEUP, + IPI_TIMER, + IPI_RESCHEDULE, + IPI_CALL_FUNC, + IPI_CPU_STOP, + IPI_IRQ_WORK, + IPI_COMPLETION, + NR_IPI, + /* + * CPU_BACKTRACE is special and not included in NR_IPI + * or tracable with trace_ipi_* + */ + IPI_CPU_BACKTRACE = NR_IPI, + /* + * SGI8-15 can be reserved by secure firmware, and thus may + * not be usable by the kernel. Please keep the above limited + * to at most 8 entries. + */ + MAX_IPI +}; + +static int ipi_irq_base __read_mostly; +static int nr_ipi __read_mostly = NR_IPI; +static struct irq_desc *ipi_desc[MAX_IPI] __read_mostly; + +static void ipi_setup(int cpu); + +static DECLARE_COMPLETION(cpu_running); + +static struct smp_operations smp_ops __ro_after_init; + +void __init smp_set_ops(const struct smp_operations *ops) +{ + if (ops) + smp_ops = *ops; +}; + +static unsigned long get_arch_pgd(pgd_t *pgd) +{ +#ifdef CONFIG_ARM_LPAE + return __phys_to_pfn(virt_to_phys(pgd)); +#else + return virt_to_phys(pgd); +#endif +} + +#if defined(CONFIG_BIG_LITTLE) && defined(CONFIG_HARDEN_BRANCH_PREDICTOR) +static int secondary_biglittle_prepare(unsigned int cpu) +{ + if (!cpu_vtable[cpu]) + cpu_vtable[cpu] = kzalloc(sizeof(*cpu_vtable[cpu]), GFP_KERNEL); + + return cpu_vtable[cpu] ? 0 : -ENOMEM; +} + +static void secondary_biglittle_init(void) +{ + init_proc_vtable(lookup_processor(read_cpuid_id())->proc); +} +#else +static int secondary_biglittle_prepare(unsigned int cpu) +{ + return 0; +} + +static void secondary_biglittle_init(void) +{ +} +#endif + +int __cpu_up(unsigned int cpu, struct task_struct *idle) +{ + int ret; + + if (!smp_ops.smp_boot_secondary) + return -ENOSYS; + + ret = secondary_biglittle_prepare(cpu); + if (ret) + return ret; + + /* + * We need to tell the secondary core where to find + * its stack and the page tables. + */ + secondary_data.stack = task_stack_page(idle) + THREAD_START_SP; +#ifdef CONFIG_ARM_MPU + secondary_data.mpu_rgn_info = &mpu_rgn_info; +#endif + +#ifdef CONFIG_MMU + secondary_data.pgdir = virt_to_phys(idmap_pgd); + secondary_data.swapper_pg_dir = get_arch_pgd(swapper_pg_dir); +#endif + secondary_data.task = idle; + sync_cache_w(&secondary_data); + + /* + * Now bring the CPU into our world. + */ + ret = smp_ops.smp_boot_secondary(cpu, idle); + if (ret == 0) { + /* + * CPU was successfully started, wait for it + * to come online or time out. + */ + wait_for_completion_timeout(&cpu_running, + msecs_to_jiffies(1000)); + + if (!cpu_online(cpu)) { + pr_crit("CPU%u: failed to come online\n", cpu); + ret = -EIO; + } + } else { + pr_err("CPU%u: failed to boot: %d\n", cpu, ret); + } + + + memset(&secondary_data, 0, sizeof(secondary_data)); + return ret; +} + +/* platform specific SMP operations */ +void __init smp_init_cpus(void) +{ + if (smp_ops.smp_init_cpus) + smp_ops.smp_init_cpus(); +} + +int platform_can_secondary_boot(void) +{ + return !!smp_ops.smp_boot_secondary; +} + +int platform_can_cpu_hotplug(void) +{ +#ifdef CONFIG_HOTPLUG_CPU + if (smp_ops.cpu_kill) + return 1; +#endif + + return 0; +} + +#ifdef CONFIG_HOTPLUG_CPU +static int platform_cpu_kill(unsigned int cpu) +{ + if (smp_ops.cpu_kill) + return smp_ops.cpu_kill(cpu); + return 1; +} + +static int platform_cpu_disable(unsigned int cpu) +{ + if (smp_ops.cpu_disable) + return smp_ops.cpu_disable(cpu); + + return 0; +} + +int platform_can_hotplug_cpu(unsigned int cpu) +{ + /* cpu_die must be specified to support hotplug */ + if (!smp_ops.cpu_die) + return 0; + + if (smp_ops.cpu_can_disable) + return smp_ops.cpu_can_disable(cpu); + + /* + * By default, allow disabling all CPUs except the first one, + * since this is special on a lot of platforms, e.g. because + * of clock tick interrupts. + */ + return cpu != 0; +} + +static void ipi_teardown(int cpu) +{ + int i; + + if (WARN_ON_ONCE(!ipi_irq_base)) + return; + + for (i = 0; i < nr_ipi; i++) + disable_percpu_irq(ipi_irq_base + i); +} + +/* + * __cpu_disable runs on the processor to be shutdown. + */ +int __cpu_disable(void) +{ + unsigned int cpu = smp_processor_id(); + int ret; + + ret = platform_cpu_disable(cpu); + if (ret) + return ret; + +#ifdef CONFIG_GENERIC_ARCH_TOPOLOGY + remove_cpu_topology(cpu); +#endif + + /* + * Take this CPU offline. Once we clear this, we can't return, + * and we must not schedule until we're ready to give up the cpu. + */ + set_cpu_online(cpu, false); + ipi_teardown(cpu); + + /* + * OK - migrate IRQs away from this CPU + */ + irq_migrate_all_off_this_cpu(); + + /* + * Flush user cache and TLB mappings, and then remove this CPU + * from the vm mask set of all processes. + * + * Caches are flushed to the Level of Unification Inner Shareable + * to write-back dirty lines to unified caches shared by all CPUs. + */ + flush_cache_louis(); + local_flush_tlb_all(); + + return 0; +} + +/* + * called on the thread which is asking for a CPU to be shutdown - + * waits until shutdown has completed, or it is timed out. + */ +void __cpu_die(unsigned int cpu) +{ + if (!cpu_wait_death(cpu, 5)) { + pr_err("CPU%u: cpu didn't die\n", cpu); + return; + } + pr_debug("CPU%u: shutdown\n", cpu); + + clear_tasks_mm_cpumask(cpu); + /* + * platform_cpu_kill() is generally expected to do the powering off + * and/or cutting of clocks to the dying CPU. Optionally, this may + * be done by the CPU which is dying in preference to supporting + * this call, but that means there is _no_ synchronisation between + * the requesting CPU and the dying CPU actually losing power. + */ + if (!platform_cpu_kill(cpu)) + pr_err("CPU%u: unable to kill\n", cpu); +} + +/* + * Called from the idle thread for the CPU which has been shutdown. + * + * Note that we disable IRQs here, but do not re-enable them + * before returning to the caller. This is also the behaviour + * of the other hotplug-cpu capable cores, so presumably coming + * out of idle fixes this. + */ +void arch_cpu_idle_dead(void) +{ + unsigned int cpu = smp_processor_id(); + + idle_task_exit(); + + local_irq_disable(); + + /* + * Flush the data out of the L1 cache for this CPU. This must be + * before the completion to ensure that data is safely written out + * before platform_cpu_kill() gets called - which may disable + * *this* CPU and power down its cache. + */ + flush_cache_louis(); + + /* + * Tell __cpu_die() that this CPU is now safe to dispose of. Once + * this returns, power and/or clocks can be removed at any point + * from this CPU and its cache by platform_cpu_kill(). + */ + (void)cpu_report_death(); + + /* + * Ensure that the cache lines associated with that completion are + * written out. This covers the case where _this_ CPU is doing the + * powering down, to ensure that the completion is visible to the + * CPU waiting for this one. + */ + flush_cache_louis(); + + /* + * The actual CPU shutdown procedure is at least platform (if not + * CPU) specific. This may remove power, or it may simply spin. + * + * Platforms are generally expected *NOT* to return from this call, + * although there are some which do because they have no way to + * power down the CPU. These platforms are the _only_ reason we + * have a return path which uses the fragment of assembly below. + * + * The return path should not be used for platforms which can + * power off the CPU. + */ + if (smp_ops.cpu_die) + smp_ops.cpu_die(cpu); + + pr_warn("CPU%u: smp_ops.cpu_die() returned, trying to resuscitate\n", + cpu); + + /* + * Do not return to the idle loop - jump back to the secondary + * cpu initialisation. There's some initialisation which needs + * to be repeated to undo the effects of taking the CPU offline. + */ + __asm__("mov sp, %0\n" + " mov fp, #0\n" + " mov r0, %1\n" + " b secondary_start_kernel" + : + : "r" (task_stack_page(current) + THREAD_SIZE - 8), + "r" (current) + : "r0"); +} +#endif /* CONFIG_HOTPLUG_CPU */ + +/* + * Called by both boot and secondaries to move global data into + * per-processor storage. + */ +static void smp_store_cpu_info(unsigned int cpuid) +{ + struct cpuinfo_arm *cpu_info = &per_cpu(cpu_data, cpuid); + + cpu_info->loops_per_jiffy = loops_per_jiffy; + cpu_info->cpuid = read_cpuid_id(); + + store_cpu_topology(cpuid); + check_cpu_icache_size(cpuid); +} + +static void set_current(struct task_struct *cur) +{ + /* Set TPIDRURO */ + asm("mcr p15, 0, %0, c13, c0, 3" :: "r"(cur) : "memory"); +} + +/* + * This is the secondary CPU boot entry. We're using this CPUs + * idle thread stack, but a set of temporary page tables. + */ +asmlinkage void secondary_start_kernel(struct task_struct *task) +{ + struct mm_struct *mm = &init_mm; + unsigned int cpu; + + set_current(task); + + secondary_biglittle_init(); + + /* + * The identity mapping is uncached (strongly ordered), so + * switch away from it before attempting any exclusive accesses. + */ + cpu_switch_mm(mm->pgd, mm); + local_flush_bp_all(); + enter_lazy_tlb(mm, current); + local_flush_tlb_all(); + + /* + * All kernel threads share the same mm context; grab a + * reference and switch to it. + */ + cpu = smp_processor_id(); + mmgrab(mm); + current->active_mm = mm; + cpumask_set_cpu(cpu, mm_cpumask(mm)); + + cpu_init(); + +#ifndef CONFIG_MMU + setup_vectors_base(); +#endif + pr_debug("CPU%u: Booted secondary processor\n", cpu); + + trace_hardirqs_off(); + + /* + * Give the platform a chance to do its own initialisation. + */ + if (smp_ops.smp_secondary_init) + smp_ops.smp_secondary_init(cpu); + + notify_cpu_starting(cpu); + + ipi_setup(cpu); + + calibrate_delay(); + + smp_store_cpu_info(cpu); + + /* + * OK, now it's safe to let the boot CPU continue. Wait for + * the CPU migration code to notice that the CPU is online + * before we continue - which happens after __cpu_up returns. + */ + set_cpu_online(cpu, true); + + check_other_bugs(); + + complete(&cpu_running); + + local_irq_enable(); + local_fiq_enable(); + local_abt_enable(); + + /* + * OK, it's off to the idle thread for us + */ + cpu_startup_entry(CPUHP_AP_ONLINE_IDLE); +} + +void __init smp_cpus_done(unsigned int max_cpus) +{ + int cpu; + unsigned long bogosum = 0; + + for_each_online_cpu(cpu) + bogosum += per_cpu(cpu_data, cpu).loops_per_jiffy; + + printk(KERN_INFO "SMP: Total of %d processors activated " + "(%lu.%02lu BogoMIPS).\n", + num_online_cpus(), + bogosum / (500000/HZ), + (bogosum / (5000/HZ)) % 100); + + hyp_mode_check(); +} + +void __init smp_prepare_boot_cpu(void) +{ + set_my_cpu_offset(per_cpu_offset(smp_processor_id())); +} + +void __init smp_prepare_cpus(unsigned int max_cpus) +{ + unsigned int ncores = num_possible_cpus(); + + init_cpu_topology(); + + smp_store_cpu_info(smp_processor_id()); + + /* + * are we trying to boot more cores than exist? + */ + if (max_cpus > ncores) + max_cpus = ncores; + if (ncores > 1 && max_cpus) { + /* + * Initialise the present map, which describes the set of CPUs + * actually populated at the present time. A platform should + * re-initialize the map in the platforms smp_prepare_cpus() + * if present != possible (e.g. physical hotplug). + */ + init_cpu_present(cpu_possible_mask); + + /* + * Initialise the SCU if there are more than one CPU + * and let them know where to start. + */ + if (smp_ops.smp_prepare_cpus) + smp_ops.smp_prepare_cpus(max_cpus); + } +} + +static const char *ipi_types[NR_IPI] __tracepoint_string = { + [IPI_WAKEUP] = "CPU wakeup interrupts", + [IPI_TIMER] = "Timer broadcast interrupts", + [IPI_RESCHEDULE] = "Rescheduling interrupts", + [IPI_CALL_FUNC] = "Function call interrupts", + [IPI_CPU_STOP] = "CPU stop interrupts", + [IPI_IRQ_WORK] = "IRQ work interrupts", + [IPI_COMPLETION] = "completion interrupts", +}; + +static void smp_cross_call(const struct cpumask *target, unsigned int ipinr); + +void show_ipi_list(struct seq_file *p, int prec) +{ + unsigned int cpu, i; + + for (i = 0; i < NR_IPI; i++) { + if (!ipi_desc[i]) + continue; + + seq_printf(p, "%*s%u: ", prec - 1, "IPI", i); + + for_each_online_cpu(cpu) + seq_printf(p, "%10u ", irq_desc_kstat_cpu(ipi_desc[i], cpu)); + + seq_printf(p, " %s\n", ipi_types[i]); + } +} + +void arch_send_call_function_ipi_mask(const struct cpumask *mask) +{ + smp_cross_call(mask, IPI_CALL_FUNC); +} + +void arch_send_wakeup_ipi_mask(const struct cpumask *mask) +{ + smp_cross_call(mask, IPI_WAKEUP); +} + +void arch_send_call_function_single_ipi(int cpu) +{ + smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC); +} + +#ifdef CONFIG_IRQ_WORK +void arch_irq_work_raise(void) +{ + if (arch_irq_work_has_interrupt()) + smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK); +} +#endif + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST +void tick_broadcast(const struct cpumask *mask) +{ + smp_cross_call(mask, IPI_TIMER); +} +#endif + +static DEFINE_RAW_SPINLOCK(stop_lock); + +/* + * ipi_cpu_stop - handle IPI from smp_send_stop() + */ +static void ipi_cpu_stop(unsigned int cpu) +{ + if (system_state <= SYSTEM_RUNNING) { + raw_spin_lock(&stop_lock); + pr_crit("CPU%u: stopping\n", cpu); + dump_stack(); + raw_spin_unlock(&stop_lock); + } + + set_cpu_online(cpu, false); + + local_fiq_disable(); + local_irq_disable(); + + while (1) { + cpu_relax(); + wfe(); + } +} + +static DEFINE_PER_CPU(struct completion *, cpu_completion); + +int register_ipi_completion(struct completion *completion, int cpu) +{ + per_cpu(cpu_completion, cpu) = completion; + return IPI_COMPLETION; +} + +static void ipi_complete(unsigned int cpu) +{ + complete(per_cpu(cpu_completion, cpu)); +} + +/* + * Main handler for inter-processor interrupts + */ +static void do_handle_IPI(int ipinr) +{ + unsigned int cpu = smp_processor_id(); + + if ((unsigned)ipinr < NR_IPI) + trace_ipi_entry_rcuidle(ipi_types[ipinr]); + + switch (ipinr) { + case IPI_WAKEUP: + break; + +#ifdef CONFIG_GENERIC_CLOCKEVENTS_BROADCAST + case IPI_TIMER: + tick_receive_broadcast(); + break; +#endif + + case IPI_RESCHEDULE: + scheduler_ipi(); + break; + + case IPI_CALL_FUNC: + generic_smp_call_function_interrupt(); + break; + + case IPI_CPU_STOP: + ipi_cpu_stop(cpu); + break; + +#ifdef CONFIG_IRQ_WORK + case IPI_IRQ_WORK: + irq_work_run(); + break; +#endif + + case IPI_COMPLETION: + ipi_complete(cpu); + break; + + case IPI_CPU_BACKTRACE: + printk_deferred_enter(); + nmi_cpu_backtrace(get_irq_regs()); + printk_deferred_exit(); + break; + + default: + pr_crit("CPU%u: Unknown IPI message 0x%x\n", + cpu, ipinr); + break; + } + + if ((unsigned)ipinr < NR_IPI) + trace_ipi_exit_rcuidle(ipi_types[ipinr]); +} + +/* Legacy version, should go away once all irqchips have been converted */ +void handle_IPI(int ipinr, struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + irq_enter(); + do_handle_IPI(ipinr); + irq_exit(); + + set_irq_regs(old_regs); +} + +static irqreturn_t ipi_handler(int irq, void *data) +{ + do_handle_IPI(irq - ipi_irq_base); + return IRQ_HANDLED; +} + +static void smp_cross_call(const struct cpumask *target, unsigned int ipinr) +{ + trace_ipi_raise_rcuidle(target, ipi_types[ipinr]); + __ipi_send_mask(ipi_desc[ipinr], target); +} + +static void ipi_setup(int cpu) +{ + int i; + + if (WARN_ON_ONCE(!ipi_irq_base)) + return; + + for (i = 0; i < nr_ipi; i++) + enable_percpu_irq(ipi_irq_base + i, 0); +} + +void __init set_smp_ipi_range(int ipi_base, int n) +{ + int i; + + WARN_ON(n < MAX_IPI); + nr_ipi = min(n, MAX_IPI); + + for (i = 0; i < nr_ipi; i++) { + int err; + + err = request_percpu_irq(ipi_base + i, ipi_handler, + "IPI", &irq_stat); + WARN_ON(err); + + ipi_desc[i] = irq_to_desc(ipi_base + i); + irq_set_status_flags(ipi_base + i, IRQ_HIDDEN); + } + + ipi_irq_base = ipi_base; + + /* Setup the boot CPU immediately */ + ipi_setup(smp_processor_id()); +} + +void smp_send_reschedule(int cpu) +{ + smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE); +} + +void smp_send_stop(void) +{ + unsigned long timeout; + struct cpumask mask; + + cpumask_copy(&mask, cpu_online_mask); + cpumask_clear_cpu(smp_processor_id(), &mask); + if (!cpumask_empty(&mask)) + smp_cross_call(&mask, IPI_CPU_STOP); + + /* Wait up to one second for other CPUs to stop */ + timeout = USEC_PER_SEC; + while (num_online_cpus() > 1 && timeout--) + udelay(1); + + if (num_online_cpus() > 1) + pr_warn("SMP: failed to stop secondary CPUs\n"); +} + +/* In case panic() and panic() called at the same time on CPU1 and CPU2, + * and CPU 1 calls panic_smp_self_stop() before crash_smp_send_stop() + * CPU1 can't receive the ipi irqs from CPU2, CPU1 will be always online, + * kdump fails. So split out the panic_smp_self_stop() and add + * set_cpu_online(smp_processor_id(), false). + */ +void panic_smp_self_stop(void) +{ + pr_debug("CPU %u will stop doing anything useful since another CPU has paniced\n", + smp_processor_id()); + set_cpu_online(smp_processor_id(), false); + while (1) + cpu_relax(); +} + +#ifdef CONFIG_CPU_FREQ + +static DEFINE_PER_CPU(unsigned long, l_p_j_ref); +static DEFINE_PER_CPU(unsigned long, l_p_j_ref_freq); +static unsigned long global_l_p_j_ref; +static unsigned long global_l_p_j_ref_freq; + +static int cpufreq_callback(struct notifier_block *nb, + unsigned long val, void *data) +{ + struct cpufreq_freqs *freq = data; + struct cpumask *cpus = freq->policy->cpus; + int cpu, first = cpumask_first(cpus); + unsigned int lpj; + + if (freq->flags & CPUFREQ_CONST_LOOPS) + return NOTIFY_OK; + + if (!per_cpu(l_p_j_ref, first)) { + for_each_cpu(cpu, cpus) { + per_cpu(l_p_j_ref, cpu) = + per_cpu(cpu_data, cpu).loops_per_jiffy; + per_cpu(l_p_j_ref_freq, cpu) = freq->old; + } + + if (!global_l_p_j_ref) { + global_l_p_j_ref = loops_per_jiffy; + global_l_p_j_ref_freq = freq->old; + } + } + + if ((val == CPUFREQ_PRECHANGE && freq->old < freq->new) || + (val == CPUFREQ_POSTCHANGE && freq->old > freq->new)) { + loops_per_jiffy = cpufreq_scale(global_l_p_j_ref, + global_l_p_j_ref_freq, + freq->new); + + lpj = cpufreq_scale(per_cpu(l_p_j_ref, first), + per_cpu(l_p_j_ref_freq, first), freq->new); + for_each_cpu(cpu, cpus) + per_cpu(cpu_data, cpu).loops_per_jiffy = lpj; + } + return NOTIFY_OK; +} + +static struct notifier_block cpufreq_notifier = { + .notifier_call = cpufreq_callback, +}; + +static int __init register_cpufreq_notifier(void) +{ + return cpufreq_register_notifier(&cpufreq_notifier, + CPUFREQ_TRANSITION_NOTIFIER); +} +core_initcall(register_cpufreq_notifier); + +#endif + +static void raise_nmi(cpumask_t *mask) +{ + __ipi_send_mask(ipi_desc[IPI_CPU_BACKTRACE], mask); +} + +void arch_trigger_cpumask_backtrace(const cpumask_t *mask, bool exclude_self) +{ + nmi_trigger_cpumask_backtrace(mask, exclude_self, raise_nmi); +} diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c new file mode 100644 index 000000000..6de47fb3b --- /dev/null +++ b/arch/arm/kernel/smp_scu.c @@ -0,0 +1,124 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/smp_scu.c + * + * Copyright (C) 2002 ARM Ltd. + * All Rights Reserved + */ +#include <linux/init.h> +#include <linux/io.h> + +#include <asm/smp_plat.h> +#include <asm/smp_scu.h> +#include <asm/cacheflush.h> +#include <asm/cputype.h> + +#define SCU_CTRL 0x00 +#define SCU_ENABLE (1 << 0) +#define SCU_STANDBY_ENABLE (1 << 5) +#define SCU_CONFIG 0x04 +#define SCU_CPU_STATUS 0x08 +#define SCU_CPU_STATUS_MASK GENMASK(1, 0) +#define SCU_INVALIDATE 0x0c +#define SCU_FPGA_REVISION 0x10 + +#ifdef CONFIG_SMP +/* + * Get the number of CPU cores from the SCU configuration + */ +unsigned int __init scu_get_core_count(void __iomem *scu_base) +{ + unsigned int ncores = readl_relaxed(scu_base + SCU_CONFIG); + return (ncores & 0x03) + 1; +} + +/* + * Enable the SCU + */ +void scu_enable(void __iomem *scu_base) +{ + u32 scu_ctrl; + +#ifdef CONFIG_ARM_ERRATA_764369 + /* Cortex-A9 only */ + if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) { + scu_ctrl = readl_relaxed(scu_base + 0x30); + if (!(scu_ctrl & 1)) + writel_relaxed(scu_ctrl | 0x1, scu_base + 0x30); + } +#endif + + scu_ctrl = readl_relaxed(scu_base + SCU_CTRL); + /* already enabled? */ + if (scu_ctrl & SCU_ENABLE) + return; + + scu_ctrl |= SCU_ENABLE; + + /* Cortex-A9 earlier than r2p0 has no standby bit in SCU */ + if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090 && + (read_cpuid_id() & 0x00f0000f) >= 0x00200000) + scu_ctrl |= SCU_STANDBY_ENABLE; + + writel_relaxed(scu_ctrl, scu_base + SCU_CTRL); + + /* + * Ensure that the data accessed by CPU0 before the SCU was + * initialised is visible to the other CPUs. + */ + flush_cache_all(); +} +#endif + +static int scu_set_power_mode_internal(void __iomem *scu_base, + unsigned int logical_cpu, + unsigned int mode) +{ + unsigned int val; + int cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(logical_cpu), 0); + + if (mode > 3 || mode == 1 || cpu > 3) + return -EINVAL; + + val = readb_relaxed(scu_base + SCU_CPU_STATUS + cpu); + val &= ~SCU_CPU_STATUS_MASK; + val |= mode; + writeb_relaxed(val, scu_base + SCU_CPU_STATUS + cpu); + + return 0; +} + +/* + * Set the executing CPUs power mode as defined. This will be in + * preparation for it executing a WFI instruction. + * + * This function must be called with preemption disabled, and as it + * has the side effect of disabling coherency, caches must have been + * flushed. Interrupts must also have been disabled. + */ +int scu_power_mode(void __iomem *scu_base, unsigned int mode) +{ + return scu_set_power_mode_internal(scu_base, smp_processor_id(), mode); +} + +/* + * Set the given (logical) CPU's power mode to SCU_PM_NORMAL. + */ +int scu_cpu_power_enable(void __iomem *scu_base, unsigned int cpu) +{ + return scu_set_power_mode_internal(scu_base, cpu, SCU_PM_NORMAL); +} + +int scu_get_cpu_power_mode(void __iomem *scu_base, unsigned int logical_cpu) +{ + unsigned int val; + int cpu = MPIDR_AFFINITY_LEVEL(cpu_logical_map(logical_cpu), 0); + + if (cpu > 3) + return -EINVAL; + + val = readb_relaxed(scu_base + SCU_CPU_STATUS + cpu); + val &= SCU_CPU_STATUS_MASK; + + return val; +} diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c new file mode 100644 index 000000000..d4908b373 --- /dev/null +++ b/arch/arm/kernel/smp_tlb.c @@ -0,0 +1,253 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/smp_tlb.c + * + * Copyright (C) 2002 ARM Limited, All Rights Reserved. + */ +#include <linux/preempt.h> +#include <linux/smp.h> +#include <linux/uaccess.h> + +#include <asm/smp_plat.h> +#include <asm/tlbflush.h> +#include <asm/mmu_context.h> + +/**********************************************************************/ + +/* + * TLB operations + */ +struct tlb_args { + struct vm_area_struct *ta_vma; + unsigned long ta_start; + unsigned long ta_end; +}; + +static inline void ipi_flush_tlb_all(void *ignored) +{ + local_flush_tlb_all(); +} + +static inline void ipi_flush_tlb_mm(void *arg) +{ + struct mm_struct *mm = (struct mm_struct *)arg; + + local_flush_tlb_mm(mm); +} + +static inline void ipi_flush_tlb_page(void *arg) +{ + struct tlb_args *ta = (struct tlb_args *)arg; + unsigned int __ua_flags = uaccess_save_and_enable(); + + local_flush_tlb_page(ta->ta_vma, ta->ta_start); + + uaccess_restore(__ua_flags); +} + +static inline void ipi_flush_tlb_kernel_page(void *arg) +{ + struct tlb_args *ta = (struct tlb_args *)arg; + + local_flush_tlb_kernel_page(ta->ta_start); +} + +static inline void ipi_flush_tlb_range(void *arg) +{ + struct tlb_args *ta = (struct tlb_args *)arg; + unsigned int __ua_flags = uaccess_save_and_enable(); + + local_flush_tlb_range(ta->ta_vma, ta->ta_start, ta->ta_end); + + uaccess_restore(__ua_flags); +} + +static inline void ipi_flush_tlb_kernel_range(void *arg) +{ + struct tlb_args *ta = (struct tlb_args *)arg; + + local_flush_tlb_kernel_range(ta->ta_start, ta->ta_end); +} + +static inline void ipi_flush_bp_all(void *ignored) +{ + local_flush_bp_all(); +} + +#ifdef CONFIG_ARM_ERRATA_798181 +bool (*erratum_a15_798181_handler)(void); + +static bool erratum_a15_798181_partial(void) +{ + asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0)); + dsb(ish); + return false; +} + +static bool erratum_a15_798181_broadcast(void) +{ + asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0)); + dsb(ish); + return true; +} + +void erratum_a15_798181_init(void) +{ + unsigned int midr = read_cpuid_id(); + unsigned int revidr = read_cpuid(CPUID_REVIDR); + + /* Brahma-B15 r0p0..r0p2 affected + * Cortex-A15 r0p0..r3p3 w/o ECO fix affected + * Fixes applied to A15 with respect to the revision and revidr are: + * + * r0p0-r2p1: No fixes applied + * r2p2,r2p3: + * REVIDR[4]: 798181 Moving a virtual page that is being accessed + * by an active process can lead to unexpected behavior + * REVIDR[9]: Not defined + * r2p4,r3p0,r3p1,r3p2: + * REVIDR[4]: 798181 Moving a virtual page that is being accessed + * by an active process can lead to unexpected behavior + * REVIDR[9]: 798181 Moving a virtual page that is being accessed + * by an active process can lead to unexpected behavior + * - This is an update to a previously released ECO. + * r3p3: + * REVIDR[4]: Reserved + * REVIDR[9]: 798181 Moving a virtual page that is being accessed + * by an active process can lead to unexpected behavior + * - This is an update to a previously released ECO. + * + * Handling: + * REVIDR[9] set -> No WA + * REVIDR[4] set, REVIDR[9] cleared -> Partial WA + * Both cleared -> Full WA + */ + if ((midr & 0xff0ffff0) == 0x420f00f0 && midr <= 0x420f00f2) { + erratum_a15_798181_handler = erratum_a15_798181_broadcast; + } else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr < 0x412fc0f2) { + erratum_a15_798181_handler = erratum_a15_798181_broadcast; + } else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr < 0x412fc0f4) { + if (revidr & 0x10) + erratum_a15_798181_handler = + erratum_a15_798181_partial; + else + erratum_a15_798181_handler = + erratum_a15_798181_broadcast; + } else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr < 0x413fc0f3) { + if ((revidr & 0x210) == 0) + erratum_a15_798181_handler = + erratum_a15_798181_broadcast; + else if (revidr & 0x10) + erratum_a15_798181_handler = + erratum_a15_798181_partial; + } else if ((midr & 0xff0ffff0) == 0x410fc0f0 && midr < 0x414fc0f0) { + if ((revidr & 0x200) == 0) + erratum_a15_798181_handler = + erratum_a15_798181_partial; + } +} +#endif + +static void ipi_flush_tlb_a15_erratum(void *arg) +{ + dmb(); +} + +static void broadcast_tlb_a15_erratum(void) +{ + if (!erratum_a15_798181()) + return; + + smp_call_function(ipi_flush_tlb_a15_erratum, NULL, 1); +} + +static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm) +{ + int this_cpu; + cpumask_t mask = { CPU_BITS_NONE }; + + if (!erratum_a15_798181()) + return; + + this_cpu = get_cpu(); + a15_erratum_get_cpumask(this_cpu, mm, &mask); + smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1); + put_cpu(); +} + +void flush_tlb_all(void) +{ + if (tlb_ops_need_broadcast()) + on_each_cpu(ipi_flush_tlb_all, NULL, 1); + else + __flush_tlb_all(); + broadcast_tlb_a15_erratum(); +} + +void flush_tlb_mm(struct mm_struct *mm) +{ + if (tlb_ops_need_broadcast()) + on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1); + else + __flush_tlb_mm(mm); + broadcast_tlb_mm_a15_erratum(mm); +} + +void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr) +{ + if (tlb_ops_need_broadcast()) { + struct tlb_args ta; + ta.ta_vma = vma; + ta.ta_start = uaddr; + on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page, + &ta, 1); + } else + __flush_tlb_page(vma, uaddr); + broadcast_tlb_mm_a15_erratum(vma->vm_mm); +} + +void flush_tlb_kernel_page(unsigned long kaddr) +{ + if (tlb_ops_need_broadcast()) { + struct tlb_args ta; + ta.ta_start = kaddr; + on_each_cpu(ipi_flush_tlb_kernel_page, &ta, 1); + } else + __flush_tlb_kernel_page(kaddr); + broadcast_tlb_a15_erratum(); +} + +void flush_tlb_range(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + if (tlb_ops_need_broadcast()) { + struct tlb_args ta; + ta.ta_vma = vma; + ta.ta_start = start; + ta.ta_end = end; + on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_range, + &ta, 1); + } else + local_flush_tlb_range(vma, start, end); + broadcast_tlb_mm_a15_erratum(vma->vm_mm); +} + +void flush_tlb_kernel_range(unsigned long start, unsigned long end) +{ + if (tlb_ops_need_broadcast()) { + struct tlb_args ta; + ta.ta_start = start; + ta.ta_end = end; + on_each_cpu(ipi_flush_tlb_kernel_range, &ta, 1); + } else + local_flush_tlb_kernel_range(start, end); + broadcast_tlb_a15_erratum(); +} + +void flush_bp_all(void) +{ + if (tlb_ops_need_broadcast()) + on_each_cpu(ipi_flush_bp_all, NULL, 1); + else + __flush_bp_all(); +} diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c new file mode 100644 index 000000000..9a14f721a --- /dev/null +++ b/arch/arm/kernel/smp_twd.c @@ -0,0 +1,340 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/smp_twd.c + * + * Copyright (C) 2002 ARM Ltd. + * All Rights Reserved + */ +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/clk.h> +#include <linux/cpu.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/smp.h> +#include <linux/jiffies.h> +#include <linux/clockchips.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/of_irq.h> +#include <linux/of_address.h> + +#include <asm/smp_twd.h> + +/* set up by the platform code */ +static void __iomem *twd_base; + +static struct clk *twd_clk; +static unsigned long twd_timer_rate; +static DEFINE_PER_CPU(bool, percpu_setup_called); + +static struct clock_event_device __percpu *twd_evt; +static unsigned int twd_features = + CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT; +static int twd_ppi; + +static int twd_shutdown(struct clock_event_device *clk) +{ + writel_relaxed(0, twd_base + TWD_TIMER_CONTROL); + return 0; +} + +static int twd_set_oneshot(struct clock_event_device *clk) +{ + /* period set, and timer enabled in 'next_event' hook */ + writel_relaxed(TWD_TIMER_CONTROL_IT_ENABLE | TWD_TIMER_CONTROL_ONESHOT, + twd_base + TWD_TIMER_CONTROL); + return 0; +} + +static int twd_set_periodic(struct clock_event_device *clk) +{ + unsigned long ctrl = TWD_TIMER_CONTROL_ENABLE | + TWD_TIMER_CONTROL_IT_ENABLE | + TWD_TIMER_CONTROL_PERIODIC; + + writel_relaxed(DIV_ROUND_CLOSEST(twd_timer_rate, HZ), + twd_base + TWD_TIMER_LOAD); + writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL); + return 0; +} + +static int twd_set_next_event(unsigned long evt, + struct clock_event_device *unused) +{ + unsigned long ctrl = readl_relaxed(twd_base + TWD_TIMER_CONTROL); + + ctrl |= TWD_TIMER_CONTROL_ENABLE; + + writel_relaxed(evt, twd_base + TWD_TIMER_COUNTER); + writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL); + + return 0; +} + +/* + * local_timer_ack: checks for a local timer interrupt. + * + * If a local timer interrupt has occurred, acknowledge and return 1. + * Otherwise, return 0. + */ +static int twd_timer_ack(void) +{ + if (readl_relaxed(twd_base + TWD_TIMER_INTSTAT)) { + writel_relaxed(1, twd_base + TWD_TIMER_INTSTAT); + return 1; + } + + return 0; +} + +static void twd_timer_stop(void) +{ + struct clock_event_device *clk = raw_cpu_ptr(twd_evt); + + twd_shutdown(clk); + disable_percpu_irq(clk->irq); +} + +/* + * Updates clockevent frequency when the cpu frequency changes. + * Called on the cpu that is changing frequency with interrupts disabled. + */ +static void twd_update_frequency(void *new_rate) +{ + twd_timer_rate = *((unsigned long *) new_rate); + + clockevents_update_freq(raw_cpu_ptr(twd_evt), twd_timer_rate); +} + +static int twd_rate_change(struct notifier_block *nb, + unsigned long flags, void *data) +{ + struct clk_notifier_data *cnd = data; + + /* + * The twd clock events must be reprogrammed to account for the new + * frequency. The timer is local to a cpu, so cross-call to the + * changing cpu. + */ + if (flags == POST_RATE_CHANGE) + on_each_cpu(twd_update_frequency, + (void *)&cnd->new_rate, 1); + + return NOTIFY_OK; +} + +static struct notifier_block twd_clk_nb = { + .notifier_call = twd_rate_change, +}; + +static int twd_clk_init(void) +{ + if (twd_evt && raw_cpu_ptr(twd_evt) && !IS_ERR(twd_clk)) + return clk_notifier_register(twd_clk, &twd_clk_nb); + + return 0; +} +core_initcall(twd_clk_init); + +static void twd_calibrate_rate(void) +{ + unsigned long count; + u64 waitjiffies; + + /* + * If this is the first time round, we need to work out how fast + * the timer ticks + */ + if (twd_timer_rate == 0) { + pr_info("Calibrating local timer... "); + + /* Wait for a tick to start */ + waitjiffies = get_jiffies_64() + 1; + + while (get_jiffies_64() < waitjiffies) + udelay(10); + + /* OK, now the tick has started, let's get the timer going */ + waitjiffies += 5; + + /* enable, no interrupt or reload */ + writel_relaxed(0x1, twd_base + TWD_TIMER_CONTROL); + + /* maximum value */ + writel_relaxed(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER); + + while (get_jiffies_64() < waitjiffies) + udelay(10); + + count = readl_relaxed(twd_base + TWD_TIMER_COUNTER); + + twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5); + + pr_cont("%lu.%02luMHz.\n", twd_timer_rate / 1000000, + (twd_timer_rate / 10000) % 100); + } +} + +static irqreturn_t twd_handler(int irq, void *dev_id) +{ + struct clock_event_device *evt = dev_id; + + if (twd_timer_ack()) { + evt->event_handler(evt); + return IRQ_HANDLED; + } + + return IRQ_NONE; +} + +static void twd_get_clock(struct device_node *np) +{ + int err; + + if (np) + twd_clk = of_clk_get(np, 0); + else + twd_clk = clk_get_sys("smp_twd", NULL); + + if (IS_ERR(twd_clk)) { + pr_err("smp_twd: clock not found %d\n", (int) PTR_ERR(twd_clk)); + return; + } + + err = clk_prepare_enable(twd_clk); + if (err) { + pr_err("smp_twd: clock failed to prepare+enable: %d\n", err); + clk_put(twd_clk); + return; + } + + twd_timer_rate = clk_get_rate(twd_clk); +} + +/* + * Setup the local clock events for a CPU. + */ +static void twd_timer_setup(void) +{ + struct clock_event_device *clk = raw_cpu_ptr(twd_evt); + int cpu = smp_processor_id(); + + /* + * If the basic setup for this CPU has been done before don't + * bother with the below. + */ + if (per_cpu(percpu_setup_called, cpu)) { + writel_relaxed(0, twd_base + TWD_TIMER_CONTROL); + clockevents_register_device(clk); + enable_percpu_irq(clk->irq, 0); + return; + } + per_cpu(percpu_setup_called, cpu) = true; + + twd_calibrate_rate(); + + /* + * The following is done once per CPU the first time .setup() is + * called. + */ + writel_relaxed(0, twd_base + TWD_TIMER_CONTROL); + + clk->name = "local_timer"; + clk->features = twd_features; + clk->rating = 350; + clk->set_state_shutdown = twd_shutdown; + clk->set_state_periodic = twd_set_periodic; + clk->set_state_oneshot = twd_set_oneshot; + clk->tick_resume = twd_shutdown; + clk->set_next_event = twd_set_next_event; + clk->irq = twd_ppi; + clk->cpumask = cpumask_of(cpu); + + clockevents_config_and_register(clk, twd_timer_rate, + 0xf, 0xffffffff); + enable_percpu_irq(clk->irq, 0); +} + +static int twd_timer_starting_cpu(unsigned int cpu) +{ + twd_timer_setup(); + return 0; +} + +static int twd_timer_dying_cpu(unsigned int cpu) +{ + twd_timer_stop(); + return 0; +} + +static int __init twd_local_timer_common_register(struct device_node *np) +{ + int err; + + twd_evt = alloc_percpu(struct clock_event_device); + if (!twd_evt) { + err = -ENOMEM; + goto out_free; + } + + err = request_percpu_irq(twd_ppi, twd_handler, "twd", twd_evt); + if (err) { + pr_err("twd: can't register interrupt %d (%d)\n", twd_ppi, err); + goto out_free; + } + + cpuhp_setup_state_nocalls(CPUHP_AP_ARM_TWD_STARTING, + "arm/timer/twd:starting", + twd_timer_starting_cpu, twd_timer_dying_cpu); + + twd_get_clock(np); + if (!of_property_read_bool(np, "always-on")) + twd_features |= CLOCK_EVT_FEAT_C3STOP; + + /* + * Immediately configure the timer on the boot CPU, unless we need + * jiffies to be incrementing to calibrate the rate in which case + * setup the timer in late_time_init. + */ + if (twd_timer_rate) + twd_timer_setup(); + else + late_time_init = twd_timer_setup; + + return 0; + +out_free: + iounmap(twd_base); + twd_base = NULL; + free_percpu(twd_evt); + + return err; +} + +static int __init twd_local_timer_of_register(struct device_node *np) +{ + int err; + + twd_ppi = irq_of_parse_and_map(np, 0); + if (!twd_ppi) { + err = -EINVAL; + goto out; + } + + twd_base = of_iomap(np, 0); + if (!twd_base) { + err = -ENOMEM; + goto out; + } + + err = twd_local_timer_common_register(np); + +out: + WARN(err, "twd_local_timer_of_register failed (%d)\n", err); + return err; +} +TIMER_OF_DECLARE(arm_twd_a9, "arm,cortex-a9-twd-timer", twd_local_timer_of_register); +TIMER_OF_DECLARE(arm_twd_a5, "arm,cortex-a5-twd-timer", twd_local_timer_of_register); +TIMER_OF_DECLARE(arm_twd_11mp, "arm,arm11mp-twd-timer", twd_local_timer_of_register); diff --git a/arch/arm/kernel/spectre.c b/arch/arm/kernel/spectre.c new file mode 100644 index 000000000..0dcefc36f --- /dev/null +++ b/arch/arm/kernel/spectre.c @@ -0,0 +1,71 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/bpf.h> +#include <linux/cpu.h> +#include <linux/device.h> + +#include <asm/spectre.h> + +static bool _unprivileged_ebpf_enabled(void) +{ +#ifdef CONFIG_BPF_SYSCALL + return !sysctl_unprivileged_bpf_disabled; +#else + return false; +#endif +} + +ssize_t cpu_show_spectre_v1(struct device *dev, struct device_attribute *attr, + char *buf) +{ + return sprintf(buf, "Mitigation: __user pointer sanitization\n"); +} + +static unsigned int spectre_v2_state; +static unsigned int spectre_v2_methods; + +void spectre_v2_update_state(unsigned int state, unsigned int method) +{ + if (state > spectre_v2_state) + spectre_v2_state = state; + spectre_v2_methods |= method; +} + +ssize_t cpu_show_spectre_v2(struct device *dev, struct device_attribute *attr, + char *buf) +{ + const char *method; + + if (spectre_v2_state == SPECTRE_UNAFFECTED) + return sprintf(buf, "%s\n", "Not affected"); + + if (spectre_v2_state != SPECTRE_MITIGATED) + return sprintf(buf, "%s\n", "Vulnerable"); + + if (_unprivileged_ebpf_enabled()) + return sprintf(buf, "Vulnerable: Unprivileged eBPF enabled\n"); + + switch (spectre_v2_methods) { + case SPECTRE_V2_METHOD_BPIALL: + method = "Branch predictor hardening"; + break; + + case SPECTRE_V2_METHOD_ICIALLU: + method = "I-cache invalidation"; + break; + + case SPECTRE_V2_METHOD_SMC: + case SPECTRE_V2_METHOD_HVC: + method = "Firmware call"; + break; + + case SPECTRE_V2_METHOD_LOOP8: + method = "History overwrite"; + break; + + default: + method = "Multiple mitigations"; + break; + } + + return sprintf(buf, "Mitigation: %s\n", method); +} diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c new file mode 100644 index 000000000..85443b5d1 --- /dev/null +++ b/arch/arm/kernel/stacktrace.c @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include <linux/export.h> +#include <linux/kprobes.h> +#include <linux/sched.h> +#include <linux/sched/debug.h> +#include <linux/stacktrace.h> + +#include <asm/sections.h> +#include <asm/stacktrace.h> +#include <asm/traps.h> + +#include "reboot.h" + +#if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) +/* + * Unwind the current stack frame and store the new register values in the + * structure passed as argument. Unwinding is equivalent to a function return, + * hence the new PC value rather than LR should be used for backtrace. + * + * With framepointer enabled, a simple function prologue looks like this: + * mov ip, sp + * stmdb sp!, {fp, ip, lr, pc} + * sub fp, ip, #4 + * + * A simple function epilogue looks like this: + * ldm sp, {fp, sp, pc} + * + * When compiled with clang, pc and sp are not pushed. A simple function + * prologue looks like this when built with clang: + * + * stmdb {..., fp, lr} + * add fp, sp, #x + * sub sp, sp, #y + * + * A simple function epilogue looks like this when built with clang: + * + * sub sp, fp, #x + * ldm {..., fp, pc} + * + * + * Note that with framepointer enabled, even the leaf functions have the same + * prologue and epilogue, therefore we can ignore the LR value in this case. + */ + +extern unsigned long call_with_stack_end; + +static int frame_pointer_check(struct stackframe *frame) +{ + unsigned long high, low; + unsigned long fp = frame->fp; + unsigned long pc = frame->pc; + + /* + * call_with_stack() is the only place we allow SP to jump from one + * stack to another, with FP and SP pointing to different stacks, + * skipping the FP boundary check at this point. + */ + if (pc >= (unsigned long)&call_with_stack && + pc < (unsigned long)&call_with_stack_end) + return 0; + + /* only go to a higher address on the stack */ + low = frame->sp; + high = ALIGN(low, THREAD_SIZE); + + /* check current frame pointer is within bounds */ +#ifdef CONFIG_CC_IS_CLANG + if (fp < low + 4 || fp > high - 4) + return -EINVAL; +#else + if (fp < low + 12 || fp > high - 4) + return -EINVAL; +#endif + + return 0; +} + +int notrace unwind_frame(struct stackframe *frame) +{ + unsigned long fp = frame->fp; + + if (frame_pointer_check(frame)) + return -EINVAL; + + /* + * When we unwind through an exception stack, include the saved PC + * value into the stack trace. + */ + if (frame->ex_frame) { + struct pt_regs *regs = (struct pt_regs *)frame->sp; + + /* + * We check that 'regs + sizeof(struct pt_regs)' (that is, + * ®s[1]) does not exceed the bottom of the stack to avoid + * accessing data outside the task's stack. This may happen + * when frame->ex_frame is a false positive. + */ + if ((unsigned long)®s[1] > ALIGN(frame->sp, THREAD_SIZE)) + return -EINVAL; + + frame->pc = regs->ARM_pc; + frame->ex_frame = false; + return 0; + } + + /* restore the registers from the stack frame */ +#ifdef CONFIG_CC_IS_CLANG + frame->sp = frame->fp; + frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp)); + frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 4)); +#else + frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp - 12)); + frame->sp = READ_ONCE_NOCHECK(*(unsigned long *)(fp - 8)); + frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp - 4)); +#endif +#ifdef CONFIG_KRETPROBES + if (is_kretprobe_trampoline(frame->pc)) + frame->pc = kretprobe_find_ret_addr(frame->tsk, + (void *)frame->fp, &frame->kr_cur); +#endif + + if (in_entry_text(frame->pc)) + frame->ex_frame = true; + + return 0; +} +#endif + +void notrace walk_stackframe(struct stackframe *frame, + int (*fn)(struct stackframe *, void *), void *data) +{ + while (1) { + int ret; + + if (fn(frame, data)) + break; + ret = unwind_frame(frame); + if (ret < 0) + break; + } +} +EXPORT_SYMBOL(walk_stackframe); + +#ifdef CONFIG_STACKTRACE +struct stack_trace_data { + struct stack_trace *trace; + unsigned int no_sched_functions; + unsigned int skip; +}; + +static int save_trace(struct stackframe *frame, void *d) +{ + struct stack_trace_data *data = d; + struct stack_trace *trace = data->trace; + unsigned long addr = frame->pc; + + if (data->no_sched_functions && in_sched_functions(addr)) + return 0; + if (data->skip) { + data->skip--; + return 0; + } + + trace->entries[trace->nr_entries++] = addr; + return trace->nr_entries >= trace->max_entries; +} + +/* This must be noinline to so that our skip calculation works correctly */ +static noinline void __save_stack_trace(struct task_struct *tsk, + struct stack_trace *trace, unsigned int nosched) +{ + struct stack_trace_data data; + struct stackframe frame; + + data.trace = trace; + data.skip = trace->skip; + data.no_sched_functions = nosched; + + if (tsk != current) { +#ifdef CONFIG_SMP + /* + * What guarantees do we have here that 'tsk' is not + * running on another CPU? For now, ignore it as we + * can't guarantee we won't explode. + */ + return; +#else + frame.fp = thread_saved_fp(tsk); + frame.sp = thread_saved_sp(tsk); + frame.lr = 0; /* recovered from the stack */ + frame.pc = thread_saved_pc(tsk); +#endif + } else { + /* We don't want this function nor the caller */ + data.skip += 2; + frame.fp = (unsigned long)__builtin_frame_address(0); + frame.sp = current_stack_pointer; + frame.lr = (unsigned long)__builtin_return_address(0); +here: + frame.pc = (unsigned long)&&here; + } +#ifdef CONFIG_KRETPROBES + frame.kr_cur = NULL; + frame.tsk = tsk; +#endif +#ifdef CONFIG_UNWINDER_FRAME_POINTER + frame.ex_frame = false; +#endif + + walk_stackframe(&frame, save_trace, &data); +} + +void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace) +{ + struct stack_trace_data data; + struct stackframe frame; + + data.trace = trace; + data.skip = trace->skip; + data.no_sched_functions = 0; + + frame.fp = regs->ARM_fp; + frame.sp = regs->ARM_sp; + frame.lr = regs->ARM_lr; + frame.pc = regs->ARM_pc; +#ifdef CONFIG_KRETPROBES + frame.kr_cur = NULL; + frame.tsk = current; +#endif +#ifdef CONFIG_UNWINDER_FRAME_POINTER + frame.ex_frame = in_entry_text(frame.pc); +#endif + + walk_stackframe(&frame, save_trace, &data); +} + +void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace) +{ + __save_stack_trace(tsk, trace, 1); +} +EXPORT_SYMBOL(save_stack_trace_tsk); + +void save_stack_trace(struct stack_trace *trace) +{ + __save_stack_trace(current, trace, 0); +} +EXPORT_SYMBOL_GPL(save_stack_trace); +#endif diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c new file mode 100644 index 000000000..43f0a3ebf --- /dev/null +++ b/arch/arm/kernel/suspend.c @@ -0,0 +1,122 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/ftrace.h> +#include <linux/init.h> +#include <linux/slab.h> +#include <linux/mm_types.h> +#include <linux/pgtable.h> + +#include <asm/bugs.h> +#include <asm/cacheflush.h> +#include <asm/idmap.h> +#include <asm/memory.h> +#include <asm/smp_plat.h> +#include <asm/suspend.h> +#include <asm/tlbflush.h> + +extern int __cpu_suspend(unsigned long, int (*)(unsigned long), u32 cpuid); +extern void cpu_resume_mmu(void); + +#ifdef CONFIG_MMU +int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) +{ + struct mm_struct *mm = current->active_mm; + u32 __mpidr = cpu_logical_map(smp_processor_id()); + int ret; + + if (!idmap_pgd) + return -EINVAL; + + /* + * Function graph tracer state gets incosistent when the kernel + * calls functions that never return (aka suspend finishers) hence + * disable graph tracing during their execution. + */ + pause_graph_tracing(); + + /* + * Provide a temporary page table with an identity mapping for + * the MMU-enable code, required for resuming. On successful + * resume (indicated by a zero return code), we need to switch + * back to the correct page tables. + */ + ret = __cpu_suspend(arg, fn, __mpidr); + + unpause_graph_tracing(); + + if (ret == 0) { + cpu_switch_mm(mm->pgd, mm); + local_flush_bp_all(); + local_flush_tlb_all(); + check_other_bugs(); + } + + return ret; +} +#else +int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) +{ + u32 __mpidr = cpu_logical_map(smp_processor_id()); + int ret; + + pause_graph_tracing(); + ret = __cpu_suspend(arg, fn, __mpidr); + unpause_graph_tracing(); + + return ret; +} +#define idmap_pgd NULL +#endif + +/* + * This is called by __cpu_suspend() to save the state, and do whatever + * flushing is required to ensure that when the CPU goes to sleep we have + * the necessary data available when the caches are not searched. + */ +void __cpu_suspend_save(u32 *ptr, u32 ptrsz, u32 sp, u32 *save_ptr) +{ + u32 *ctx = ptr; + + *save_ptr = virt_to_phys(ptr); + + /* This must correspond to the LDM in cpu_resume() assembly */ + *ptr++ = virt_to_phys(idmap_pgd); + *ptr++ = sp; + *ptr++ = virt_to_phys(cpu_do_resume); + + cpu_do_suspend(ptr); + + flush_cache_louis(); + + /* + * flush_cache_louis does not guarantee that + * save_ptr and ptr are cleaned to main memory, + * just up to the Level of Unification Inner Shareable. + * Since the context pointer and context itself + * are to be retrieved with the MMU off that + * data must be cleaned from all cache levels + * to main memory using "area" cache primitives. + */ + __cpuc_flush_dcache_area(ctx, ptrsz); + __cpuc_flush_dcache_area(save_ptr, sizeof(*save_ptr)); + + outer_clean_range(*save_ptr, *save_ptr + ptrsz); + outer_clean_range(virt_to_phys(save_ptr), + virt_to_phys(save_ptr) + sizeof(*save_ptr)); +} + +extern struct sleep_save_sp sleep_save_sp; + +static int cpu_suspend_alloc_sp(void) +{ + void *ctx_ptr; + /* ctx_ptr is an array of physical addresses */ + ctx_ptr = kcalloc(mpidr_hash_size(), sizeof(u32), GFP_KERNEL); + + if (WARN_ON(!ctx_ptr)) + return -ENOMEM; + sleep_save_sp.save_ptr_stash = ctx_ptr; + sleep_save_sp.save_ptr_stash_phys = virt_to_phys(ctx_ptr); + sync_cache_w(&sleep_save_sp); + return 0; +} +early_initcall(cpu_suspend_alloc_sp); diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c new file mode 100644 index 000000000..b74bfcf94 --- /dev/null +++ b/arch/arm/kernel/swp_emulate.c @@ -0,0 +1,258 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/swp_emulate.c + * + * Copyright (C) 2009 ARM Limited + * __user_* functions adapted from include/asm/uaccess.h + * + * Implements emulation of the SWP/SWPB instructions using load-exclusive and + * store-exclusive for processors that have them disabled (or future ones that + * might not implement them). + * + * Syntax of SWP{B} instruction: SWP{B}<c> <Rt>, <Rt2>, [<Rn>] + * Where: Rt = destination + * Rt2 = source + * Rn = address + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/sched.h> +#include <linux/sched/mm.h> +#include <linux/syscalls.h> +#include <linux/perf_event.h> + +#include <asm/opcodes.h> +#include <asm/system_info.h> +#include <asm/traps.h> +#include <linux/uaccess.h> + +/* + * Error-checking SWP macros implemented using ldrex{b}/strex{b} + */ +#define __user_swpX_asm(data, addr, res, temp, B) \ + __asm__ __volatile__( \ + "0: ldrex"B" %2, [%3]\n" \ + "1: strex"B" %0, %1, [%3]\n" \ + " cmp %0, #0\n" \ + " moveq %1, %2\n" \ + " movne %0, %4\n" \ + "2:\n" \ + " .section .text.fixup,\"ax\"\n" \ + " .align 2\n" \ + "3: mov %0, %5\n" \ + " b 2b\n" \ + " .previous\n" \ + " .section __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 0b, 3b\n" \ + " .long 1b, 3b\n" \ + " .previous" \ + : "=&r" (res), "+r" (data), "=&r" (temp) \ + : "r" (addr), "i" (-EAGAIN), "i" (-EFAULT) \ + : "cc", "memory") + +#define __user_swp_asm(data, addr, res, temp) \ + __user_swpX_asm(data, addr, res, temp, "") +#define __user_swpb_asm(data, addr, res, temp) \ + __user_swpX_asm(data, addr, res, temp, "b") + +/* + * Macros/defines for extracting register numbers from instruction. + */ +#define EXTRACT_REG_NUM(instruction, offset) \ + (((instruction) & (0xf << (offset))) >> (offset)) +#define RN_OFFSET 16 +#define RT_OFFSET 12 +#define RT2_OFFSET 0 +/* + * Bit 22 of the instruction encoding distinguishes between + * the SWP and SWPB variants (bit set means SWPB). + */ +#define TYPE_SWPB (1 << 22) + +static unsigned long swpcounter; +static unsigned long swpbcounter; +static unsigned long abtcounter; +static pid_t previous_pid; + +#ifdef CONFIG_PROC_FS +static int proc_status_show(struct seq_file *m, void *v) +{ + seq_printf(m, "Emulated SWP:\t\t%lu\n", swpcounter); + seq_printf(m, "Emulated SWPB:\t\t%lu\n", swpbcounter); + seq_printf(m, "Aborted SWP{B}:\t\t%lu\n", abtcounter); + if (previous_pid != 0) + seq_printf(m, "Last process:\t\t%d\n", previous_pid); + return 0; +} +#endif + +/* + * Set up process info to signal segmentation fault - called on access error. + */ +static void set_segfault(struct pt_regs *regs, unsigned long addr) +{ + int si_code; + + mmap_read_lock(current->mm); + if (find_vma(current->mm, addr) == NULL) + si_code = SEGV_MAPERR; + else + si_code = SEGV_ACCERR; + mmap_read_unlock(current->mm); + + pr_debug("SWP{B} emulation: access caused memory abort!\n"); + arm_notify_die("Illegal memory access", regs, + SIGSEGV, si_code, + (void __user *)instruction_pointer(regs), + 0, 0); + + abtcounter++; +} + +static int emulate_swpX(unsigned int address, unsigned int *data, + unsigned int type) +{ + unsigned int res = 0; + + if ((type != TYPE_SWPB) && (address & 0x3)) { + /* SWP to unaligned address not permitted */ + pr_debug("SWP instruction on unaligned pointer!\n"); + return -EFAULT; + } + + while (1) { + unsigned long temp; + unsigned int __ua_flags; + + __ua_flags = uaccess_save_and_enable(); + if (type == TYPE_SWPB) + __user_swpb_asm(*data, address, res, temp); + else + __user_swp_asm(*data, address, res, temp); + uaccess_restore(__ua_flags); + + if (likely(res != -EAGAIN) || signal_pending(current)) + break; + + cond_resched(); + } + + if (res == 0) { + if (type == TYPE_SWPB) + swpbcounter++; + else + swpcounter++; + } + + return res; +} + +/* + * swp_handler logs the id of calling process, dissects the instruction, sanity + * checks the memory location, calls emulate_swpX for the actual operation and + * deals with fixup/error handling before returning + */ +static int swp_handler(struct pt_regs *regs, unsigned int instr) +{ + unsigned int address, destreg, data, type; + unsigned int res = 0; + + perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->ARM_pc); + + res = arm_check_condition(instr, regs->ARM_cpsr); + switch (res) { + case ARM_OPCODE_CONDTEST_PASS: + break; + case ARM_OPCODE_CONDTEST_FAIL: + /* Condition failed - return to next instruction */ + regs->ARM_pc += 4; + return 0; + case ARM_OPCODE_CONDTEST_UNCOND: + /* If unconditional encoding - not a SWP, undef */ + return -EFAULT; + default: + return -EINVAL; + } + + if (current->pid != previous_pid) { + pr_debug("\"%s\" (%ld) uses deprecated SWP{B} instruction\n", + current->comm, (unsigned long)current->pid); + previous_pid = current->pid; + } + + address = regs->uregs[EXTRACT_REG_NUM(instr, RN_OFFSET)]; + data = regs->uregs[EXTRACT_REG_NUM(instr, RT2_OFFSET)]; + destreg = EXTRACT_REG_NUM(instr, RT_OFFSET); + + type = instr & TYPE_SWPB; + + pr_debug("addr in r%d->0x%08x, dest is r%d, source in r%d->0x%08x)\n", + EXTRACT_REG_NUM(instr, RN_OFFSET), address, + destreg, EXTRACT_REG_NUM(instr, RT2_OFFSET), data); + + /* Check access in reasonable access range for both SWP and SWPB */ + if (!access_ok((void __user *)(address & ~3), 4)) { + pr_debug("SWP{B} emulation: access to %p not allowed!\n", + (void *)address); + res = -EFAULT; + } else { + res = emulate_swpX(address, &data, type); + } + + if (res == 0) { + /* + * On successful emulation, revert the adjustment to the PC + * made in kernel/traps.c in order to resume execution at the + * instruction following the SWP{B}. + */ + regs->ARM_pc += 4; + regs->uregs[destreg] = data; + } else if (res == -EFAULT) { + /* + * Memory errors do not mean emulation failed. + * Set up signal info to return SEGV, then return OK + */ + set_segfault(regs, address); + } + + return 0; +} + +/* + * Only emulate SWP/SWPB executed in ARM state/User mode. + * The kernel must be SWP free and SWP{B} does not exist in Thumb/ThumbEE. + */ +static struct undef_hook swp_hook = { + .instr_mask = 0x0fb00ff0, + .instr_val = 0x01000090, + .cpsr_mask = MODE_MASK | PSR_T_BIT | PSR_J_BIT, + .cpsr_val = USR_MODE, + .fn = swp_handler +}; + +/* + * Register handler and create status file in /proc/cpu + * Invoked as late_initcall, since not needed before init spawned. + */ +static int __init swp_emulation_init(void) +{ + if (cpu_architecture() < CPU_ARCH_ARMv7) + return 0; + +#ifdef CONFIG_PROC_FS + if (!proc_create_single("cpu/swp_emulation", S_IRUGO, NULL, + proc_status_show)) + return -ENOMEM; +#endif /* CONFIG_PROC_FS */ + + pr_notice("Registering SWP/SWPB emulation handler\n"); + register_undef_hook(&swp_hook); + + return 0; +} + +late_initcall(swp_emulation_init); diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c new file mode 100644 index 000000000..a5f183cfe --- /dev/null +++ b/arch/arm/kernel/sys_arm.c @@ -0,0 +1,36 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/sys_arm.c + * + * Copyright (C) People who wrote linux/arch/i386/kernel/sys_i386.c + * Copyright (C) 1995, 1996 Russell King. + * + * This file contains various random system calls that + * have a non-standard calling sequence on the Linux/arm + * platform. + */ +#include <linux/export.h> +#include <linux/errno.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/sem.h> +#include <linux/msg.h> +#include <linux/shm.h> +#include <linux/stat.h> +#include <linux/syscalls.h> +#include <linux/mman.h> +#include <linux/fs.h> +#include <linux/file.h> +#include <linux/ipc.h> +#include <linux/uaccess.h> +#include <linux/slab.h> + +/* + * Since loff_t is a 64 bit type we avoid a lot of ABI hassle + * with a different argument ordering. + */ +asmlinkage long sys_arm_fadvise64_64(int fd, int advice, + loff_t offset, loff_t len) +{ + return ksys_fadvise64_64(fd, offset, len, advice); +} diff --git a/arch/arm/kernel/sys_oabi-compat.c b/arch/arm/kernel/sys_oabi-compat.c new file mode 100644 index 000000000..68112c172 --- /dev/null +++ b/arch/arm/kernel/sys_oabi-compat.c @@ -0,0 +1,513 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * arch/arm/kernel/sys_oabi-compat.c + * + * Compatibility wrappers for syscalls that are used from + * old ABI user space binaries with an EABI kernel. + * + * Author: Nicolas Pitre + * Created: Oct 7, 2005 + * Copyright: MontaVista Software, Inc. + */ + +/* + * The legacy ABI and the new ARM EABI have different rules making some + * syscalls incompatible especially with structure arguments. + * Most notably, Eabi says 64-bit members should be 64-bit aligned instead of + * simply word aligned. EABI also pads structures to the size of the largest + * member it contains instead of the invariant 32-bit. + * + * The following syscalls are affected: + * + * sys_stat64: + * sys_lstat64: + * sys_fstat64: + * sys_fstatat64: + * + * struct stat64 has different sizes and some members are shifted + * Compatibility wrappers are needed for them and provided below. + * + * sys_fcntl64: + * + * struct flock64 has different sizes and some members are shifted + * A compatibility wrapper is needed and provided below. + * + * sys_statfs64: + * sys_fstatfs64: + * + * struct statfs64 has extra padding with EABI growing its size from + * 84 to 88. This struct is now __attribute__((packed,aligned(4))) + * with a small assembly wrapper to force the sz argument to 84 if it is 88 + * to avoid copying the extra padding over user space unexpecting it. + * + * sys_newuname: + * + * struct new_utsname has no padding with EABI. No problem there. + * + * sys_epoll_ctl: + * sys_epoll_wait: + * + * struct epoll_event has its second member shifted also affecting the + * structure size. Compatibility wrappers are needed and provided below. + * + * sys_ipc: + * sys_semop: + * sys_semtimedop: + * + * struct sembuf loses its padding with EABI. Since arrays of them are + * used they have to be copyed to remove the padding. Compatibility wrappers + * provided below. + * + * sys_bind: + * sys_connect: + * sys_sendmsg: + * sys_sendto: + * sys_socketcall: + * + * struct sockaddr_un loses its padding with EABI. Since the size of the + * structure is used as a validation test in unix_mkname(), we need to + * change the length argument to 110 whenever it is 112. Compatibility + * wrappers provided below. + */ + +#include <linux/syscalls.h> +#include <linux/errno.h> +#include <linux/fs.h> +#include <linux/cred.h> +#include <linux/fcntl.h> +#include <linux/eventpoll.h> +#include <linux/sem.h> +#include <linux/socket.h> +#include <linux/net.h> +#include <linux/ipc.h> +#include <linux/ipc_namespace.h> +#include <linux/uaccess.h> +#include <linux/slab.h> + +#include <asm/syscall.h> + +struct oldabi_stat64 { + unsigned long long st_dev; + unsigned int __pad1; + unsigned long __st_ino; + unsigned int st_mode; + unsigned int st_nlink; + + unsigned long st_uid; + unsigned long st_gid; + + unsigned long long st_rdev; + unsigned int __pad2; + + long long st_size; + unsigned long st_blksize; + unsigned long long st_blocks; + + unsigned long st_atime; + unsigned long st_atime_nsec; + + unsigned long st_mtime; + unsigned long st_mtime_nsec; + + unsigned long st_ctime; + unsigned long st_ctime_nsec; + + unsigned long long st_ino; +} __attribute__ ((packed,aligned(4))); + +static long cp_oldabi_stat64(struct kstat *stat, + struct oldabi_stat64 __user *statbuf) +{ + struct oldabi_stat64 tmp; + + tmp.st_dev = huge_encode_dev(stat->dev); + tmp.__pad1 = 0; + tmp.__st_ino = stat->ino; + tmp.st_mode = stat->mode; + tmp.st_nlink = stat->nlink; + tmp.st_uid = from_kuid_munged(current_user_ns(), stat->uid); + tmp.st_gid = from_kgid_munged(current_user_ns(), stat->gid); + tmp.st_rdev = huge_encode_dev(stat->rdev); + tmp.st_size = stat->size; + tmp.st_blocks = stat->blocks; + tmp.__pad2 = 0; + tmp.st_blksize = stat->blksize; + tmp.st_atime = stat->atime.tv_sec; + tmp.st_atime_nsec = stat->atime.tv_nsec; + tmp.st_mtime = stat->mtime.tv_sec; + tmp.st_mtime_nsec = stat->mtime.tv_nsec; + tmp.st_ctime = stat->ctime.tv_sec; + tmp.st_ctime_nsec = stat->ctime.tv_nsec; + tmp.st_ino = stat->ino; + return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0; +} + +asmlinkage long sys_oabi_stat64(const char __user * filename, + struct oldabi_stat64 __user * statbuf) +{ + struct kstat stat; + int error = vfs_stat(filename, &stat); + if (!error) + error = cp_oldabi_stat64(&stat, statbuf); + return error; +} + +asmlinkage long sys_oabi_lstat64(const char __user * filename, + struct oldabi_stat64 __user * statbuf) +{ + struct kstat stat; + int error = vfs_lstat(filename, &stat); + if (!error) + error = cp_oldabi_stat64(&stat, statbuf); + return error; +} + +asmlinkage long sys_oabi_fstat64(unsigned long fd, + struct oldabi_stat64 __user * statbuf) +{ + struct kstat stat; + int error = vfs_fstat(fd, &stat); + if (!error) + error = cp_oldabi_stat64(&stat, statbuf); + return error; +} + +asmlinkage long sys_oabi_fstatat64(int dfd, + const char __user *filename, + struct oldabi_stat64 __user *statbuf, + int flag) +{ + struct kstat stat; + int error; + + error = vfs_fstatat(dfd, filename, &stat, flag); + if (error) + return error; + return cp_oldabi_stat64(&stat, statbuf); +} + +struct oabi_flock64 { + short l_type; + short l_whence; + loff_t l_start; + loff_t l_len; + pid_t l_pid; +} __attribute__ ((packed,aligned(4))); + +static int get_oabi_flock(struct flock64 *kernel, struct oabi_flock64 __user *arg) +{ + struct oabi_flock64 user; + + if (copy_from_user(&user, (struct oabi_flock64 __user *)arg, + sizeof(user))) + return -EFAULT; + + kernel->l_type = user.l_type; + kernel->l_whence = user.l_whence; + kernel->l_start = user.l_start; + kernel->l_len = user.l_len; + kernel->l_pid = user.l_pid; + + return 0; +} + +static int put_oabi_flock(struct flock64 *kernel, struct oabi_flock64 __user *arg) +{ + struct oabi_flock64 user; + + user.l_type = kernel->l_type; + user.l_whence = kernel->l_whence; + user.l_start = kernel->l_start; + user.l_len = kernel->l_len; + user.l_pid = kernel->l_pid; + + if (copy_to_user((struct oabi_flock64 __user *)arg, + &user, sizeof(user))) + return -EFAULT; + + return 0; +} + +asmlinkage long sys_oabi_fcntl64(unsigned int fd, unsigned int cmd, + unsigned long arg) +{ + void __user *argp = (void __user *)arg; + struct fd f = fdget_raw(fd); + struct flock64 flock; + long err = -EBADF; + + if (!f.file) + goto out; + + switch (cmd) { + case F_GETLK64: + case F_OFD_GETLK: + err = security_file_fcntl(f.file, cmd, arg); + if (err) + break; + err = get_oabi_flock(&flock, argp); + if (err) + break; + err = fcntl_getlk64(f.file, cmd, &flock); + if (!err) + err = put_oabi_flock(&flock, argp); + break; + case F_SETLK64: + case F_SETLKW64: + case F_OFD_SETLK: + case F_OFD_SETLKW: + err = security_file_fcntl(f.file, cmd, arg); + if (err) + break; + err = get_oabi_flock(&flock, argp); + if (err) + break; + err = fcntl_setlk64(fd, f.file, cmd, &flock); + break; + default: + err = sys_fcntl64(fd, cmd, arg); + break; + } + fdput(f); +out: + return err; +} + +struct oabi_epoll_event { + __poll_t events; + __u64 data; +} __attribute__ ((packed,aligned(4))); + +#ifdef CONFIG_EPOLL +asmlinkage long sys_oabi_epoll_ctl(int epfd, int op, int fd, + struct oabi_epoll_event __user *event) +{ + struct oabi_epoll_event user; + struct epoll_event kernel; + + if (ep_op_has_event(op) && + copy_from_user(&user, event, sizeof(user))) + return -EFAULT; + + kernel.events = user.events; + kernel.data = user.data; + + return do_epoll_ctl(epfd, op, fd, &kernel, false); +} +#else +asmlinkage long sys_oabi_epoll_ctl(int epfd, int op, int fd, + struct oabi_epoll_event __user *event) +{ + return -EINVAL; +} +#endif + +struct epoll_event __user * +epoll_put_uevent(__poll_t revents, __u64 data, + struct epoll_event __user *uevent) +{ + if (in_oabi_syscall()) { + struct oabi_epoll_event __user *oevent = (void __user *)uevent; + + if (__put_user(revents, &oevent->events) || + __put_user(data, &oevent->data)) + return NULL; + + return (void __user *)(oevent+1); + } + + if (__put_user(revents, &uevent->events) || + __put_user(data, &uevent->data)) + return NULL; + + return uevent+1; +} + +struct oabi_sembuf { + unsigned short sem_num; + short sem_op; + short sem_flg; + unsigned short __pad; +}; + +#define sc_semopm sem_ctls[2] + +#ifdef CONFIG_SYSVIPC +asmlinkage long sys_oabi_semtimedop(int semid, + struct oabi_sembuf __user *tsops, + unsigned nsops, + const struct old_timespec32 __user *timeout) +{ + struct ipc_namespace *ns; + struct sembuf *sops; + long err; + int i; + + ns = current->nsproxy->ipc_ns; + if (nsops > ns->sc_semopm) + return -E2BIG; + if (nsops < 1 || nsops > SEMOPM) + return -EINVAL; + sops = kvmalloc_array(nsops, sizeof(*sops), GFP_KERNEL); + if (!sops) + return -ENOMEM; + err = 0; + for (i = 0; i < nsops; i++) { + struct oabi_sembuf osb; + err |= copy_from_user(&osb, tsops, sizeof(osb)); + sops[i].sem_num = osb.sem_num; + sops[i].sem_op = osb.sem_op; + sops[i].sem_flg = osb.sem_flg; + tsops++; + } + if (err) { + err = -EFAULT; + goto out; + } + + if (timeout) { + struct timespec64 ts; + err = get_old_timespec32(&ts, timeout); + if (err) + goto out; + err = __do_semtimedop(semid, sops, nsops, &ts, ns); + goto out; + } + err = __do_semtimedop(semid, sops, nsops, NULL, ns); +out: + kvfree(sops); + return err; +} + +asmlinkage long sys_oabi_semop(int semid, struct oabi_sembuf __user *tsops, + unsigned nsops) +{ + return sys_oabi_semtimedop(semid, tsops, nsops, NULL); +} + +asmlinkage int sys_oabi_ipc(uint call, int first, int second, int third, + void __user *ptr, long fifth) +{ + switch (call & 0xffff) { + case SEMOP: + return sys_oabi_semtimedop(first, + (struct oabi_sembuf __user *)ptr, + second, NULL); + case SEMTIMEDOP: + return sys_oabi_semtimedop(first, + (struct oabi_sembuf __user *)ptr, + second, + (const struct old_timespec32 __user *)fifth); + default: + return sys_ipc(call, first, second, third, ptr, fifth); + } +} +#else +asmlinkage long sys_oabi_semtimedop(int semid, + struct oabi_sembuf __user *tsops, + unsigned nsops, + const struct old_timespec32 __user *timeout) +{ + return -ENOSYS; +} + +asmlinkage long sys_oabi_semop(int semid, struct oabi_sembuf __user *tsops, + unsigned nsops) +{ + return -ENOSYS; +} + +asmlinkage int sys_oabi_ipc(uint call, int first, int second, int third, + void __user *ptr, long fifth) +{ + return -ENOSYS; +} +#endif + +asmlinkage long sys_oabi_bind(int fd, struct sockaddr __user *addr, int addrlen) +{ + sa_family_t sa_family; + if (addrlen == 112 && + get_user(sa_family, &addr->sa_family) == 0 && + sa_family == AF_UNIX) + addrlen = 110; + return sys_bind(fd, addr, addrlen); +} + +asmlinkage long sys_oabi_connect(int fd, struct sockaddr __user *addr, int addrlen) +{ + sa_family_t sa_family; + if (addrlen == 112 && + get_user(sa_family, &addr->sa_family) == 0 && + sa_family == AF_UNIX) + addrlen = 110; + return sys_connect(fd, addr, addrlen); +} + +asmlinkage long sys_oabi_sendto(int fd, void __user *buff, + size_t len, unsigned flags, + struct sockaddr __user *addr, + int addrlen) +{ + sa_family_t sa_family; + if (addrlen == 112 && + get_user(sa_family, &addr->sa_family) == 0 && + sa_family == AF_UNIX) + addrlen = 110; + return sys_sendto(fd, buff, len, flags, addr, addrlen); +} + +asmlinkage long sys_oabi_sendmsg(int fd, struct user_msghdr __user *msg, unsigned flags) +{ + struct sockaddr __user *addr; + int msg_namelen; + sa_family_t sa_family; + if (msg && + get_user(msg_namelen, &msg->msg_namelen) == 0 && + msg_namelen == 112 && + get_user(addr, &msg->msg_name) == 0 && + get_user(sa_family, &addr->sa_family) == 0 && + sa_family == AF_UNIX) + { + /* + * HACK ALERT: there is a limit to how much backward bending + * we should do for what is actually a transitional + * compatibility layer. This already has known flaws with + * a few ioctls that we don't intend to fix. Therefore + * consider this blatent hack as another one... and take care + * to run for cover. In most cases it will "just work fine". + * If it doesn't, well, tough. + */ + put_user(110, &msg->msg_namelen); + } + return sys_sendmsg(fd, msg, flags); +} + +asmlinkage long sys_oabi_socketcall(int call, unsigned long __user *args) +{ + unsigned long r = -EFAULT, a[6]; + + switch (call) { + case SYS_BIND: + if (copy_from_user(a, args, 3 * sizeof(long)) == 0) + r = sys_oabi_bind(a[0], (struct sockaddr __user *)a[1], a[2]); + break; + case SYS_CONNECT: + if (copy_from_user(a, args, 3 * sizeof(long)) == 0) + r = sys_oabi_connect(a[0], (struct sockaddr __user *)a[1], a[2]); + break; + case SYS_SENDTO: + if (copy_from_user(a, args, 6 * sizeof(long)) == 0) + r = sys_oabi_sendto(a[0], (void __user *)a[1], a[2], a[3], + (struct sockaddr __user *)a[4], a[5]); + break; + case SYS_SENDMSG: + if (copy_from_user(a, args, 3 * sizeof(long)) == 0) + r = sys_oabi_sendmsg(a[0], (struct user_msghdr __user *)a[1], a[2]); + break; + default: + r = sys_socketcall(call, args); + } + + return r; +} diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c new file mode 100644 index 000000000..d3a85f01b --- /dev/null +++ b/arch/arm/kernel/tcm.c @@ -0,0 +1,435 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2008-2009 ST-Ericsson AB + * TCM memory handling for ARM systems + * + * Author: Linus Walleij <linus.walleij@stericsson.com> + * Author: Rickard Andersson <rickard.andersson@stericsson.com> + */ +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/stddef.h> +#include <linux/ioport.h> +#include <linux/genalloc.h> +#include <linux/string.h> /* memcpy */ +#include <asm/cputype.h> +#include <asm/mach/map.h> +#include <asm/memory.h> +#include <asm/system_info.h> +#include <asm/traps.h> +#include <asm/tcm.h> + +#define TCMTR_FORMAT_MASK 0xe0000000U + +static struct gen_pool *tcm_pool; +static bool dtcm_present; +static bool itcm_present; + +/* TCM section definitions from the linker */ +extern char __itcm_start, __sitcm_text, __eitcm_text; +extern char __dtcm_start, __sdtcm_data, __edtcm_data; + +/* These will be increased as we run */ +static u32 dtcm_end = DTCM_OFFSET; +static u32 itcm_end = ITCM_OFFSET; + +/* + * TCM memory resources + */ +static struct resource dtcm_res = { + .name = "DTCM RAM", + .start = DTCM_OFFSET, + .end = DTCM_OFFSET, + .flags = IORESOURCE_MEM +}; + +static struct resource itcm_res = { + .name = "ITCM RAM", + .start = ITCM_OFFSET, + .end = ITCM_OFFSET, + .flags = IORESOURCE_MEM +}; + +static struct map_desc dtcm_iomap[] __initdata = { + { + .virtual = DTCM_OFFSET, + .pfn = __phys_to_pfn(DTCM_OFFSET), + .length = 0, + .type = MT_MEMORY_RW_DTCM + } +}; + +static struct map_desc itcm_iomap[] __initdata = { + { + .virtual = ITCM_OFFSET, + .pfn = __phys_to_pfn(ITCM_OFFSET), + .length = 0, + .type = MT_MEMORY_RWX_ITCM, + } +}; + +/* + * Allocate a chunk of TCM memory + */ +void *tcm_alloc(size_t len) +{ + unsigned long vaddr; + + if (!tcm_pool) + return NULL; + + vaddr = gen_pool_alloc(tcm_pool, len); + if (!vaddr) + return NULL; + + return (void *) vaddr; +} +EXPORT_SYMBOL(tcm_alloc); + +/* + * Free a chunk of TCM memory + */ +void tcm_free(void *addr, size_t len) +{ + gen_pool_free(tcm_pool, (unsigned long) addr, len); +} +EXPORT_SYMBOL(tcm_free); + +bool tcm_dtcm_present(void) +{ + return dtcm_present; +} +EXPORT_SYMBOL(tcm_dtcm_present); + +bool tcm_itcm_present(void) +{ + return itcm_present; +} +EXPORT_SYMBOL(tcm_itcm_present); + +static int __init setup_tcm_bank(u8 type, u8 bank, u8 banks, + u32 *offset) +{ + const int tcm_sizes[16] = { 0, -1, -1, 4, 8, 16, 32, 64, 128, + 256, 512, 1024, -1, -1, -1, -1 }; + u32 tcm_region; + int tcm_size; + + /* + * If there are more than one TCM bank of this type, + * select the TCM bank to operate on in the TCM selection + * register. + */ + if (banks > 1) + asm("mcr p15, 0, %0, c9, c2, 0" + : /* No output operands */ + : "r" (bank)); + + /* Read the special TCM region register c9, 0 */ + if (!type) + asm("mrc p15, 0, %0, c9, c1, 0" + : "=r" (tcm_region)); + else + asm("mrc p15, 0, %0, c9, c1, 1" + : "=r" (tcm_region)); + + tcm_size = tcm_sizes[(tcm_region >> 2) & 0x0f]; + if (tcm_size < 0) { + pr_err("CPU: %sTCM%d of unknown size\n", + type ? "I" : "D", bank); + return -EINVAL; + } else if (tcm_size > 32) { + pr_err("CPU: %sTCM%d larger than 32k found\n", + type ? "I" : "D", bank); + return -EINVAL; + } else { + pr_info("CPU: found %sTCM%d %dk @ %08x, %senabled\n", + type ? "I" : "D", + bank, + tcm_size, + (tcm_region & 0xfffff000U), + (tcm_region & 1) ? "" : "not "); + } + + /* Not much fun you can do with a size 0 bank */ + if (tcm_size == 0) + return 0; + + /* Force move the TCM bank to where we want it, enable */ + tcm_region = *offset | (tcm_region & 0x00000ffeU) | 1; + + if (!type) + asm("mcr p15, 0, %0, c9, c1, 0" + : /* No output operands */ + : "r" (tcm_region)); + else + asm("mcr p15, 0, %0, c9, c1, 1" + : /* No output operands */ + : "r" (tcm_region)); + + /* Increase offset */ + *offset += (tcm_size << 10); + + pr_info("CPU: moved %sTCM%d %dk to %08x, enabled\n", + type ? "I" : "D", + bank, + tcm_size, + (tcm_region & 0xfffff000U)); + return 0; +} + +/* + * When we are running in the non-secure world and the secure world + * has not explicitly given us access to the TCM we will get an + * undefined error when reading the TCM region register in the + * setup_tcm_bank function (above). + * + * There are two variants of this register read that we need to trap, + * the read for the data TCM and the read for the instruction TCM: + * c0370628: ee196f11 mrc 15, 0, r6, cr9, cr1, {0} + * c0370674: ee196f31 mrc 15, 0, r6, cr9, cr1, {1} + * + * Our undef hook mask explicitly matches all fields of the encoded + * instruction other than the destination register. The mask also + * only allows operand 2 to have the values 0 or 1. + * + * The undefined hook is defined as __init and __initdata, and therefore + * must be removed before tcm_init returns. + * + * In this particular case (MRC with ARM condition code ALways) the + * Thumb-2 and ARM instruction encoding are identical, so this hook + * will work on a Thumb-2 kernel. + * + * See A8.8.107, DDI0406C_C ARM Architecture Reference Manual, Encoding + * T1/A1 for the bit-by-bit details. + * + * mrc p15, 0, XX, c9, c1, 0 + * mrc p15, 0, XX, c9, c1, 1 + * | | | | | | | +---- opc2 0|1 = 000|001 + * | | | | | | +------- CRm 0 = 0001 + * | | | | | +----------- CRn 0 = 1001 + * | | | | +--------------- Rt ? = ???? + * | | | +------------------- opc1 0 = 000 + * | | +----------------------- coproc 15 = 1111 + * | +-------------------------- condition ALways = 1110 + * +----------------------------- instruction MRC = 1110 + * + * Encoding this as per A8.8.107 of DDI0406C, Encoding T1/A1, yields: + * 1111 1111 1111 1111 0000 1111 1101 1111 Required Mask + * 1110 1110 0001 1001 ???? 1111 0001 0001 mrc p15, 0, XX, c9, c1, 0 + * 1110 1110 0001 1001 ???? 1111 0011 0001 mrc p15, 0, XX, c9, c1, 1 + * [ ] [ ] [ ]| [ ] [ ] [ ] [ ]| +--- CRm + * | | | | | | | | +----- SBO + * | | | | | | | +------- opc2 + * | | | | | | +----------- coproc + * | | | | | +---------------- Rt + * | | | | +--------------------- CRn + * | | | +------------------------- SBO + * | | +--------------------------- opc1 + * | +------------------------------- instruction + * +------------------------------------ condition + */ +#define TCM_REGION_READ_MASK 0xffff0fdf +#define TCM_REGION_READ_INSTR 0xee190f11 +#define DEST_REG_SHIFT 12 +#define DEST_REG_MASK 0xf + +static int __init tcm_handler(struct pt_regs *regs, unsigned int instr) +{ + regs->uregs[(instr >> DEST_REG_SHIFT) & DEST_REG_MASK] = 0; + regs->ARM_pc += 4; + return 0; +} + +static struct undef_hook tcm_hook __initdata = { + .instr_mask = TCM_REGION_READ_MASK, + .instr_val = TCM_REGION_READ_INSTR, + .cpsr_mask = MODE_MASK, + .cpsr_val = SVC_MODE, + .fn = tcm_handler +}; + +/* + * This initializes the TCM memory + */ +void __init tcm_init(void) +{ + u32 tcm_status; + u8 dtcm_banks; + u8 itcm_banks; + size_t dtcm_code_sz = &__edtcm_data - &__sdtcm_data; + size_t itcm_code_sz = &__eitcm_text - &__sitcm_text; + char *start; + char *end; + char *ram; + int ret; + int i; + + /* + * Prior to ARMv5 there is no TCM, and trying to read the status + * register will hang the processor. + */ + if (cpu_architecture() < CPU_ARCH_ARMv5) { + if (dtcm_code_sz || itcm_code_sz) + pr_info("CPU TCM: %u bytes of DTCM and %u bytes of " + "ITCM code compiled in, but no TCM present " + "in pre-v5 CPU\n", dtcm_code_sz, itcm_code_sz); + return; + } + + tcm_status = read_cpuid_tcmstatus(); + + /* + * This code only supports v6-compatible TCMTR implementations. + */ + if (tcm_status & TCMTR_FORMAT_MASK) + return; + + dtcm_banks = (tcm_status >> 16) & 0x03; + itcm_banks = (tcm_status & 0x03); + + register_undef_hook(&tcm_hook); + + /* Values greater than 2 for D/ITCM banks are "reserved" */ + if (dtcm_banks > 2) + dtcm_banks = 0; + if (itcm_banks > 2) + itcm_banks = 0; + + /* Setup DTCM if present */ + if (dtcm_banks > 0) { + for (i = 0; i < dtcm_banks; i++) { + ret = setup_tcm_bank(0, i, dtcm_banks, &dtcm_end); + if (ret) + goto unregister; + } + /* This means you compiled more code than fits into DTCM */ + if (dtcm_code_sz > (dtcm_end - DTCM_OFFSET)) { + pr_info("CPU DTCM: %u bytes of code compiled to " + "DTCM but only %lu bytes of DTCM present\n", + dtcm_code_sz, (dtcm_end - DTCM_OFFSET)); + goto no_dtcm; + } + /* + * This means that the DTCM sizes were 0 or the DTCM banks + * were inaccessible due to TrustZone configuration. + */ + if (!(dtcm_end - DTCM_OFFSET)) + goto no_dtcm; + dtcm_res.end = dtcm_end - 1; + request_resource(&iomem_resource, &dtcm_res); + dtcm_iomap[0].length = dtcm_end - DTCM_OFFSET; + iotable_init(dtcm_iomap, 1); + /* Copy data from RAM to DTCM */ + start = &__sdtcm_data; + end = &__edtcm_data; + ram = &__dtcm_start; + memcpy(start, ram, dtcm_code_sz); + pr_debug("CPU DTCM: copied data from %p - %p\n", + start, end); + dtcm_present = true; + } else if (dtcm_code_sz) { + pr_info("CPU DTCM: %u bytes of code compiled to DTCM but no " + "DTCM banks present in CPU\n", dtcm_code_sz); + } + +no_dtcm: + /* Setup ITCM if present */ + if (itcm_banks > 0) { + for (i = 0; i < itcm_banks; i++) { + ret = setup_tcm_bank(1, i, itcm_banks, &itcm_end); + if (ret) + goto unregister; + } + /* This means you compiled more code than fits into ITCM */ + if (itcm_code_sz > (itcm_end - ITCM_OFFSET)) { + pr_info("CPU ITCM: %u bytes of code compiled to " + "ITCM but only %lu bytes of ITCM present\n", + itcm_code_sz, (itcm_end - ITCM_OFFSET)); + goto unregister; + } + /* + * This means that the ITCM sizes were 0 or the ITCM banks + * were inaccessible due to TrustZone configuration. + */ + if (!(itcm_end - ITCM_OFFSET)) + goto unregister; + itcm_res.end = itcm_end - 1; + request_resource(&iomem_resource, &itcm_res); + itcm_iomap[0].length = itcm_end - ITCM_OFFSET; + iotable_init(itcm_iomap, 1); + /* Copy code from RAM to ITCM */ + start = &__sitcm_text; + end = &__eitcm_text; + ram = &__itcm_start; + memcpy(start, ram, itcm_code_sz); + pr_debug("CPU ITCM: copied code from %p - %p\n", + start, end); + itcm_present = true; + } else if (itcm_code_sz) { + pr_info("CPU ITCM: %u bytes of code compiled to ITCM but no " + "ITCM banks present in CPU\n", itcm_code_sz); + } + +unregister: + unregister_undef_hook(&tcm_hook); +} + +/* + * This creates the TCM memory pool and has to be done later, + * during the core_initicalls, since the allocator is not yet + * up and running when the first initialization runs. + */ +static int __init setup_tcm_pool(void) +{ + u32 dtcm_pool_start = (u32) &__edtcm_data; + u32 itcm_pool_start = (u32) &__eitcm_text; + int ret; + + /* + * Set up malloc pool, 2^2 = 4 bytes granularity since + * the TCM is sometimes just 4 KiB. NB: pages and cache + * line alignments does not matter in TCM! + */ + tcm_pool = gen_pool_create(2, -1); + + pr_debug("Setting up TCM memory pool\n"); + + /* Add the rest of DTCM to the TCM pool */ + if (dtcm_present) { + if (dtcm_pool_start < dtcm_end) { + ret = gen_pool_add(tcm_pool, dtcm_pool_start, + dtcm_end - dtcm_pool_start, -1); + if (ret) { + pr_err("CPU DTCM: could not add DTCM " \ + "remainder to pool!\n"); + return ret; + } + pr_debug("CPU DTCM: Added %08x bytes @ %08x to " \ + "the TCM memory pool\n", + dtcm_end - dtcm_pool_start, + dtcm_pool_start); + } + } + + /* Add the rest of ITCM to the TCM pool */ + if (itcm_present) { + if (itcm_pool_start < itcm_end) { + ret = gen_pool_add(tcm_pool, itcm_pool_start, + itcm_end - itcm_pool_start, -1); + if (ret) { + pr_err("CPU ITCM: could not add ITCM " \ + "remainder to pool!\n"); + return ret; + } + pr_debug("CPU ITCM: Added %08x bytes @ %08x to " \ + "the TCM memory pool\n", + itcm_end - itcm_pool_start, + itcm_pool_start); + } + } + return 0; +} + +core_initcall(setup_tcm_pool); diff --git a/arch/arm/kernel/thumbee.c b/arch/arm/kernel/thumbee.c new file mode 100644 index 000000000..d832eb9e6 --- /dev/null +++ b/arch/arm/kernel/thumbee.c @@ -0,0 +1,70 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * arch/arm/kernel/thumbee.c + * + * Copyright (C) 2008 ARM Limited + */ + +#include <linux/kernel.h> +#include <linux/init.h> + +#include <asm/cputype.h> +#include <asm/system_info.h> +#include <asm/thread_notify.h> + +/* + * Access to the ThumbEE Handler Base register + */ +static inline unsigned long teehbr_read(void) +{ + unsigned long v; + asm("mrc p14, 6, %0, c1, c0, 0\n" : "=r" (v)); + return v; +} + +static inline void teehbr_write(unsigned long v) +{ + asm("mcr p14, 6, %0, c1, c0, 0\n" : : "r" (v)); +} + +static int thumbee_notifier(struct notifier_block *self, unsigned long cmd, void *t) +{ + struct thread_info *thread = t; + + switch (cmd) { + case THREAD_NOTIFY_FLUSH: + teehbr_write(0); + break; + case THREAD_NOTIFY_SWITCH: + current_thread_info()->thumbee_state = teehbr_read(); + teehbr_write(thread->thumbee_state); + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block thumbee_notifier_block = { + .notifier_call = thumbee_notifier, +}; + +static int __init thumbee_init(void) +{ + unsigned long pfr0; + unsigned int cpu_arch = cpu_architecture(); + + if (cpu_arch < CPU_ARCH_ARMv7) + return 0; + + pfr0 = read_cpuid_ext(CPUID_EXT_PFR0); + if ((pfr0 & 0x0000f000) != 0x00001000) + return 0; + + pr_info("ThumbEE CPU extension supported.\n"); + elf_hwcap |= HWCAP_THUMBEE; + thread_register_notifier(&thumbee_notifier_block); + + return 0; +} + +late_initcall(thumbee_init); diff --git a/arch/arm/kernel/time.c b/arch/arm/kernel/time.c new file mode 100644 index 000000000..b3836c94d --- /dev/null +++ b/arch/arm/kernel/time.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/time.c + * + * Copyright (C) 1991, 1992, 1995 Linus Torvalds + * Modifications for ARM (C) 1994-2001 Russell King + * + * This file contains the ARM-specific time handling details: + * reading the RTC at bootup, etc... + */ +#include <linux/clockchips.h> +#include <linux/clocksource.h> +#include <linux/errno.h> +#include <linux/export.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/of_clk.h> +#include <linux/profile.h> +#include <linux/sched.h> +#include <linux/sched_clock.h> +#include <linux/smp.h> +#include <linux/time.h> +#include <linux/timex.h> +#include <linux/timer.h> + +#include <asm/mach/arch.h> +#include <asm/mach/time.h> +#include <asm/stacktrace.h> +#include <asm/thread_info.h> + +#if defined(CONFIG_RTC_DRV_CMOS) || defined(CONFIG_RTC_DRV_CMOS_MODULE) || \ + defined(CONFIG_NVRAM) || defined(CONFIG_NVRAM_MODULE) +/* this needs a better home */ +DEFINE_SPINLOCK(rtc_lock); +EXPORT_SYMBOL(rtc_lock); +#endif /* pc-style 'CMOS' RTC support */ + +/* change this if you have some constant time drift */ +#define USECS_PER_JIFFY (1000000/HZ) + +#ifdef CONFIG_SMP +unsigned long profile_pc(struct pt_regs *regs) +{ + struct stackframe frame; + + if (!in_lock_functions(regs->ARM_pc)) + return regs->ARM_pc; + + arm_get_current_stackframe(regs, &frame); + do { + int ret = unwind_frame(&frame); + if (ret < 0) + return 0; + } while (in_lock_functions(frame.pc)); + + return frame.pc; +} +EXPORT_SYMBOL(profile_pc); +#endif + +static void dummy_clock_access(struct timespec64 *ts) +{ + ts->tv_sec = 0; + ts->tv_nsec = 0; +} + +static clock_access_fn __read_persistent_clock = dummy_clock_access; + +void read_persistent_clock64(struct timespec64 *ts) +{ + __read_persistent_clock(ts); +} + +int __init register_persistent_clock(clock_access_fn read_persistent) +{ + /* Only allow the clockaccess functions to be registered once */ + if (__read_persistent_clock == dummy_clock_access) { + if (read_persistent) + __read_persistent_clock = read_persistent; + return 0; + } + + return -EINVAL; +} + +void __init time_init(void) +{ + if (machine_desc->init_time) { + machine_desc->init_time(); + } else { +#ifdef CONFIG_COMMON_CLK + of_clk_init(NULL); +#endif + timer_probe(); + tick_setup_hrtimer_broadcast(); + } +} diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c new file mode 100644 index 000000000..ef0058de4 --- /dev/null +++ b/arch/arm/kernel/topology.c @@ -0,0 +1,245 @@ +/* + * arch/arm/kernel/topology.c + * + * Copyright (C) 2011 Linaro Limited. + * Written by: Vincent Guittot + * + * based on arch/sh/kernel/topology.c + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + */ + +#include <linux/arch_topology.h> +#include <linux/cpu.h> +#include <linux/cpufreq.h> +#include <linux/cpumask.h> +#include <linux/export.h> +#include <linux/init.h> +#include <linux/percpu.h> +#include <linux/node.h> +#include <linux/nodemask.h> +#include <linux/of.h> +#include <linux/sched.h> +#include <linux/sched/topology.h> +#include <linux/slab.h> +#include <linux/string.h> + +#include <asm/cpu.h> +#include <asm/cputype.h> +#include <asm/topology.h> + +/* + * cpu capacity scale management + */ + +/* + * cpu capacity table + * This per cpu data structure describes the relative capacity of each core. + * On a heteregenous system, cores don't have the same computation capacity + * and we reflect that difference in the cpu_capacity field so the scheduler + * can take this difference into account during load balance. A per cpu + * structure is preferred because each CPU updates its own cpu_capacity field + * during the load balance except for idle cores. One idle core is selected + * to run the rebalance_domains for all idle cores and the cpu_capacity can be + * updated during this sequence. + */ + +#ifdef CONFIG_OF +struct cpu_efficiency { + const char *compatible; + unsigned long efficiency; +}; + +/* + * Table of relative efficiency of each processors + * The efficiency value must fit in 20bit and the final + * cpu_scale value must be in the range + * 0 < cpu_scale < 3*SCHED_CAPACITY_SCALE/2 + * in order to return at most 1 when DIV_ROUND_CLOSEST + * is used to compute the capacity of a CPU. + * Processors that are not defined in the table, + * use the default SCHED_CAPACITY_SCALE value for cpu_scale. + */ +static const struct cpu_efficiency table_efficiency[] = { + {"arm,cortex-a15", 3891}, + {"arm,cortex-a7", 2048}, + {NULL, }, +}; + +static unsigned long *__cpu_capacity; +#define cpu_capacity(cpu) __cpu_capacity[cpu] + +static unsigned long middle_capacity = 1; +static bool cap_from_dt = true; + +/* + * Iterate all CPUs' descriptor in DT and compute the efficiency + * (as per table_efficiency). Also calculate a middle efficiency + * as close as possible to (max{eff_i} - min{eff_i}) / 2 + * This is later used to scale the cpu_capacity field such that an + * 'average' CPU is of middle capacity. Also see the comments near + * table_efficiency[] and update_cpu_capacity(). + */ +static void __init parse_dt_topology(void) +{ + const struct cpu_efficiency *cpu_eff; + struct device_node *cn = NULL; + unsigned long min_capacity = ULONG_MAX; + unsigned long max_capacity = 0; + unsigned long capacity = 0; + int cpu = 0; + + __cpu_capacity = kcalloc(nr_cpu_ids, sizeof(*__cpu_capacity), + GFP_NOWAIT); + + for_each_possible_cpu(cpu) { + const __be32 *rate; + int len; + + /* too early to use cpu->of_node */ + cn = of_get_cpu_node(cpu, NULL); + if (!cn) { + pr_err("missing device node for CPU %d\n", cpu); + continue; + } + + if (topology_parse_cpu_capacity(cn, cpu)) { + of_node_put(cn); + continue; + } + + cap_from_dt = false; + + for (cpu_eff = table_efficiency; cpu_eff->compatible; cpu_eff++) + if (of_device_is_compatible(cn, cpu_eff->compatible)) + break; + + if (cpu_eff->compatible == NULL) + continue; + + rate = of_get_property(cn, "clock-frequency", &len); + if (!rate || len != 4) { + pr_err("%pOF missing clock-frequency property\n", cn); + continue; + } + + capacity = ((be32_to_cpup(rate)) >> 20) * cpu_eff->efficiency; + + /* Save min capacity of the system */ + if (capacity < min_capacity) + min_capacity = capacity; + + /* Save max capacity of the system */ + if (capacity > max_capacity) + max_capacity = capacity; + + cpu_capacity(cpu) = capacity; + } + + /* If min and max capacities are equals, we bypass the update of the + * cpu_scale because all CPUs have the same capacity. Otherwise, we + * compute a middle_capacity factor that will ensure that the capacity + * of an 'average' CPU of the system will be as close as possible to + * SCHED_CAPACITY_SCALE, which is the default value, but with the + * constraint explained near table_efficiency[]. + */ + if (4*max_capacity < (3*(max_capacity + min_capacity))) + middle_capacity = (min_capacity + max_capacity) + >> (SCHED_CAPACITY_SHIFT+1); + else + middle_capacity = ((max_capacity / 3) + >> (SCHED_CAPACITY_SHIFT-1)) + 1; + + if (cap_from_dt) + topology_normalize_cpu_scale(); +} + +/* + * Look for a customed capacity of a CPU in the cpu_capacity table during the + * boot. The update of all CPUs is in O(n^2) for heteregeneous system but the + * function returns directly for SMP system. + */ +static void update_cpu_capacity(unsigned int cpu) +{ + if (!cpu_capacity(cpu) || cap_from_dt) + return; + + topology_set_cpu_scale(cpu, cpu_capacity(cpu) / middle_capacity); + + pr_info("CPU%u: update cpu_capacity %lu\n", + cpu, topology_get_cpu_scale(cpu)); +} + +#else +static inline void parse_dt_topology(void) {} +static inline void update_cpu_capacity(unsigned int cpuid) {} +#endif + +/* + * store_cpu_topology is called at boot when only one cpu is running + * and with the mutex cpu_hotplug.lock locked, when several cpus have booted, + * which prevents simultaneous write access to cpu_topology array + */ +void store_cpu_topology(unsigned int cpuid) +{ + struct cpu_topology *cpuid_topo = &cpu_topology[cpuid]; + unsigned int mpidr; + + if (cpuid_topo->package_id != -1) + goto topology_populated; + + mpidr = read_cpuid_mpidr(); + + /* create cpu topology mapping */ + if ((mpidr & MPIDR_SMP_BITMASK) == MPIDR_SMP_VALUE) { + /* + * This is a multiprocessor system + * multiprocessor format & multiprocessor mode field are set + */ + + if (mpidr & MPIDR_MT_BITMASK) { + /* core performance interdependency */ + cpuid_topo->thread_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 1); + cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 2); + } else { + /* largely independent cores */ + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = MPIDR_AFFINITY_LEVEL(mpidr, 0); + cpuid_topo->package_id = MPIDR_AFFINITY_LEVEL(mpidr, 1); + } + } else { + /* + * This is an uniprocessor system + * we are in multiprocessor format but uniprocessor system + * or in the old uniprocessor format + */ + cpuid_topo->thread_id = -1; + cpuid_topo->core_id = 0; + cpuid_topo->package_id = -1; + } + + update_cpu_capacity(cpuid); + + pr_info("CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n", + cpuid, cpu_topology[cpuid].thread_id, + cpu_topology[cpuid].core_id, + cpu_topology[cpuid].package_id, mpidr); + +topology_populated: + update_siblings_masks(cpuid); +} + +/* + * init_cpu_topology is called at boot when only one cpu is running + * which prevent simultaneous write access to cpu_topology array + */ +void __init init_cpu_topology(void) +{ + reset_cpu_topology(); + smp_wmb(); + + parse_dt_topology(); +} diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c new file mode 100644 index 000000000..20b2db6dc --- /dev/null +++ b/arch/arm/kernel/traps.c @@ -0,0 +1,963 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/traps.c + * + * Copyright (C) 1995-2009 Russell King + * Fragments that appear the same as linux/arch/i386/kernel/traps.c (C) Linus Torvalds + * + * 'traps.c' handles hardware exceptions after we have saved some state in + * 'linux/arch/arm/lib/traps.S'. Mostly a debugging aid, but will probably + * kill the offending process. + */ +#include <linux/signal.h> +#include <linux/personality.h> +#include <linux/kallsyms.h> +#include <linux/spinlock.h> +#include <linux/uaccess.h> +#include <linux/hardirq.h> +#include <linux/kdebug.h> +#include <linux/kprobes.h> +#include <linux/module.h> +#include <linux/kexec.h> +#include <linux/bug.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/sched/signal.h> +#include <linux/sched/debug.h> +#include <linux/sched/task_stack.h> +#include <linux/irq.h> + +#include <linux/atomic.h> +#include <asm/cacheflush.h> +#include <asm/exception.h> +#include <asm/spectre.h> +#include <asm/unistd.h> +#include <asm/traps.h> +#include <asm/ptrace.h> +#include <asm/unwind.h> +#include <asm/tls.h> +#include <asm/stacktrace.h> +#include <asm/system_misc.h> +#include <asm/opcodes.h> + + +static const char *handler[]= { + "prefetch abort", + "data abort", + "address exception", + "interrupt", + "undefined instruction", +}; + +void *vectors_page; + +#ifdef CONFIG_DEBUG_USER +unsigned int user_debug; + +static int __init user_debug_setup(char *str) +{ + get_option(&str, &user_debug); + return 1; +} +__setup("user_debug=", user_debug_setup); +#endif + +void dump_backtrace_entry(unsigned long where, unsigned long from, + unsigned long frame, const char *loglvl) +{ + unsigned long end = frame + 4 + sizeof(struct pt_regs); + + if (IS_ENABLED(CONFIG_UNWINDER_FRAME_POINTER) && + IS_ENABLED(CONFIG_CC_IS_GCC) && + end > ALIGN(frame, THREAD_SIZE)) { + /* + * If we are walking past the end of the stack, it may be due + * to the fact that we are on an IRQ or overflow stack. In this + * case, we can load the address of the other stack from the + * frame record. + */ + frame = ((unsigned long *)frame)[-2] - 4; + end = frame + 4 + sizeof(struct pt_regs); + } + +#ifndef CONFIG_KALLSYMS + printk("%sFunction entered at [<%08lx>] from [<%08lx>]\n", + loglvl, where, from); +#elif defined CONFIG_BACKTRACE_VERBOSE + printk("%s[<%08lx>] (%ps) from [<%08lx>] (%pS)\n", + loglvl, where, (void *)where, from, (void *)from); +#else + printk("%s %ps from %pS\n", loglvl, (void *)where, (void *)from); +#endif + + if (in_entry_text(from) && end <= ALIGN(frame, THREAD_SIZE)) + dump_mem(loglvl, "Exception stack", frame + 4, end); +} + +void dump_backtrace_stm(u32 *stack, u32 instruction, const char *loglvl) +{ + char str[80], *p; + unsigned int x; + int reg; + + for (reg = 10, x = 0, p = str; reg >= 0; reg--) { + if (instruction & BIT(reg)) { + p += sprintf(p, " r%d:%08x", reg, *stack--); + if (++x == 6) { + x = 0; + p = str; + printk("%s%s\n", loglvl, str); + } + } + } + if (p != str) + printk("%s%s\n", loglvl, str); +} + +#ifndef CONFIG_ARM_UNWIND +/* + * Stack pointers should always be within the kernels view of + * physical memory. If it is not there, then we can't dump + * out any information relating to the stack. + */ +static int verify_stack(unsigned long sp) +{ + if (sp < PAGE_OFFSET || + (!IS_ENABLED(CONFIG_VMAP_STACK) && + sp > (unsigned long)high_memory && high_memory != NULL)) + return -EFAULT; + + return 0; +} +#endif + +/* + * Dump out the contents of some memory nicely... + */ +void dump_mem(const char *lvl, const char *str, unsigned long bottom, + unsigned long top) +{ + unsigned long first; + int i; + + printk("%s%s(0x%08lx to 0x%08lx)\n", lvl, str, bottom, top); + + for (first = bottom & ~31; first < top; first += 32) { + unsigned long p; + char str[sizeof(" 12345678") * 8 + 1]; + + memset(str, ' ', sizeof(str)); + str[sizeof(str) - 1] = '\0'; + + for (p = first, i = 0; i < 8 && p < top; i++, p += 4) { + if (p >= bottom && p < top) { + unsigned long val; + if (!get_kernel_nofault(val, (unsigned long *)p)) + sprintf(str + i * 9, " %08lx", val); + else + sprintf(str + i * 9, " ????????"); + } + } + printk("%s%04lx:%s\n", lvl, first & 0xffff, str); + } +} + +static void dump_instr(const char *lvl, struct pt_regs *regs) +{ + unsigned long addr = instruction_pointer(regs); + const int thumb = thumb_mode(regs); + const int width = thumb ? 4 : 8; + char str[sizeof("00000000 ") * 5 + 2 + 1], *p = str; + int i; + + /* + * Note that we now dump the code first, just in case the backtrace + * kills us. + */ + + for (i = -4; i < 1 + !!thumb; i++) { + unsigned int val, bad; + + if (!user_mode(regs)) { + if (thumb) { + u16 val16; + bad = get_kernel_nofault(val16, &((u16 *)addr)[i]); + val = val16; + } else { + bad = get_kernel_nofault(val, &((u32 *)addr)[i]); + } + } else { + if (thumb) + bad = get_user(val, &((u16 *)addr)[i]); + else + bad = get_user(val, &((u32 *)addr)[i]); + } + + if (!bad) + p += sprintf(p, i == 0 ? "(%0*x) " : "%0*x ", + width, val); + else { + p += sprintf(p, "bad PC value"); + break; + } + } + printk("%sCode: %s\n", lvl, str); +} + +#ifdef CONFIG_ARM_UNWIND +void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk, + const char *loglvl) +{ + unwind_backtrace(regs, tsk, loglvl); +} +#else +void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk, + const char *loglvl) +{ + unsigned int fp, mode; + int ok = 1; + + printk("%sBacktrace: ", loglvl); + + if (!tsk) + tsk = current; + + if (regs) { + fp = frame_pointer(regs); + mode = processor_mode(regs); + } else if (tsk != current) { + fp = thread_saved_fp(tsk); + mode = 0x10; + } else { + asm("mov %0, fp" : "=r" (fp) : : "cc"); + mode = 0x10; + } + + if (!fp) { + pr_cont("no frame pointer"); + ok = 0; + } else if (verify_stack(fp)) { + pr_cont("invalid frame pointer 0x%08x", fp); + ok = 0; + } else if (fp < (unsigned long)end_of_stack(tsk)) + pr_cont("frame pointer underflow"); + pr_cont("\n"); + + if (ok) + c_backtrace(fp, mode, loglvl); +} +#endif + +void show_stack(struct task_struct *tsk, unsigned long *sp, const char *loglvl) +{ + dump_backtrace(NULL, tsk, loglvl); + barrier(); +} + +#ifdef CONFIG_PREEMPT +#define S_PREEMPT " PREEMPT" +#elif defined(CONFIG_PREEMPT_RT) +#define S_PREEMPT " PREEMPT_RT" +#else +#define S_PREEMPT "" +#endif +#ifdef CONFIG_SMP +#define S_SMP " SMP" +#else +#define S_SMP "" +#endif +#ifdef CONFIG_THUMB2_KERNEL +#define S_ISA " THUMB2" +#else +#define S_ISA " ARM" +#endif + +static int __die(const char *str, int err, struct pt_regs *regs) +{ + struct task_struct *tsk = current; + static int die_counter; + int ret; + + pr_emerg("Internal error: %s: %x [#%d]" S_PREEMPT S_SMP S_ISA "\n", + str, err, ++die_counter); + + /* trap and error numbers are mostly meaningless on ARM */ + ret = notify_die(DIE_OOPS, str, regs, err, tsk->thread.trap_no, SIGSEGV); + if (ret == NOTIFY_STOP) + return 1; + + print_modules(); + __show_regs(regs); + __show_regs_alloc_free(regs); + pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n", + TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), end_of_stack(tsk)); + + if (!user_mode(regs) || in_interrupt()) { + dump_mem(KERN_EMERG, "Stack: ", regs->ARM_sp, + ALIGN(regs->ARM_sp - THREAD_SIZE, THREAD_ALIGN) + + THREAD_SIZE); + dump_backtrace(regs, tsk, KERN_EMERG); + dump_instr(KERN_EMERG, regs); + } + + return 0; +} + +static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED; +static int die_owner = -1; +static unsigned int die_nest_count; + +static unsigned long oops_begin(void) +{ + int cpu; + unsigned long flags; + + oops_enter(); + + /* racy, but better than risking deadlock. */ + raw_local_irq_save(flags); + cpu = smp_processor_id(); + if (!arch_spin_trylock(&die_lock)) { + if (cpu == die_owner) + /* nested oops. should stop eventually */; + else + arch_spin_lock(&die_lock); + } + die_nest_count++; + die_owner = cpu; + console_verbose(); + bust_spinlocks(1); + return flags; +} + +static void oops_end(unsigned long flags, struct pt_regs *regs, int signr) +{ + if (regs && kexec_should_crash(current)) + crash_kexec(regs); + + bust_spinlocks(0); + die_owner = -1; + add_taint(TAINT_DIE, LOCKDEP_NOW_UNRELIABLE); + die_nest_count--; + if (!die_nest_count) + /* Nest count reaches zero, release the lock. */ + arch_spin_unlock(&die_lock); + raw_local_irq_restore(flags); + oops_exit(); + + if (in_interrupt()) + panic("Fatal exception in interrupt"); + if (panic_on_oops) + panic("Fatal exception"); + if (signr) + make_task_dead(signr); +} + +/* + * This function is protected against re-entrancy. + */ +void die(const char *str, struct pt_regs *regs, int err) +{ + enum bug_trap_type bug_type = BUG_TRAP_TYPE_NONE; + unsigned long flags = oops_begin(); + int sig = SIGSEGV; + + if (!user_mode(regs)) + bug_type = report_bug(regs->ARM_pc, regs); + if (bug_type != BUG_TRAP_TYPE_NONE) + str = "Oops - BUG"; + + if (__die(str, err, regs)) + sig = 0; + + oops_end(flags, regs, sig); +} + +void arm_notify_die(const char *str, struct pt_regs *regs, + int signo, int si_code, void __user *addr, + unsigned long err, unsigned long trap) +{ + if (user_mode(regs)) { + current->thread.error_code = err; + current->thread.trap_no = trap; + + force_sig_fault(signo, si_code, addr); + } else { + die(str, regs, err); + } +} + +#ifdef CONFIG_GENERIC_BUG + +int is_valid_bugaddr(unsigned long pc) +{ +#ifdef CONFIG_THUMB2_KERNEL + u16 bkpt; + u16 insn = __opcode_to_mem_thumb16(BUG_INSTR_VALUE); +#else + u32 bkpt; + u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE); +#endif + + if (get_kernel_nofault(bkpt, (void *)pc)) + return 0; + + return bkpt == insn; +} + +#endif + +static LIST_HEAD(undef_hook); +static DEFINE_RAW_SPINLOCK(undef_lock); + +void register_undef_hook(struct undef_hook *hook) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&undef_lock, flags); + list_add(&hook->node, &undef_hook); + raw_spin_unlock_irqrestore(&undef_lock, flags); +} + +void unregister_undef_hook(struct undef_hook *hook) +{ + unsigned long flags; + + raw_spin_lock_irqsave(&undef_lock, flags); + list_del(&hook->node); + raw_spin_unlock_irqrestore(&undef_lock, flags); +} + +static nokprobe_inline +int call_undef_hook(struct pt_regs *regs, unsigned int instr) +{ + struct undef_hook *hook; + unsigned long flags; + int (*fn)(struct pt_regs *regs, unsigned int instr) = NULL; + + raw_spin_lock_irqsave(&undef_lock, flags); + list_for_each_entry(hook, &undef_hook, node) + if ((instr & hook->instr_mask) == hook->instr_val && + (regs->ARM_cpsr & hook->cpsr_mask) == hook->cpsr_val) + fn = hook->fn; + raw_spin_unlock_irqrestore(&undef_lock, flags); + + return fn ? fn(regs, instr) : 1; +} + +asmlinkage void do_undefinstr(struct pt_regs *regs) +{ + unsigned int instr; + void __user *pc; + + pc = (void __user *)instruction_pointer(regs); + + if (processor_mode(regs) == SVC_MODE) { +#ifdef CONFIG_THUMB2_KERNEL + if (thumb_mode(regs)) { + instr = __mem_to_opcode_thumb16(((u16 *)pc)[0]); + if (is_wide_instruction(instr)) { + u16 inst2; + inst2 = __mem_to_opcode_thumb16(((u16 *)pc)[1]); + instr = __opcode_thumb32_compose(instr, inst2); + } + } else +#endif + instr = __mem_to_opcode_arm(*(u32 *) pc); + } else if (thumb_mode(regs)) { + if (get_user(instr, (u16 __user *)pc)) + goto die_sig; + instr = __mem_to_opcode_thumb16(instr); + if (is_wide_instruction(instr)) { + unsigned int instr2; + if (get_user(instr2, (u16 __user *)pc+1)) + goto die_sig; + instr2 = __mem_to_opcode_thumb16(instr2); + instr = __opcode_thumb32_compose(instr, instr2); + } + } else { + if (get_user(instr, (u32 __user *)pc)) + goto die_sig; + instr = __mem_to_opcode_arm(instr); + } + + if (call_undef_hook(regs, instr) == 0) + return; + +die_sig: +#ifdef CONFIG_DEBUG_USER + if (user_debug & UDBG_UNDEFINED) { + pr_info("%s (%d): undefined instruction: pc=%px\n", + current->comm, task_pid_nr(current), pc); + __show_regs(regs); + dump_instr(KERN_INFO, regs); + } +#endif + arm_notify_die("Oops - undefined instruction", regs, + SIGILL, ILL_ILLOPC, pc, 0, 6); +} +NOKPROBE_SYMBOL(do_undefinstr) + +/* + * Handle FIQ similarly to NMI on x86 systems. + * + * The runtime environment for NMIs is extremely restrictive + * (NMIs can pre-empt critical sections meaning almost all locking is + * forbidden) meaning this default FIQ handling must only be used in + * circumstances where non-maskability improves robustness, such as + * watchdog or debug logic. + * + * This handler is not appropriate for general purpose use in drivers + * platform code and can be overrideen using set_fiq_handler. + */ +asmlinkage void __exception_irq_entry handle_fiq_as_nmi(struct pt_regs *regs) +{ + struct pt_regs *old_regs = set_irq_regs(regs); + + nmi_enter(); + + /* nop. FIQ handlers for special arch/arm features can be added here. */ + + nmi_exit(); + + set_irq_regs(old_regs); +} + +/* + * bad_mode handles the impossible case in the vectors. If you see one of + * these, then it's extremely serious, and could mean you have buggy hardware. + * It never returns, and never tries to sync. We hope that we can at least + * dump out some state information... + */ +asmlinkage void bad_mode(struct pt_regs *regs, int reason) +{ + console_verbose(); + + pr_crit("Bad mode in %s handler detected\n", handler[reason]); + + die("Oops - bad mode", regs, 0); + local_irq_disable(); + panic("bad mode"); +} + +static int bad_syscall(int n, struct pt_regs *regs) +{ + if ((current->personality & PER_MASK) != PER_LINUX) { + send_sig(SIGSEGV, current, 1); + return regs->ARM_r0; + } + +#ifdef CONFIG_DEBUG_USER + if (user_debug & UDBG_SYSCALL) { + pr_err("[%d] %s: obsolete system call %08x.\n", + task_pid_nr(current), current->comm, n); + dump_instr(KERN_ERR, regs); + } +#endif + + arm_notify_die("Oops - bad syscall", regs, SIGILL, ILL_ILLTRP, + (void __user *)instruction_pointer(regs) - + (thumb_mode(regs) ? 2 : 4), + n, 0); + + return regs->ARM_r0; +} + +static inline int +__do_cache_op(unsigned long start, unsigned long end) +{ + int ret; + + do { + unsigned long chunk = min(PAGE_SIZE, end - start); + + if (fatal_signal_pending(current)) + return 0; + + ret = flush_icache_user_range(start, start + chunk); + if (ret) + return ret; + + cond_resched(); + start += chunk; + } while (start < end); + + return 0; +} + +static inline int +do_cache_op(unsigned long start, unsigned long end, int flags) +{ + if (end < start || flags) + return -EINVAL; + + if (!access_ok((void __user *)start, end - start)) + return -EFAULT; + + return __do_cache_op(start, end); +} + +/* + * Handle all unrecognised system calls. + * 0x9f0000 - 0x9fffff are some more esoteric system calls + */ +#define NR(x) ((__ARM_NR_##x) - __ARM_NR_BASE) +asmlinkage int arm_syscall(int no, struct pt_regs *regs) +{ + if ((no >> 16) != (__ARM_NR_BASE>> 16)) + return bad_syscall(no, regs); + + switch (no & 0xffff) { + case 0: /* branch through 0 */ + arm_notify_die("branch through zero", regs, + SIGSEGV, SEGV_MAPERR, NULL, 0, 0); + return 0; + + case NR(breakpoint): /* SWI BREAK_POINT */ + regs->ARM_pc -= thumb_mode(regs) ? 2 : 4; + ptrace_break(regs); + return regs->ARM_r0; + + /* + * Flush a region from virtual address 'r0' to virtual address 'r1' + * _exclusive_. There is no alignment requirement on either address; + * user space does not need to know the hardware cache layout. + * + * r2 contains flags. It should ALWAYS be passed as ZERO until it + * is defined to be something else. For now we ignore it, but may + * the fires of hell burn in your belly if you break this rule. ;) + * + * (at a later date, we may want to allow this call to not flush + * various aspects of the cache. Passing '0' will guarantee that + * everything necessary gets flushed to maintain consistency in + * the specified region). + */ + case NR(cacheflush): + return do_cache_op(regs->ARM_r0, regs->ARM_r1, regs->ARM_r2); + + case NR(usr26): + if (!(elf_hwcap & HWCAP_26BIT)) + break; + regs->ARM_cpsr &= ~MODE32_BIT; + return regs->ARM_r0; + + case NR(usr32): + if (!(elf_hwcap & HWCAP_26BIT)) + break; + regs->ARM_cpsr |= MODE32_BIT; + return regs->ARM_r0; + + case NR(set_tls): + set_tls(regs->ARM_r0); + return 0; + + case NR(get_tls): + return current_thread_info()->tp_value[0]; + + default: + /* Calls 9f00xx..9f07ff are defined to return -ENOSYS + if not implemented, rather than raising SIGILL. This + way the calling program can gracefully determine whether + a feature is supported. */ + if ((no & 0xffff) <= 0x7ff) + return -ENOSYS; + break; + } +#ifdef CONFIG_DEBUG_USER + /* + * experience shows that these seem to indicate that + * something catastrophic has happened + */ + if (user_debug & UDBG_SYSCALL) { + pr_err("[%d] %s: arm syscall %d\n", + task_pid_nr(current), current->comm, no); + dump_instr(KERN_ERR, regs); + if (user_mode(regs)) { + __show_regs(regs); + c_backtrace(frame_pointer(regs), processor_mode(regs), KERN_ERR); + } + } +#endif + arm_notify_die("Oops - bad syscall(2)", regs, SIGILL, ILL_ILLTRP, + (void __user *)instruction_pointer(regs) - + (thumb_mode(regs) ? 2 : 4), + no, 0); + return 0; +} + +#ifdef CONFIG_TLS_REG_EMUL + +/* + * We might be running on an ARMv6+ processor which should have the TLS + * register but for some reason we can't use it, or maybe an SMP system + * using a pre-ARMv6 processor (there are apparently a few prototypes like + * that in existence) and therefore access to that register must be + * emulated. + */ + +static int get_tp_trap(struct pt_regs *regs, unsigned int instr) +{ + int reg = (instr >> 12) & 15; + if (reg == 15) + return 1; + regs->uregs[reg] = current_thread_info()->tp_value[0]; + regs->ARM_pc += 4; + return 0; +} + +static struct undef_hook arm_mrc_hook = { + .instr_mask = 0x0fff0fff, + .instr_val = 0x0e1d0f70, + .cpsr_mask = PSR_T_BIT, + .cpsr_val = 0, + .fn = get_tp_trap, +}; + +static int __init arm_mrc_hook_init(void) +{ + register_undef_hook(&arm_mrc_hook); + return 0; +} + +late_initcall(arm_mrc_hook_init); + +#endif + +/* + * A data abort trap was taken, but we did not handle the instruction. + * Try to abort the user program, or panic if it was the kernel. + */ +asmlinkage void +baddataabort(int code, unsigned long instr, struct pt_regs *regs) +{ + unsigned long addr = instruction_pointer(regs); + +#ifdef CONFIG_DEBUG_USER + if (user_debug & UDBG_BADABORT) { + pr_err("8<--- cut here ---\n"); + pr_err("[%d] %s: bad data abort: code %d instr 0x%08lx\n", + task_pid_nr(current), current->comm, code, instr); + dump_instr(KERN_ERR, regs); + show_pte(KERN_ERR, current->mm, addr); + } +#endif + + arm_notify_die("unknown data abort code", regs, + SIGILL, ILL_ILLOPC, (void __user *)addr, instr, 0); +} + +void __readwrite_bug(const char *fn) +{ + pr_err("%s called, but not implemented\n", fn); + BUG(); +} +EXPORT_SYMBOL(__readwrite_bug); + +void __pte_error(const char *file, int line, pte_t pte) +{ + pr_err("%s:%d: bad pte %08llx.\n", file, line, (long long)pte_val(pte)); +} + +void __pmd_error(const char *file, int line, pmd_t pmd) +{ + pr_err("%s:%d: bad pmd %08llx.\n", file, line, (long long)pmd_val(pmd)); +} + +void __pgd_error(const char *file, int line, pgd_t pgd) +{ + pr_err("%s:%d: bad pgd %08llx.\n", file, line, (long long)pgd_val(pgd)); +} + +asmlinkage void __div0(void) +{ + pr_err("Division by zero in kernel.\n"); + dump_stack(); +} +EXPORT_SYMBOL(__div0); + +void abort(void) +{ + BUG(); + + /* if that doesn't kill us, halt */ + panic("Oops failed to kill thread"); +} + +#ifdef CONFIG_KUSER_HELPERS +static void __init kuser_init(void *vectors) +{ + extern char __kuser_helper_start[], __kuser_helper_end[]; + int kuser_sz = __kuser_helper_end - __kuser_helper_start; + + memcpy(vectors + 0x1000 - kuser_sz, __kuser_helper_start, kuser_sz); + + /* + * vectors + 0xfe0 = __kuser_get_tls + * vectors + 0xfe8 = hardware TLS instruction at 0xffff0fe8 + */ + if (tls_emu || has_tls_reg) + memcpy(vectors + 0xfe0, vectors + 0xfe8, 4); +} +#else +static inline void __init kuser_init(void *vectors) +{ +} +#endif + +#ifndef CONFIG_CPU_V7M +static void copy_from_lma(void *vma, void *lma_start, void *lma_end) +{ + memcpy(vma, lma_start, lma_end - lma_start); +} + +static void flush_vectors(void *vma, size_t offset, size_t size) +{ + unsigned long start = (unsigned long)vma + offset; + unsigned long end = start + size; + + flush_icache_range(start, end); +} + +#ifdef CONFIG_HARDEN_BRANCH_HISTORY +int spectre_bhb_update_vectors(unsigned int method) +{ + extern char __vectors_bhb_bpiall_start[], __vectors_bhb_bpiall_end[]; + extern char __vectors_bhb_loop8_start[], __vectors_bhb_loop8_end[]; + void *vec_start, *vec_end; + + if (system_state >= SYSTEM_FREEING_INITMEM) { + pr_err("CPU%u: Spectre BHB workaround too late - system vulnerable\n", + smp_processor_id()); + return SPECTRE_VULNERABLE; + } + + switch (method) { + case SPECTRE_V2_METHOD_LOOP8: + vec_start = __vectors_bhb_loop8_start; + vec_end = __vectors_bhb_loop8_end; + break; + + case SPECTRE_V2_METHOD_BPIALL: + vec_start = __vectors_bhb_bpiall_start; + vec_end = __vectors_bhb_bpiall_end; + break; + + default: + pr_err("CPU%u: unknown Spectre BHB state %d\n", + smp_processor_id(), method); + return SPECTRE_VULNERABLE; + } + + copy_from_lma(vectors_page, vec_start, vec_end); + flush_vectors(vectors_page, 0, vec_end - vec_start); + + return SPECTRE_MITIGATED; +} +#endif + +void __init early_trap_init(void *vectors_base) +{ + extern char __stubs_start[], __stubs_end[]; + extern char __vectors_start[], __vectors_end[]; + unsigned i; + + vectors_page = vectors_base; + + /* + * Poison the vectors page with an undefined instruction. This + * instruction is chosen to be undefined for both ARM and Thumb + * ISAs. The Thumb version is an undefined instruction with a + * branch back to the undefined instruction. + */ + for (i = 0; i < PAGE_SIZE / sizeof(u32); i++) + ((u32 *)vectors_base)[i] = 0xe7fddef1; + + /* + * Copy the vectors, stubs and kuser helpers (in entry-armv.S) + * into the vector page, mapped at 0xffff0000, and ensure these + * are visible to the instruction stream. + */ + copy_from_lma(vectors_base, __vectors_start, __vectors_end); + copy_from_lma(vectors_base + 0x1000, __stubs_start, __stubs_end); + + kuser_init(vectors_base); + + flush_vectors(vectors_base, 0, PAGE_SIZE * 2); +} +#else /* ifndef CONFIG_CPU_V7M */ +void __init early_trap_init(void *vectors_base) +{ + /* + * on V7-M there is no need to copy the vector table to a dedicated + * memory area. The address is configurable and so a table in the kernel + * image can be used. + */ +} +#endif + +#ifdef CONFIG_VMAP_STACK + +DECLARE_PER_CPU(u8 *, irq_stack_ptr); + +asmlinkage DEFINE_PER_CPU(u8 *, overflow_stack_ptr); + +static int __init allocate_overflow_stacks(void) +{ + u8 *stack; + int cpu; + + for_each_possible_cpu(cpu) { + stack = (u8 *)__get_free_page(GFP_KERNEL); + if (WARN_ON(!stack)) + return -ENOMEM; + per_cpu(overflow_stack_ptr, cpu) = &stack[OVERFLOW_STACK_SIZE]; + } + return 0; +} +early_initcall(allocate_overflow_stacks); + +asmlinkage void handle_bad_stack(struct pt_regs *regs) +{ + unsigned long tsk_stk = (unsigned long)current->stack; +#ifdef CONFIG_IRQSTACKS + unsigned long irq_stk = (unsigned long)raw_cpu_read(irq_stack_ptr); +#endif + unsigned long ovf_stk = (unsigned long)raw_cpu_read(overflow_stack_ptr); + + console_verbose(); + pr_emerg("Insufficient stack space to handle exception!"); + + pr_emerg("Task stack: [0x%08lx..0x%08lx]\n", + tsk_stk, tsk_stk + THREAD_SIZE); +#ifdef CONFIG_IRQSTACKS + pr_emerg("IRQ stack: [0x%08lx..0x%08lx]\n", + irq_stk - THREAD_SIZE, irq_stk); +#endif + pr_emerg("Overflow stack: [0x%08lx..0x%08lx]\n", + ovf_stk - OVERFLOW_STACK_SIZE, ovf_stk); + + die("kernel stack overflow", regs, 0); +} + +#ifndef CONFIG_ARM_LPAE +/* + * Normally, we rely on the logic in do_translation_fault() to update stale PMD + * entries covering the vmalloc space in a task's page tables when it first + * accesses the region in question. Unfortunately, this is not sufficient when + * the task stack resides in the vmalloc region, as do_translation_fault() is a + * C function that needs a stack to run. + * + * So we need to ensure that these PMD entries are up to date *before* the MM + * switch. As we already have some logic in the MM switch path that takes care + * of this, let's trigger it by bumping the counter every time the core vmalloc + * code modifies a PMD entry in the vmalloc region. Use release semantics on + * the store so that other CPUs observing the counter's new value are + * guaranteed to see the updated page table entries as well. + */ +void arch_sync_kernel_mappings(unsigned long start, unsigned long end) +{ + if (start < VMALLOC_END && end > VMALLOC_START) + atomic_inc_return_release(&init_mm.context.vmalloc_seq); +} +#endif +#endif diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c new file mode 100644 index 000000000..2e6aa5dc1 --- /dev/null +++ b/arch/arm/kernel/unwind.c @@ -0,0 +1,597 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * arch/arm/kernel/unwind.c + * + * Copyright (C) 2008 ARM Limited + * + * Stack unwinding support for ARM + * + * An ARM EABI version of gcc is required to generate the unwind + * tables. For information about the structure of the unwind tables, + * see "Exception Handling ABI for the ARM Architecture" at: + * + * http://infocenter.arm.com/help/topic/com.arm.doc.subset.swdev.abi/index.html + */ + +#ifndef __CHECKER__ +#if !defined (__ARM_EABI__) +#warning Your compiler does not have EABI support. +#warning ARM unwind is known to compile only with EABI compilers. +#warning Change compiler or disable ARM_UNWIND option. +#endif +#endif /* __CHECKER__ */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/export.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/spinlock.h> +#include <linux/list.h> + +#include <asm/stacktrace.h> +#include <asm/traps.h> +#include <asm/unwind.h> + +#include "reboot.h" + +/* Dummy functions to avoid linker complaints */ +void __aeabi_unwind_cpp_pr0(void) +{ +}; +EXPORT_SYMBOL(__aeabi_unwind_cpp_pr0); + +void __aeabi_unwind_cpp_pr1(void) +{ +}; +EXPORT_SYMBOL(__aeabi_unwind_cpp_pr1); + +void __aeabi_unwind_cpp_pr2(void) +{ +}; +EXPORT_SYMBOL(__aeabi_unwind_cpp_pr2); + +struct unwind_ctrl_block { + unsigned long vrs[16]; /* virtual register set */ + const unsigned long *insn; /* pointer to the current instructions word */ + unsigned long sp_high; /* highest value of sp allowed */ + unsigned long *lr_addr; /* address of LR value on the stack */ + /* + * 1 : check for stack overflow for each register pop. + * 0 : save overhead if there is plenty of stack remaining. + */ + int check_each_pop; + int entries; /* number of entries left to interpret */ + int byte; /* current byte number in the instructions word */ +}; + +enum regs { +#ifdef CONFIG_THUMB2_KERNEL + FP = 7, +#else + FP = 11, +#endif + SP = 13, + LR = 14, + PC = 15 +}; + +extern const struct unwind_idx __start_unwind_idx[]; +static const struct unwind_idx *__origin_unwind_idx; +extern const struct unwind_idx __stop_unwind_idx[]; + +static DEFINE_RAW_SPINLOCK(unwind_lock); +static LIST_HEAD(unwind_tables); + +/* Convert a prel31 symbol to an absolute address */ +#define prel31_to_addr(ptr) \ +({ \ + /* sign-extend to 32 bits */ \ + long offset = (((long)*(ptr)) << 1) >> 1; \ + (unsigned long)(ptr) + offset; \ +}) + +/* + * Binary search in the unwind index. The entries are + * guaranteed to be sorted in ascending order by the linker. + * + * start = first entry + * origin = first entry with positive offset (or stop if there is no such entry) + * stop - 1 = last entry + */ +static const struct unwind_idx *search_index(unsigned long addr, + const struct unwind_idx *start, + const struct unwind_idx *origin, + const struct unwind_idx *stop) +{ + unsigned long addr_prel31; + + pr_debug("%s(%08lx, %p, %p, %p)\n", + __func__, addr, start, origin, stop); + + /* + * only search in the section with the matching sign. This way the + * prel31 numbers can be compared as unsigned longs. + */ + if (addr < (unsigned long)start) + /* negative offsets: [start; origin) */ + stop = origin; + else + /* positive offsets: [origin; stop) */ + start = origin; + + /* prel31 for address relavive to start */ + addr_prel31 = (addr - (unsigned long)start) & 0x7fffffff; + + while (start < stop - 1) { + const struct unwind_idx *mid = start + ((stop - start) >> 1); + + /* + * As addr_prel31 is relative to start an offset is needed to + * make it relative to mid. + */ + if (addr_prel31 - ((unsigned long)mid - (unsigned long)start) < + mid->addr_offset) + stop = mid; + else { + /* keep addr_prel31 relative to start */ + addr_prel31 -= ((unsigned long)mid - + (unsigned long)start); + start = mid; + } + } + + if (likely(start->addr_offset <= addr_prel31)) + return start; + else { + pr_warn("unwind: Unknown symbol address %08lx\n", addr); + return NULL; + } +} + +static const struct unwind_idx *unwind_find_origin( + const struct unwind_idx *start, const struct unwind_idx *stop) +{ + pr_debug("%s(%p, %p)\n", __func__, start, stop); + while (start < stop) { + const struct unwind_idx *mid = start + ((stop - start) >> 1); + + if (mid->addr_offset >= 0x40000000) + /* negative offset */ + start = mid + 1; + else + /* positive offset */ + stop = mid; + } + pr_debug("%s -> %p\n", __func__, stop); + return stop; +} + +static const struct unwind_idx *unwind_find_idx(unsigned long addr) +{ + const struct unwind_idx *idx = NULL; + unsigned long flags; + + pr_debug("%s(%08lx)\n", __func__, addr); + + if (core_kernel_text(addr)) { + if (unlikely(!__origin_unwind_idx)) + __origin_unwind_idx = + unwind_find_origin(__start_unwind_idx, + __stop_unwind_idx); + + /* main unwind table */ + idx = search_index(addr, __start_unwind_idx, + __origin_unwind_idx, + __stop_unwind_idx); + } else { + /* module unwind tables */ + struct unwind_table *table; + + raw_spin_lock_irqsave(&unwind_lock, flags); + list_for_each_entry(table, &unwind_tables, list) { + if (addr >= table->begin_addr && + addr < table->end_addr) { + idx = search_index(addr, table->start, + table->origin, + table->stop); + /* Move-to-front to exploit common traces */ + list_move(&table->list, &unwind_tables); + break; + } + } + raw_spin_unlock_irqrestore(&unwind_lock, flags); + } + + pr_debug("%s: idx = %p\n", __func__, idx); + return idx; +} + +static unsigned long unwind_get_byte(struct unwind_ctrl_block *ctrl) +{ + unsigned long ret; + + if (ctrl->entries <= 0) { + pr_warn("unwind: Corrupt unwind table\n"); + return 0; + } + + ret = (*ctrl->insn >> (ctrl->byte * 8)) & 0xff; + + if (ctrl->byte == 0) { + ctrl->insn++; + ctrl->entries--; + ctrl->byte = 3; + } else + ctrl->byte--; + + return ret; +} + +/* Before poping a register check whether it is feasible or not */ +static int unwind_pop_register(struct unwind_ctrl_block *ctrl, + unsigned long **vsp, unsigned int reg) +{ + if (unlikely(ctrl->check_each_pop)) + if (*vsp >= (unsigned long *)ctrl->sp_high) + return -URC_FAILURE; + + /* Use READ_ONCE_NOCHECK here to avoid this memory access + * from being tracked by KASAN. + */ + ctrl->vrs[reg] = READ_ONCE_NOCHECK(*(*vsp)); + if (reg == 14) + ctrl->lr_addr = *vsp; + (*vsp)++; + return URC_OK; +} + +/* Helper functions to execute the instructions */ +static int unwind_exec_pop_subset_r4_to_r13(struct unwind_ctrl_block *ctrl, + unsigned long mask) +{ + unsigned long *vsp = (unsigned long *)ctrl->vrs[SP]; + int load_sp, reg = 4; + + load_sp = mask & (1 << (13 - 4)); + while (mask) { + if (mask & 1) + if (unwind_pop_register(ctrl, &vsp, reg)) + return -URC_FAILURE; + mask >>= 1; + reg++; + } + if (!load_sp) { + ctrl->vrs[SP] = (unsigned long)vsp; + } + + return URC_OK; +} + +static int unwind_exec_pop_r4_to_rN(struct unwind_ctrl_block *ctrl, + unsigned long insn) +{ + unsigned long *vsp = (unsigned long *)ctrl->vrs[SP]; + int reg; + + /* pop R4-R[4+bbb] */ + for (reg = 4; reg <= 4 + (insn & 7); reg++) + if (unwind_pop_register(ctrl, &vsp, reg)) + return -URC_FAILURE; + + if (insn & 0x8) + if (unwind_pop_register(ctrl, &vsp, 14)) + return -URC_FAILURE; + + ctrl->vrs[SP] = (unsigned long)vsp; + + return URC_OK; +} + +static int unwind_exec_pop_subset_r0_to_r3(struct unwind_ctrl_block *ctrl, + unsigned long mask) +{ + unsigned long *vsp = (unsigned long *)ctrl->vrs[SP]; + int reg = 0; + + /* pop R0-R3 according to mask */ + while (mask) { + if (mask & 1) + if (unwind_pop_register(ctrl, &vsp, reg)) + return -URC_FAILURE; + mask >>= 1; + reg++; + } + ctrl->vrs[SP] = (unsigned long)vsp; + + return URC_OK; +} + +static unsigned long unwind_decode_uleb128(struct unwind_ctrl_block *ctrl) +{ + unsigned long bytes = 0; + unsigned long insn; + unsigned long result = 0; + + /* + * unwind_get_byte() will advance `ctrl` one instruction at a time, so + * loop until we get an instruction byte where bit 7 is not set. + * + * Note: This decodes a maximum of 4 bytes to output 28 bits data where + * max is 0xfffffff: that will cover a vsp increment of 1073742336, hence + * it is sufficient for unwinding the stack. + */ + do { + insn = unwind_get_byte(ctrl); + result |= (insn & 0x7f) << (bytes * 7); + bytes++; + } while (!!(insn & 0x80) && (bytes != sizeof(result))); + + return result; +} + +/* + * Execute the current unwind instruction. + */ +static int unwind_exec_insn(struct unwind_ctrl_block *ctrl) +{ + unsigned long insn = unwind_get_byte(ctrl); + int ret = URC_OK; + + pr_debug("%s: insn = %08lx\n", __func__, insn); + + if ((insn & 0xc0) == 0x00) + ctrl->vrs[SP] += ((insn & 0x3f) << 2) + 4; + else if ((insn & 0xc0) == 0x40) { + ctrl->vrs[SP] -= ((insn & 0x3f) << 2) + 4; + } else if ((insn & 0xf0) == 0x80) { + unsigned long mask; + + insn = (insn << 8) | unwind_get_byte(ctrl); + mask = insn & 0x0fff; + if (mask == 0) { + pr_warn("unwind: 'Refuse to unwind' instruction %04lx\n", + insn); + return -URC_FAILURE; + } + + ret = unwind_exec_pop_subset_r4_to_r13(ctrl, mask); + if (ret) + goto error; + } else if ((insn & 0xf0) == 0x90 && + (insn & 0x0d) != 0x0d) { + ctrl->vrs[SP] = ctrl->vrs[insn & 0x0f]; + } else if ((insn & 0xf0) == 0xa0) { + ret = unwind_exec_pop_r4_to_rN(ctrl, insn); + if (ret) + goto error; + } else if (insn == 0xb0) { + if (ctrl->vrs[PC] == 0) + ctrl->vrs[PC] = ctrl->vrs[LR]; + /* no further processing */ + ctrl->entries = 0; + } else if (insn == 0xb1) { + unsigned long mask = unwind_get_byte(ctrl); + + if (mask == 0 || mask & 0xf0) { + pr_warn("unwind: Spare encoding %04lx\n", + (insn << 8) | mask); + return -URC_FAILURE; + } + + ret = unwind_exec_pop_subset_r0_to_r3(ctrl, mask); + if (ret) + goto error; + } else if (insn == 0xb2) { + unsigned long uleb128 = unwind_decode_uleb128(ctrl); + + ctrl->vrs[SP] += 0x204 + (uleb128 << 2); + } else { + pr_warn("unwind: Unhandled instruction %02lx\n", insn); + return -URC_FAILURE; + } + + pr_debug("%s: fp = %08lx sp = %08lx lr = %08lx pc = %08lx\n", __func__, + ctrl->vrs[FP], ctrl->vrs[SP], ctrl->vrs[LR], ctrl->vrs[PC]); + +error: + return ret; +} + +/* + * Unwind a single frame starting with *sp for the symbol at *pc. It + * updates the *pc and *sp with the new values. + */ +int unwind_frame(struct stackframe *frame) +{ + const struct unwind_idx *idx; + struct unwind_ctrl_block ctrl; + unsigned long sp_low; + + /* store the highest address on the stack to avoid crossing it*/ + sp_low = frame->sp; + ctrl.sp_high = ALIGN(sp_low - THREAD_SIZE, THREAD_ALIGN) + + THREAD_SIZE; + + pr_debug("%s(pc = %08lx lr = %08lx sp = %08lx)\n", __func__, + frame->pc, frame->lr, frame->sp); + + idx = unwind_find_idx(frame->pc); + if (!idx) { + if (frame->pc && kernel_text_address(frame->pc)) + pr_warn("unwind: Index not found %08lx\n", frame->pc); + return -URC_FAILURE; + } + + ctrl.vrs[FP] = frame->fp; + ctrl.vrs[SP] = frame->sp; + ctrl.vrs[LR] = frame->lr; + ctrl.vrs[PC] = 0; + + if (idx->insn == 1) + /* can't unwind */ + return -URC_FAILURE; + else if (frame->pc == prel31_to_addr(&idx->addr_offset)) { + /* + * Unwinding is tricky when we're halfway through the prologue, + * since the stack frame that the unwinder expects may not be + * fully set up yet. However, one thing we do know for sure is + * that if we are unwinding from the very first instruction of + * a function, we are still effectively in the stack frame of + * the caller, and the unwind info has no relevance yet. + */ + if (frame->pc == frame->lr) + return -URC_FAILURE; + frame->pc = frame->lr; + return URC_OK; + } else if ((idx->insn & 0x80000000) == 0) + /* prel31 to the unwind table */ + ctrl.insn = (unsigned long *)prel31_to_addr(&idx->insn); + else if ((idx->insn & 0xff000000) == 0x80000000) + /* only personality routine 0 supported in the index */ + ctrl.insn = &idx->insn; + else { + pr_warn("unwind: Unsupported personality routine %08lx in the index at %p\n", + idx->insn, idx); + return -URC_FAILURE; + } + + /* check the personality routine */ + if ((*ctrl.insn & 0xff000000) == 0x80000000) { + ctrl.byte = 2; + ctrl.entries = 1; + } else if ((*ctrl.insn & 0xff000000) == 0x81000000) { + ctrl.byte = 1; + ctrl.entries = 1 + ((*ctrl.insn & 0x00ff0000) >> 16); + } else { + pr_warn("unwind: Unsupported personality routine %08lx at %p\n", + *ctrl.insn, ctrl.insn); + return -URC_FAILURE; + } + + ctrl.check_each_pop = 0; + + if (prel31_to_addr(&idx->addr_offset) == (u32)&call_with_stack) { + /* + * call_with_stack() is the only place where we permit SP to + * jump from one stack to another, and since we know it is + * guaranteed to happen, set up the SP bounds accordingly. + */ + sp_low = frame->fp; + ctrl.sp_high = ALIGN(frame->fp, THREAD_SIZE); + } + + while (ctrl.entries > 0) { + int urc; + if ((ctrl.sp_high - ctrl.vrs[SP]) < sizeof(ctrl.vrs)) + ctrl.check_each_pop = 1; + urc = unwind_exec_insn(&ctrl); + if (urc < 0) + return urc; + if (ctrl.vrs[SP] < sp_low || ctrl.vrs[SP] > ctrl.sp_high) + return -URC_FAILURE; + } + + if (ctrl.vrs[PC] == 0) + ctrl.vrs[PC] = ctrl.vrs[LR]; + + /* check for infinite loop */ + if (frame->pc == ctrl.vrs[PC] && frame->sp == ctrl.vrs[SP]) + return -URC_FAILURE; + + frame->fp = ctrl.vrs[FP]; + frame->sp = ctrl.vrs[SP]; + frame->lr = ctrl.vrs[LR]; + frame->pc = ctrl.vrs[PC]; + frame->lr_addr = ctrl.lr_addr; + + return URC_OK; +} + +void unwind_backtrace(struct pt_regs *regs, struct task_struct *tsk, + const char *loglvl) +{ + struct stackframe frame; + + pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); + + if (!tsk) + tsk = current; + + if (regs) { + arm_get_current_stackframe(regs, &frame); + /* PC might be corrupted, use LR in that case. */ + if (!kernel_text_address(regs->ARM_pc)) + frame.pc = regs->ARM_lr; + } else if (tsk == current) { + frame.fp = (unsigned long)__builtin_frame_address(0); + frame.sp = current_stack_pointer; + frame.lr = (unsigned long)__builtin_return_address(0); + /* We are saving the stack and execution state at this + * point, so we should ensure that frame.pc is within + * this block of code. + */ +here: + frame.pc = (unsigned long)&&here; + } else { + /* task blocked in __switch_to */ + frame.fp = thread_saved_fp(tsk); + frame.sp = thread_saved_sp(tsk); + /* + * The function calling __switch_to cannot be a leaf function + * so LR is recovered from the stack. + */ + frame.lr = 0; + frame.pc = thread_saved_pc(tsk); + } + + while (1) { + int urc; + unsigned long where = frame.pc; + + urc = unwind_frame(&frame); + if (urc < 0) + break; + dump_backtrace_entry(where, frame.pc, frame.sp - 4, loglvl); + } +} + +struct unwind_table *unwind_table_add(unsigned long start, unsigned long size, + unsigned long text_addr, + unsigned long text_size) +{ + unsigned long flags; + struct unwind_table *tab = kmalloc(sizeof(*tab), GFP_KERNEL); + + pr_debug("%s(%08lx, %08lx, %08lx, %08lx)\n", __func__, start, size, + text_addr, text_size); + + if (!tab) + return tab; + + tab->start = (const struct unwind_idx *)start; + tab->stop = (const struct unwind_idx *)(start + size); + tab->origin = unwind_find_origin(tab->start, tab->stop); + tab->begin_addr = text_addr; + tab->end_addr = text_addr + text_size; + + raw_spin_lock_irqsave(&unwind_lock, flags); + list_add_tail(&tab->list, &unwind_tables); + raw_spin_unlock_irqrestore(&unwind_lock, flags); + + return tab; +} + +void unwind_table_del(struct unwind_table *tab) +{ + unsigned long flags; + + if (!tab) + return; + + raw_spin_lock_irqsave(&unwind_lock, flags); + list_del(&tab->list); + raw_spin_unlock_irqrestore(&unwind_lock, flags); + + kfree(tab); +} diff --git a/arch/arm/kernel/v7m.c b/arch/arm/kernel/v7m.c new file mode 100644 index 000000000..094c5c59f --- /dev/null +++ b/arch/arm/kernel/v7m.c @@ -0,0 +1,16 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (C) 2013 Uwe Kleine-Koenig for Pengutronix + */ +#include <linux/io.h> +#include <linux/reboot.h> +#include <asm/barrier.h> +#include <asm/v7m.h> + +void armv7m_restart(enum reboot_mode mode, const char *cmd) +{ + dsb(); + __raw_writel(V7M_SCB_AIRCR_VECTKEY | V7M_SCB_AIRCR_SYSRESETREQ, + BASEADDR_V7M_SCB + V7M_SCB_AIRCR); + dsb(); +} diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c new file mode 100644 index 000000000..3408269d1 --- /dev/null +++ b/arch/arm/kernel/vdso.c @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Adapted from arm64 version. + * + * Copyright (C) 2012 ARM Limited + * Copyright (C) 2015 Mentor Graphics Corporation. + */ + +#include <linux/cache.h> +#include <linux/elf.h> +#include <linux/err.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/of.h> +#include <linux/printk.h> +#include <linux/slab.h> +#include <linux/timekeeper_internal.h> +#include <linux/vmalloc.h> +#include <asm/arch_timer.h> +#include <asm/barrier.h> +#include <asm/cacheflush.h> +#include <asm/page.h> +#include <asm/vdso.h> +#include <asm/vdso_datapage.h> +#include <clocksource/arm_arch_timer.h> +#include <vdso/helpers.h> +#include <vdso/vsyscall.h> + +#define MAX_SYMNAME 64 + +static struct page **vdso_text_pagelist; + +extern char vdso_start[], vdso_end[]; + +/* Total number of pages needed for the data and text portions of the VDSO. */ +unsigned int vdso_total_pages __ro_after_init; + +/* + * The VDSO data page. + */ +static union vdso_data_store vdso_data_store __page_aligned_data; +struct vdso_data *vdso_data = vdso_data_store.data; + +static struct page *vdso_data_page __ro_after_init; +static const struct vm_special_mapping vdso_data_mapping = { + .name = "[vvar]", + .pages = &vdso_data_page, +}; + +static int vdso_mremap(const struct vm_special_mapping *sm, + struct vm_area_struct *new_vma) +{ + current->mm->context.vdso = new_vma->vm_start; + + return 0; +} + +static struct vm_special_mapping vdso_text_mapping __ro_after_init = { + .name = "[vdso]", + .mremap = vdso_mremap, +}; + +struct elfinfo { + Elf32_Ehdr *hdr; /* ptr to ELF */ + Elf32_Sym *dynsym; /* ptr to .dynsym section */ + unsigned long dynsymsize; /* size of .dynsym section */ + char *dynstr; /* ptr to .dynstr section */ +}; + +/* Cached result of boot-time check for whether the arch timer exists, + * and if so, whether the virtual counter is useable. + */ +bool cntvct_ok __ro_after_init; + +static bool __init cntvct_functional(void) +{ + struct device_node *np; + bool ret = false; + + if (!IS_ENABLED(CONFIG_ARM_ARCH_TIMER)) + goto out; + + /* The arm_arch_timer core should export + * arch_timer_use_virtual or similar so we don't have to do + * this. + */ + np = of_find_compatible_node(NULL, NULL, "arm,armv7-timer"); + if (!np) + np = of_find_compatible_node(NULL, NULL, "arm,armv8-timer"); + if (!np) + goto out_put; + + if (of_property_read_bool(np, "arm,cpu-registers-not-fw-configured")) + goto out_put; + + ret = true; + +out_put: + of_node_put(np); +out: + return ret; +} + +static void * __init find_section(Elf32_Ehdr *ehdr, const char *name, + unsigned long *size) +{ + Elf32_Shdr *sechdrs; + unsigned int i; + char *secnames; + + /* Grab section headers and strings so we can tell who is who */ + sechdrs = (void *)ehdr + ehdr->e_shoff; + secnames = (void *)ehdr + sechdrs[ehdr->e_shstrndx].sh_offset; + + /* Find the section they want */ + for (i = 1; i < ehdr->e_shnum; i++) { + if (strcmp(secnames + sechdrs[i].sh_name, name) == 0) { + if (size) + *size = sechdrs[i].sh_size; + return (void *)ehdr + sechdrs[i].sh_offset; + } + } + + if (size) + *size = 0; + return NULL; +} + +static Elf32_Sym * __init find_symbol(struct elfinfo *lib, const char *symname) +{ + unsigned int i; + + for (i = 0; i < (lib->dynsymsize / sizeof(Elf32_Sym)); i++) { + char name[MAX_SYMNAME], *c; + + if (lib->dynsym[i].st_name == 0) + continue; + strlcpy(name, lib->dynstr + lib->dynsym[i].st_name, + MAX_SYMNAME); + c = strchr(name, '@'); + if (c) + *c = 0; + if (strcmp(symname, name) == 0) + return &lib->dynsym[i]; + } + return NULL; +} + +static void __init vdso_nullpatch_one(struct elfinfo *lib, const char *symname) +{ + Elf32_Sym *sym; + + sym = find_symbol(lib, symname); + if (!sym) + return; + + sym->st_name = 0; +} + +static void __init patch_vdso(void *ehdr) +{ + struct elfinfo einfo; + + einfo = (struct elfinfo) { + .hdr = ehdr, + }; + + einfo.dynsym = find_section(einfo.hdr, ".dynsym", &einfo.dynsymsize); + einfo.dynstr = find_section(einfo.hdr, ".dynstr", NULL); + + /* If the virtual counter is absent or non-functional we don't + * want programs to incur the slight additional overhead of + * dispatching through the VDSO only to fall back to syscalls. + */ + if (!cntvct_ok) { + vdso_nullpatch_one(&einfo, "__vdso_gettimeofday"); + vdso_nullpatch_one(&einfo, "__vdso_clock_gettime"); + vdso_nullpatch_one(&einfo, "__vdso_clock_gettime64"); + } +} + +static int __init vdso_init(void) +{ + unsigned int text_pages; + int i; + + if (memcmp(vdso_start, "\177ELF", 4)) { + pr_err("VDSO is not a valid ELF object!\n"); + return -ENOEXEC; + } + + text_pages = (vdso_end - vdso_start) >> PAGE_SHIFT; + + /* Allocate the VDSO text pagelist */ + vdso_text_pagelist = kcalloc(text_pages, sizeof(struct page *), + GFP_KERNEL); + if (vdso_text_pagelist == NULL) + return -ENOMEM; + + /* Grab the VDSO data page. */ + vdso_data_page = virt_to_page(vdso_data); + + /* Grab the VDSO text pages. */ + for (i = 0; i < text_pages; i++) { + struct page *page; + + page = virt_to_page(vdso_start + i * PAGE_SIZE); + vdso_text_pagelist[i] = page; + } + + vdso_text_mapping.pages = vdso_text_pagelist; + + vdso_total_pages = 1; /* for the data/vvar page */ + vdso_total_pages += text_pages; + + cntvct_ok = cntvct_functional(); + + patch_vdso(vdso_start); + + return 0; +} +arch_initcall(vdso_init); + +static int install_vvar(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma; + + vma = _install_special_mapping(mm, addr, PAGE_SIZE, + VM_READ | VM_MAYREAD, + &vdso_data_mapping); + + return PTR_ERR_OR_ZERO(vma); +} + +/* assumes mmap_lock is write-locked */ +void arm_install_vdso(struct mm_struct *mm, unsigned long addr) +{ + struct vm_area_struct *vma; + unsigned long len; + + mm->context.vdso = 0; + + if (vdso_text_pagelist == NULL) + return; + + if (install_vvar(mm, addr)) + return; + + /* Account for vvar page. */ + addr += PAGE_SIZE; + len = (vdso_total_pages - 1) << PAGE_SHIFT; + + vma = _install_special_mapping(mm, addr, len, + VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC, + &vdso_text_mapping); + + if (!IS_ERR(vma)) + mm->context.vdso = addr; +} + diff --git a/arch/arm/kernel/vmlinux-xip.lds.S b/arch/arm/kernel/vmlinux-xip.lds.S new file mode 100644 index 000000000..76678732c --- /dev/null +++ b/arch/arm/kernel/vmlinux-xip.lds.S @@ -0,0 +1,197 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* ld script to make ARM Linux kernel + * taken from the i386 version by Russell King + * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz> + */ + +/* No __ro_after_init data in the .rodata section - which will always be ro */ +#define RO_AFTER_INIT_DATA + +#include <linux/sizes.h> + +#include <asm/vmlinux.lds.h> +#include <asm/cache.h> +#include <asm/thread_info.h> +#include <asm/memory.h> +#include <asm/mpu.h> +#include <asm/page.h> + +OUTPUT_ARCH(arm) +ENTRY(stext) + +#ifndef __ARMEB__ +jiffies = jiffies_64; +#else +jiffies = jiffies_64 + 4; +#endif + +SECTIONS +{ + /* + * XXX: The linker does not define how output sections are + * assigned to input sections when there are multiple statements + * matching the same input section name. There is no documented + * order of matching. + * + * unwind exit sections must be discarded before the rest of the + * unwind sections get included. + */ + /DISCARD/ : { + ARM_DISCARD + *(.alt.smp.init) + *(.pv_table) +#ifndef CONFIG_ARM_UNWIND + *(.ARM.exidx) *(.ARM.exidx.*) + *(.ARM.extab) *(.ARM.extab.*) +#endif + } + + . = XIP_VIRT_ADDR(CONFIG_XIP_PHYS_ADDR); + _xiprom = .; /* XIP ROM area to be mapped */ + + .head.text : { + _text = .; + HEAD_TEXT + } + + .text : { /* Real text segment */ + _stext = .; /* Text and read-only data */ + ARM_TEXT + } + + RO_DATA(PAGE_SIZE) + + . = ALIGN(4); + __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { + __start___ex_table = .; + ARM_MMU_KEEP(*(__ex_table)) + __stop___ex_table = .; + } + +#ifdef CONFIG_ARM_UNWIND + ARM_UNWIND_SECTIONS +#endif + + _etext = .; /* End of text and rodata section */ + + ARM_VECTORS + INIT_TEXT_SECTION(8) + .exit.text : { + ARM_EXIT_KEEP(EXIT_TEXT) + } + .init.proc.info : { + ARM_CPU_DISCARD(PROC_INFO) + } + .init.arch.info : { + __arch_info_begin = .; + *(.arch.info.init) + __arch_info_end = .; + } + .init.tagtable : { + __tagtable_begin = .; + *(.taglist.init) + __tagtable_end = .; + } + .init.rodata : { + INIT_SETUP(16) + INIT_CALLS + CON_INITCALL + INIT_RAM_FS + } + +#ifdef CONFIG_ARM_MPU + . = ALIGN(SZ_128K); +#endif + _exiprom = .; /* End of XIP ROM area */ + +/* + * From this point, stuff is considered writable and will be copied to RAM + */ + __data_loc = ALIGN(4); /* location in file */ + . = PAGE_OFFSET + TEXT_OFFSET; /* location in memory */ +#undef LOAD_OFFSET +#define LOAD_OFFSET (PAGE_OFFSET + TEXT_OFFSET - __data_loc) + + . = ALIGN(THREAD_SIZE); + _sdata = .; + RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE) + .data.ro_after_init : AT(ADDR(.data.ro_after_init) - LOAD_OFFSET) { + *(.data..ro_after_init) + } + _edata = .; + + . = ALIGN(PAGE_SIZE); + __init_begin = .; + .init.data : AT(ADDR(.init.data) - LOAD_OFFSET) { + INIT_DATA + } + .exit.data : AT(ADDR(.exit.data) - LOAD_OFFSET) { + ARM_EXIT_KEEP(EXIT_DATA) + } +#ifdef CONFIG_SMP + PERCPU_SECTION(L1_CACHE_BYTES) +#endif + +#ifdef CONFIG_HAVE_TCM + ARM_TCM +#endif + + /* + * End of copied data. We need a dummy section to get its LMA. + * Also located before final ALIGN() as trailing padding is not stored + * in the resulting binary file and useless to copy. + */ + .data.endmark : AT(ADDR(.data.endmark) - LOAD_OFFSET) { } + _edata_loc = LOADADDR(.data.endmark); + + . = ALIGN(PAGE_SIZE); + __init_end = .; + + BSS_SECTION(0, 0, 8) +#ifdef CONFIG_ARM_MPU + . = ALIGN(PMSAv8_MINALIGN); +#endif + _end = .; + + STABS_DEBUG + DWARF_DEBUG + ARM_DETAILS + + ARM_ASSERTS +} + +/* + * These must never be empty + * If you have to comment these two assert statements out, your + * binutils is too old (for other reasons as well) + */ +ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support") +#ifndef CONFIG_COMPILE_TEST +ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined") +#endif + +#ifdef CONFIG_XIP_DEFLATED_DATA +/* + * The .bss is used as a stack area for __inflate_kernel_data() whose stack + * frame is 9568 bytes. Make sure it has extra room left. + */ +ASSERT((_end - __bss_start) >= 12288, ".bss too small for CONFIG_XIP_DEFLATED_DATA") +#endif + +#if defined(CONFIG_ARM_MPU) && !defined(CONFIG_COMPILE_TEST) +/* + * Due to PMSAv7 restriction on base address and size we have to + * enforce minimal alignment restrictions. It was seen that weaker + * alignment restriction on _xiprom will likely force XIP address + * space spawns multiple MPU regions thus it is likely we run in + * situation when we are reprogramming MPU region we run on with + * something which doesn't cover reprogramming code itself, so as soon + * as we update MPU settings we'd immediately try to execute straight + * from background region which is XN. + * It seem that alignment in 1M should suit most users. + * _exiprom is aligned as 1/8 of 1M so can be covered by subregion + * disable + */ +ASSERT(!(_xiprom & (SZ_1M - 1)), "XIP start address may cause MPU programming issues") +ASSERT(!(_exiprom & (SZ_128K - 1)), "XIP end address may cause MPU programming issues") +#endif diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S new file mode 100644 index 000000000..aa12b65a7 --- /dev/null +++ b/arch/arm/kernel/vmlinux.lds.S @@ -0,0 +1,181 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* ld script to make ARM Linux kernel + * taken from the i386 version by Russell King + * Written by Martin Mares <mj@atrey.karlin.mff.cuni.cz> + */ + +#ifdef CONFIG_XIP_KERNEL +#include "vmlinux-xip.lds.S" +#else + +#include <linux/pgtable.h> +#include <asm/vmlinux.lds.h> +#include <asm/cache.h> +#include <asm/thread_info.h> +#include <asm/memory.h> +#include <asm/mpu.h> +#include <asm/page.h> + +OUTPUT_ARCH(arm) +ENTRY(stext) + +#ifndef __ARMEB__ +jiffies = jiffies_64; +#else +jiffies = jiffies_64 + 4; +#endif + +SECTIONS +{ + /* + * XXX: The linker does not define how output sections are + * assigned to input sections when there are multiple statements + * matching the same input section name. There is no documented + * order of matching. + * + * unwind exit sections must be discarded before the rest of the + * unwind sections get included. + */ + /DISCARD/ : { + ARM_DISCARD +#ifndef CONFIG_SMP_ON_UP + *(.alt.smp.init) +#endif +#ifndef CONFIG_ARM_UNWIND + *(.ARM.exidx) *(.ARM.exidx.*) + *(.ARM.extab) *(.ARM.extab.*) +#endif + } + + . = KERNEL_OFFSET + TEXT_OFFSET; + .head.text : { + _text = .; + HEAD_TEXT + } + +#ifdef CONFIG_STRICT_KERNEL_RWX + . = ALIGN(1<<SECTION_SHIFT); +#endif + +#ifdef CONFIG_ARM_MPU + . = ALIGN(PMSAv8_MINALIGN); +#endif + .text : { /* Real text segment */ + _stext = .; /* Text and read-only data */ + ARM_TEXT + } + +#ifdef CONFIG_DEBUG_ALIGN_RODATA + . = ALIGN(1<<SECTION_SHIFT); +#endif + _etext = .; /* End of text section */ + + RO_DATA(PAGE_SIZE) + + . = ALIGN(4); + __ex_table : AT(ADDR(__ex_table) - LOAD_OFFSET) { + __start___ex_table = .; + ARM_MMU_KEEP(*(__ex_table)) + __stop___ex_table = .; + } + +#ifdef CONFIG_ARM_UNWIND + ARM_UNWIND_SECTIONS +#endif + +#ifdef CONFIG_STRICT_KERNEL_RWX + . = ALIGN(1<<SECTION_SHIFT); +#else + . = ALIGN(PAGE_SIZE); +#endif + __init_begin = .; + + ARM_VECTORS + INIT_TEXT_SECTION(8) + .exit.text : { + ARM_EXIT_KEEP(EXIT_TEXT) + } + .init.proc.info : { + ARM_CPU_DISCARD(PROC_INFO) + } + .init.arch.info : { + __arch_info_begin = .; + *(.arch.info.init) + __arch_info_end = .; + } + .init.tagtable : { + __tagtable_begin = .; + *(.taglist.init) + __tagtable_end = .; + } +#ifdef CONFIG_SMP_ON_UP + .init.smpalt : { + __smpalt_begin = .; + *(.alt.smp.init) + __smpalt_end = .; + } +#endif + .init.pv_table : { + __pv_table_begin = .; + *(.pv_table) + __pv_table_end = .; + } + + INIT_DATA_SECTION(16) + + .exit.data : { + ARM_EXIT_KEEP(EXIT_DATA) + } + +#ifdef CONFIG_SMP + PERCPU_SECTION(L1_CACHE_BYTES) +#endif + +#ifdef CONFIG_HAVE_TCM + ARM_TCM +#endif + +#ifdef CONFIG_STRICT_KERNEL_RWX + . = ALIGN(1<<SECTION_SHIFT); +#else + . = ALIGN(THREAD_ALIGN); +#endif + __init_end = .; + + _sdata = .; + RW_DATA(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN) + _edata = .; + + BSS_SECTION(0, 0, 0) +#ifdef CONFIG_ARM_MPU + . = ALIGN(PMSAv8_MINALIGN); +#endif + _end = .; + + STABS_DEBUG + DWARF_DEBUG + ARM_DETAILS + + ARM_ASSERTS +} + +#ifdef CONFIG_STRICT_KERNEL_RWX +/* + * Without CONFIG_DEBUG_ALIGN_RODATA, __start_rodata_section_aligned will + * be the first section-aligned location after __start_rodata. Otherwise, + * it will be equal to __start_rodata. + */ +__start_rodata_section_aligned = ALIGN(__start_rodata, 1 << SECTION_SHIFT); +#endif + +/* + * These must never be empty + * If you have to comment these two assert statements out, your + * binutils is too old (for other reasons as well) + */ +ASSERT((__proc_info_end - __proc_info_begin), "missing CPU support") +#ifndef CONFIG_COMPILE_TEST +ASSERT((__arch_info_end - __arch_info_begin), "no machine record defined") +#endif + +#endif /* CONFIG_XIP_KERNEL */ diff --git a/arch/arm/kernel/xscale-cp0.c b/arch/arm/kernel/xscale-cp0.c new file mode 100644 index 000000000..ed4f6e776 --- /dev/null +++ b/arch/arm/kernel/xscale-cp0.c @@ -0,0 +1,181 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * linux/arch/arm/kernel/xscale-cp0.c + * + * XScale DSP and iWMMXt coprocessor context switching and handling + */ + +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/signal.h> +#include <linux/sched.h> +#include <linux/init.h> +#include <linux/io.h> +#include <asm/thread_notify.h> +#include <asm/cputype.h> + +asm(" .arch armv5te\n"); + +static inline void dsp_save_state(u32 *state) +{ + __asm__ __volatile__ ( + "mrrc p0, 0, %0, %1, c0\n" + : "=r" (state[0]), "=r" (state[1])); +} + +static inline void dsp_load_state(u32 *state) +{ + __asm__ __volatile__ ( + "mcrr p0, 0, %0, %1, c0\n" + : : "r" (state[0]), "r" (state[1])); +} + +static int dsp_do(struct notifier_block *self, unsigned long cmd, void *t) +{ + struct thread_info *thread = t; + + switch (cmd) { + case THREAD_NOTIFY_FLUSH: + thread->cpu_context.extra[0] = 0; + thread->cpu_context.extra[1] = 0; + break; + + case THREAD_NOTIFY_SWITCH: + dsp_save_state(current_thread_info()->cpu_context.extra); + dsp_load_state(thread->cpu_context.extra); + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block dsp_notifier_block = { + .notifier_call = dsp_do, +}; + + +#ifdef CONFIG_IWMMXT +static int iwmmxt_do(struct notifier_block *self, unsigned long cmd, void *t) +{ + struct thread_info *thread = t; + + switch (cmd) { + case THREAD_NOTIFY_FLUSH: + /* + * flush_thread() zeroes thread->fpstate, so no need + * to do anything here. + * + * FALLTHROUGH: Ensure we don't try to overwrite our newly + * initialised state information on the first fault. + */ + + case THREAD_NOTIFY_EXIT: + iwmmxt_task_release(thread); + break; + + case THREAD_NOTIFY_SWITCH: + iwmmxt_task_switch(thread); + break; + } + + return NOTIFY_DONE; +} + +static struct notifier_block iwmmxt_notifier_block = { + .notifier_call = iwmmxt_do, +}; +#endif + + +static u32 __init xscale_cp_access_read(void) +{ + u32 value; + + __asm__ __volatile__ ( + "mrc p15, 0, %0, c15, c1, 0\n\t" + : "=r" (value)); + + return value; +} + +static void __init xscale_cp_access_write(u32 value) +{ + u32 temp; + + __asm__ __volatile__ ( + "mcr p15, 0, %1, c15, c1, 0\n\t" + "mrc p15, 0, %0, c15, c1, 0\n\t" + "mov %0, %0\n\t" + "sub pc, pc, #4\n\t" + : "=r" (temp) : "r" (value)); +} + +/* + * Detect whether we have a MAC coprocessor (40 bit register) or an + * iWMMXt coprocessor (64 bit registers) by loading 00000100:00000000 + * into a coprocessor register and reading it back, and checking + * whether the upper word survived intact. + */ +static int __init cpu_has_iwmmxt(void) +{ + u32 lo; + u32 hi; + + /* + * This sequence is interpreted by the DSP coprocessor as: + * mar acc0, %2, %3 + * mra %0, %1, acc0 + * + * And by the iWMMXt coprocessor as: + * tmcrr wR0, %2, %3 + * tmrrc %0, %1, wR0 + */ + __asm__ __volatile__ ( + "mcrr p0, 0, %2, %3, c0\n" + "mrrc p0, 0, %0, %1, c0\n" + : "=r" (lo), "=r" (hi) + : "r" (0), "r" (0x100)); + + return !!hi; +} + + +/* + * If we detect that the CPU has iWMMXt (and CONFIG_IWMMXT=y), we + * disable CP0/CP1 on boot, and let call_fpe() and the iWMMXt lazy + * switch code handle iWMMXt context switching. If on the other + * hand the CPU has a DSP coprocessor, we keep access to CP0 enabled + * all the time, and save/restore acc0 on context switch in non-lazy + * fashion. + */ +static int __init xscale_cp0_init(void) +{ + u32 cp_access; + + /* do not attempt to probe iwmmxt on non-xscale family CPUs */ + if (!cpu_is_xscale_family()) + return 0; + + cp_access = xscale_cp_access_read() & ~3; + xscale_cp_access_write(cp_access | 1); + + if (cpu_has_iwmmxt()) { +#ifndef CONFIG_IWMMXT + pr_warn("CAUTION: XScale iWMMXt coprocessor detected, but kernel support is missing.\n"); +#else + pr_info("XScale iWMMXt coprocessor detected.\n"); + elf_hwcap |= HWCAP_IWMMXT; + thread_register_notifier(&iwmmxt_notifier_block); +#endif + } else { + pr_info("XScale DSP coprocessor detected.\n"); + thread_register_notifier(&dsp_notifier_block); + cp_access |= 1; + } + + xscale_cp_access_write(cp_access); + + return 0; +} + +late_initcall(xscale_cp0_init); |