diff options
Diffstat (limited to 'arch/arm64/kernel')
38 files changed, 2857 insertions, 334 deletions
diff --git a/arch/arm64/kernel/Makefile b/arch/arm64/kernel/Makefile index 2173149d8..14f7b651c 100644 --- a/arch/arm64/kernel/Makefile +++ b/arch/arm64/kernel/Makefile @@ -26,8 +26,7 @@ $(obj)/%.stub.o: $(obj)/%.o FORCE $(call if_changed,objcopy) arm64-obj-$(CONFIG_COMPAT) += sys32.o kuser32.o signal32.o \ - sys_compat.o entry32.o \ - ../../arm/kernel/opcodes.o + sys_compat.o entry32.o arm64-obj-$(CONFIG_FUNCTION_TRACER) += ftrace.o entry-ftrace.o arm64-obj-$(CONFIG_MODULES) += arm64ksyms.o module.o arm64-obj-$(CONFIG_ARM64_MODULE_PLTS) += module-plts.o @@ -42,16 +41,15 @@ arm64-obj-$(CONFIG_EFI) += efi.o efi-entry.stub.o arm64-obj-$(CONFIG_PCI) += pci.o arm64-obj-$(CONFIG_ARMV8_DEPRECATED) += armv8_deprecated.o arm64-obj-$(CONFIG_ACPI) += acpi.o +arm64-obj-$(CONFIG_ACPI_NUMA) += acpi_numa.o arm64-obj-$(CONFIG_ARM64_ACPI_PARKING_PROTOCOL) += acpi_parking_protocol.o arm64-obj-$(CONFIG_PARAVIRT) += paravirt.o arm64-obj-$(CONFIG_RANDOMIZE_BASE) += kaslr.o arm64-obj-$(CONFIG_HIBERNATION) += hibernate.o hibernate-asm.o +arm64-obj-$(CONFIG_KEXEC) += machine_kexec.o relocate_kernel.o \ + cpu-reset.o -obj-y += $(arm64-obj-y) vdso/ +obj-y += $(arm64-obj-y) vdso/ probes/ obj-m += $(arm64-obj-m) head-y := head.o extra-y += $(head-y) vmlinux.lds - -# vDSO - this must be built first to generate the symbol offsets -$(call objectify,$(arm64-obj-y)): $(obj)/vdso/vdso-offsets.h -$(obj)/vdso/vdso-offsets.h: $(obj)/vdso diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c new file mode 100644 index 000000000..f85149cc7 --- /dev/null +++ b/arch/arm64/kernel/acpi_numa.c @@ -0,0 +1,112 @@ +/* + * ACPI 5.1 based NUMA setup for ARM64 + * Lots of code was borrowed from arch/x86/mm/srat.c + * + * Copyright 2004 Andi Kleen, SuSE Labs. + * Copyright (C) 2013-2016, Linaro Ltd. + * Author: Hanjun Guo <hanjun.guo@linaro.org> + * + * Reads the ACPI SRAT table to figure out what memory belongs to which CPUs. + * + * Called from acpi_numa_init while reading the SRAT and SLIT tables. + * Assumes all memory regions belonging to a single proximity domain + * are in one chunk. Holes between them will be included in the node. + */ + +#define pr_fmt(fmt) "ACPI: NUMA: " fmt + +#include <linux/acpi.h> +#include <linux/bitmap.h> +#include <linux/bootmem.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/memblock.h> +#include <linux/mmzone.h> +#include <linux/module.h> +#include <linux/topology.h> + +#include <acpi/processor.h> +#include <asm/numa.h> + +static int cpus_in_srat; + +struct __node_cpu_hwid { + u32 node_id; /* logical node containing this CPU */ + u64 cpu_hwid; /* MPIDR for this CPU */ +}; + +static struct __node_cpu_hwid early_node_cpu_hwid[NR_CPUS] = { +[0 ... NR_CPUS - 1] = {NUMA_NO_NODE, PHYS_CPUID_INVALID} }; + +int acpi_numa_get_nid(unsigned int cpu, u64 hwid) +{ + int i; + + for (i = 0; i < cpus_in_srat; i++) { + if (hwid == early_node_cpu_hwid[i].cpu_hwid) + return early_node_cpu_hwid[i].node_id; + } + + return NUMA_NO_NODE; +} + +/* Callback for Proximity Domain -> ACPI processor UID mapping */ +void __init acpi_numa_gicc_affinity_init(struct acpi_srat_gicc_affinity *pa) +{ + int pxm, node; + phys_cpuid_t mpidr; + + if (srat_disabled()) + return; + + if (pa->header.length < sizeof(struct acpi_srat_gicc_affinity)) { + pr_err("SRAT: Invalid SRAT header length: %d\n", + pa->header.length); + bad_srat(); + return; + } + + if (!(pa->flags & ACPI_SRAT_GICC_ENABLED)) + return; + + if (cpus_in_srat >= NR_CPUS) { + pr_warn_once("SRAT: cpu_to_node_map[%d] is too small, may not be able to use all cpus\n", + NR_CPUS); + return; + } + + pxm = pa->proximity_domain; + node = acpi_map_pxm_to_node(pxm); + + if (node == NUMA_NO_NODE || node >= MAX_NUMNODES) { + pr_err("SRAT: Too many proximity domains %d\n", pxm); + bad_srat(); + return; + } + + mpidr = acpi_map_madt_entry(pa->acpi_processor_uid); + if (mpidr == PHYS_CPUID_INVALID) { + pr_err("SRAT: PXM %d with ACPI ID %d has no valid MPIDR in MADT\n", + pxm, pa->acpi_processor_uid); + bad_srat(); + return; + } + + early_node_cpu_hwid[cpus_in_srat].node_id = node; + early_node_cpu_hwid[cpus_in_srat].cpu_hwid = mpidr; + node_set(node, numa_nodes_parsed); + cpus_in_srat++; + pr_info("SRAT: PXM %d -> MPIDR 0x%Lx -> Node %d\n", + pxm, mpidr, node); +} + +int __init arm64_acpi_numa_init(void) +{ + int ret; + + ret = acpi_numa_init(); + if (ret) + return ret; + + return srat_disabled() ? -EINVAL : 0; +} diff --git a/arch/arm64/kernel/arm64ksyms.c b/arch/arm64/kernel/arm64ksyms.c index 678f30b05..78f368039 100644 --- a/arch/arm64/kernel/arm64ksyms.c +++ b/arch/arm64/kernel/arm64ksyms.c @@ -27,6 +27,7 @@ #include <linux/uaccess.h> #include <linux/io.h> #include <linux/arm-smccc.h> +#include <linux/kprobes.h> #include <asm/checksum.h> @@ -34,8 +35,8 @@ EXPORT_SYMBOL(copy_page); EXPORT_SYMBOL(clear_page); /* user mem (segment) */ -EXPORT_SYMBOL(__copy_from_user); -EXPORT_SYMBOL(__copy_to_user); +EXPORT_SYMBOL(__arch_copy_from_user); +EXPORT_SYMBOL(__arch_copy_to_user); EXPORT_SYMBOL(__clear_user); EXPORT_SYMBOL(__copy_in_user); @@ -68,6 +69,7 @@ EXPORT_SYMBOL(test_and_change_bit); #ifdef CONFIG_FUNCTION_TRACER EXPORT_SYMBOL(_mcount); +NOKPROBE_SYMBOL(_mcount); #endif /* arm-smccc */ diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index c37202c0c..42ffdb54e 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -121,7 +121,7 @@ static int run_all_cpu_set_hw_mode(struct insn_emulation *insn, bool enable) * 0 - If all the hooks ran successfully. * -EINVAL - At least one hook is not supported by the CPU. */ -static int run_all_insn_set_hw_mode(unsigned long cpu) +static int run_all_insn_set_hw_mode(unsigned int cpu) { int rc = 0; unsigned long flags; @@ -131,7 +131,7 @@ static int run_all_insn_set_hw_mode(unsigned long cpu) list_for_each_entry(insn, &insn_emulation, node) { bool enable = (insn->current_mode == INSN_HW); if (insn->ops->set_hw_mode && insn->ops->set_hw_mode(enable)) { - pr_warn("CPU[%ld] cannot support the emulation of %s", + pr_warn("CPU[%u] cannot support the emulation of %s", cpu, insn->ops->name); rc = -EINVAL; } @@ -316,28 +316,6 @@ static void __init register_insn_emulation_sysctl(struct ctl_table *table) */ #define TYPE_SWPB (1 << 22) -/* - * Set up process info to signal segmentation fault - called on access error. - */ -static void set_segfault(struct pt_regs *regs, unsigned long addr) -{ - siginfo_t info; - - down_read(¤t->mm->mmap_sem); - if (find_vma(current->mm, addr) == NULL) - info.si_code = SEGV_MAPERR; - else - info.si_code = SEGV_ACCERR; - up_read(¤t->mm->mmap_sem); - - info.si_signo = SIGSEGV; - info.si_errno = 0; - info.si_addr = (void *) instruction_pointer(regs); - - pr_debug("SWP{B} emulation: access caused memory abort!\n"); - arm64_notify_die("Illegal memory access", regs, &info, 0); -} - static int emulate_swpX(unsigned int address, unsigned int *data, unsigned int type) { @@ -366,6 +344,21 @@ static int emulate_swpX(unsigned int address, unsigned int *data, return res; } +#define ARM_OPCODE_CONDITION_UNCOND 0xf + +static unsigned int __kprobes aarch32_check_condition(u32 opcode, u32 psr) +{ + u32 cc_bits = opcode >> 28; + + if (cc_bits != ARM_OPCODE_CONDITION_UNCOND) { + if ((*aarch32_opcode_cond_checks[cc_bits])(psr)) + return ARM_OPCODE_CONDTEST_PASS; + else + return ARM_OPCODE_CONDTEST_FAIL; + } + return ARM_OPCODE_CONDTEST_UNCOND; +} + /* * swp_handler logs the id of calling process, dissects the instruction, sanity * checks the memory location, calls emulate_swpX for the actual operation and @@ -380,7 +373,7 @@ static int swp_handler(struct pt_regs *regs, u32 instr) type = instr & TYPE_SWPB; - switch (arm_check_condition(instr, regs->pstate)) { + switch (aarch32_check_condition(instr, regs->pstate)) { case ARM_OPCODE_CONDTEST_PASS: break; case ARM_OPCODE_CONDTEST_FAIL: @@ -430,7 +423,8 @@ ret: return 0; fault: - set_segfault(regs, address); + pr_debug("SWP{B} emulation: access caused memory abort!\n"); + arm64_notify_segfault(regs, address); return 0; } @@ -461,7 +455,7 @@ static int cp15barrier_handler(struct pt_regs *regs, u32 instr) { perf_sw_event(PERF_COUNT_SW_EMULATION_FAULTS, 1, regs, regs->pc); - switch (arm_check_condition(instr, regs->pstate)) { + switch (aarch32_check_condition(instr, regs->pstate)) { case ARM_OPCODE_CONDTEST_PASS: break; case ARM_OPCODE_CONDTEST_FAIL: @@ -617,20 +611,6 @@ static struct insn_emulation_ops setend_ops = { .set_hw_mode = setend_set_hw_mode, }; -static int insn_cpu_hotplug_notify(struct notifier_block *b, - unsigned long action, void *hcpu) -{ - int rc = 0; - if ((action & ~CPU_TASKS_FROZEN) == CPU_STARTING) - rc = run_all_insn_set_hw_mode((unsigned long)hcpu); - - return notifier_from_errno(rc); -} - -static struct notifier_block insn_cpu_hotplug_notifier = { - .notifier_call = insn_cpu_hotplug_notify, -}; - /* * Invoked as late_initcall, since not needed before init spawned. */ @@ -649,7 +629,9 @@ static int __init armv8_deprecated_init(void) pr_info("setend instruction emulation is not supported on the system"); } - register_cpu_notifier(&insn_cpu_hotplug_notifier); + cpuhp_setup_state_nocalls(CPUHP_AP_ARM64_ISNDEP_STARTING, + "AP_ARM64_ISNDEP_STARTING", + run_all_insn_set_hw_mode, NULL); register_insn_emulation_sysctl(ctl_abi); return 0; diff --git a/arch/arm64/kernel/asm-offsets.c b/arch/arm64/kernel/asm-offsets.c index 2f4ba7744..05070b72f 100644 --- a/arch/arm64/kernel/asm-offsets.c +++ b/arch/arm64/kernel/asm-offsets.c @@ -51,6 +51,17 @@ int main(void) DEFINE(S_X5, offsetof(struct pt_regs, regs[5])); DEFINE(S_X6, offsetof(struct pt_regs, regs[6])); DEFINE(S_X7, offsetof(struct pt_regs, regs[7])); + DEFINE(S_X8, offsetof(struct pt_regs, regs[8])); + DEFINE(S_X10, offsetof(struct pt_regs, regs[10])); + DEFINE(S_X12, offsetof(struct pt_regs, regs[12])); + DEFINE(S_X14, offsetof(struct pt_regs, regs[14])); + DEFINE(S_X16, offsetof(struct pt_regs, regs[16])); + DEFINE(S_X18, offsetof(struct pt_regs, regs[18])); + DEFINE(S_X20, offsetof(struct pt_regs, regs[20])); + DEFINE(S_X22, offsetof(struct pt_regs, regs[22])); + DEFINE(S_X24, offsetof(struct pt_regs, regs[24])); + DEFINE(S_X26, offsetof(struct pt_regs, regs[26])); + DEFINE(S_X28, offsetof(struct pt_regs, regs[28])); DEFINE(S_LR, offsetof(struct pt_regs, regs[30])); DEFINE(S_SP, offsetof(struct pt_regs, sp)); #ifdef CONFIG_COMPAT @@ -78,6 +89,7 @@ int main(void) BLANK(); DEFINE(CLOCK_REALTIME, CLOCK_REALTIME); DEFINE(CLOCK_MONOTONIC, CLOCK_MONOTONIC); + DEFINE(CLOCK_MONOTONIC_RAW, CLOCK_MONOTONIC_RAW); DEFINE(CLOCK_REALTIME_RES, MONOTONIC_RES_NSEC); DEFINE(CLOCK_REALTIME_COARSE, CLOCK_REALTIME_COARSE); DEFINE(CLOCK_MONOTONIC_COARSE,CLOCK_MONOTONIC_COARSE); @@ -85,6 +97,8 @@ int main(void) DEFINE(NSEC_PER_SEC, NSEC_PER_SEC); BLANK(); DEFINE(VDSO_CS_CYCLE_LAST, offsetof(struct vdso_data, cs_cycle_last)); + DEFINE(VDSO_RAW_TIME_SEC, offsetof(struct vdso_data, raw_time_sec)); + DEFINE(VDSO_RAW_TIME_NSEC, offsetof(struct vdso_data, raw_time_nsec)); DEFINE(VDSO_XTIME_CLK_SEC, offsetof(struct vdso_data, xtime_clock_sec)); DEFINE(VDSO_XTIME_CLK_NSEC, offsetof(struct vdso_data, xtime_clock_nsec)); DEFINE(VDSO_XTIME_CRS_SEC, offsetof(struct vdso_data, xtime_coarse_sec)); @@ -92,7 +106,8 @@ int main(void) DEFINE(VDSO_WTM_CLK_SEC, offsetof(struct vdso_data, wtm_clock_sec)); DEFINE(VDSO_WTM_CLK_NSEC, offsetof(struct vdso_data, wtm_clock_nsec)); DEFINE(VDSO_TB_SEQ_COUNT, offsetof(struct vdso_data, tb_seq_count)); - DEFINE(VDSO_CS_MULT, offsetof(struct vdso_data, cs_mult)); + DEFINE(VDSO_CS_MONO_MULT, offsetof(struct vdso_data, cs_mono_mult)); + DEFINE(VDSO_CS_RAW_MULT, offsetof(struct vdso_data, cs_raw_mult)); DEFINE(VDSO_CS_SHIFT, offsetof(struct vdso_data, cs_shift)); DEFINE(VDSO_TZ_MINWEST, offsetof(struct vdso_data, tz_minuteswest)); DEFINE(VDSO_TZ_DSTTIME, offsetof(struct vdso_data, tz_dsttime)); diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S new file mode 100644 index 000000000..65f42d257 --- /dev/null +++ b/arch/arm64/kernel/cpu-reset.S @@ -0,0 +1,54 @@ +/* + * CPU reset routines + * + * Copyright (C) 2001 Deep Blue Solutions Ltd. + * Copyright (C) 2012 ARM Ltd. + * Copyright (C) 2015 Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/linkage.h> +#include <asm/assembler.h> +#include <asm/sysreg.h> +#include <asm/virt.h> + +.text +.pushsection .idmap.text, "ax" + +/* + * __cpu_soft_restart(el2_switch, entry, arg0, arg1, arg2) - Helper for + * cpu_soft_restart. + * + * @el2_switch: Flag to indicate a swich to EL2 is needed. + * @entry: Location to jump to for soft reset. + * arg0: First argument passed to @entry. + * arg1: Second argument passed to @entry. + * arg2: Third argument passed to @entry. + * + * Put the CPU into the same state as it would be if it had been reset, and + * branch to what would be the reset vector. It must be executed with the + * flat identity mapping. + */ +ENTRY(__cpu_soft_restart) + /* Clear sctlr_el1 flags. */ + mrs x12, sctlr_el1 + ldr x13, =SCTLR_ELx_FLAGS + bic x12, x12, x13 + msr sctlr_el1, x12 + isb + + cbz x0, 1f // el2_switch? + mov x0, #HVC_SOFT_RESTART + hvc #0 // no return + +1: mov x18, x1 // entry + mov x0, x2 // arg0 + mov x1, x3 // arg1 + mov x2, x4 // arg2 + br x18 +ENDPROC(__cpu_soft_restart) + +.popsection diff --git a/arch/arm64/kernel/cpu-reset.h b/arch/arm64/kernel/cpu-reset.h new file mode 100644 index 000000000..d4e9ecb26 --- /dev/null +++ b/arch/arm64/kernel/cpu-reset.h @@ -0,0 +1,34 @@ +/* + * CPU reset routines + * + * Copyright (C) 2015 Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#ifndef _ARM64_CPU_RESET_H +#define _ARM64_CPU_RESET_H + +#include <asm/virt.h> + +void __cpu_soft_restart(unsigned long el2_switch, unsigned long entry, + unsigned long arg0, unsigned long arg1, unsigned long arg2); + +static inline void __noreturn cpu_soft_restart(unsigned long el2_switch, + unsigned long entry, unsigned long arg0, unsigned long arg1, + unsigned long arg2) +{ + typeof(__cpu_soft_restart) *restart; + + el2_switch = el2_switch && !is_kernel_in_hyp_mode() && + is_hyp_mode_available(); + restart = (void *)virt_to_phys(__cpu_soft_restart); + + cpu_install_idmap(); + restart(el2_switch, entry, arg0, arg1, arg2); + unreachable(); +} + +#endif diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index af716b651..82b0fc2e6 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -46,6 +46,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .desc = "ARM errata 826319, 827319, 824069", .capability = ARM64_WORKAROUND_CLEAN_CACHE, MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x02), + .enable = cpu_enable_cache_maint_trap, }, #endif #ifdef CONFIG_ARM64_ERRATUM_819472 @@ -54,6 +55,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { .desc = "ARM errata 819472", .capability = ARM64_WORKAROUND_CLEAN_CACHE, MIDR_RANGE(MIDR_CORTEX_A53, 0x00, 0x01), + .enable = cpu_enable_cache_maint_trap, }, #endif #ifdef CONFIG_ARM64_ERRATUM_832075 @@ -133,3 +135,8 @@ void check_local_cpu_errata(void) { update_cpu_capabilities(arm64_errata, "enabling workaround for"); } + +void __init enable_errata_workarounds(void) +{ + enable_cpu_capabilities(arm64_errata); +} diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 811773d1c..62272eac1 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -726,6 +726,19 @@ static bool runs_at_el2(const struct arm64_cpu_capabilities *entry, int __unused return is_kernel_in_hyp_mode(); } +static bool hyp_offset_low(const struct arm64_cpu_capabilities *entry, + int __unused) +{ + phys_addr_t idmap_addr = virt_to_phys(__hyp_idmap_text_start); + + /* + * Activate the lower HYP offset only if: + * - the idmap doesn't clash with it, + * - the kernel is not running at EL2. + */ + return idmap_addr > GENMASK(VA_BITS - 2, 0) && !is_kernel_in_hyp_mode(); +} + static const struct arm64_cpu_capabilities arm64_features[] = { { .desc = "GIC system register CPU interface", @@ -803,6 +816,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .field_pos = ID_AA64PFR0_EL0_SHIFT, .min_field_value = ID_AA64PFR0_EL0_32BIT_64BIT, }, + { + .desc = "Reduced HYP mapping offset", + .capability = ARM64_HYP_OFFSET_LOW, + .def_scope = SCOPE_SYSTEM, + .matches = hyp_offset_low, + }, {}, }; @@ -913,8 +932,7 @@ void update_cpu_capabilities(const struct arm64_cpu_capabilities *caps, * Run through the enabled capabilities and enable() it on all active * CPUs */ -static void __init -enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) +void __init enable_cpu_capabilities(const struct arm64_cpu_capabilities *caps) { for (; caps->matches; caps++) if (caps->enable && cpus_have_cap(caps->capability)) @@ -1036,6 +1054,7 @@ void __init setup_cpu_features(void) /* Set the CPU feature capabilies */ setup_feature_capabilities(); + enable_errata_workarounds(); setup_elf_hwcaps(arm64_elf_hwcaps); if (system_supports_32bit_el0()) diff --git a/arch/arm64/kernel/cpuidle.c b/arch/arm64/kernel/cpuidle.c index e11857fce..75a0f8ace 100644 --- a/arch/arm64/kernel/cpuidle.c +++ b/arch/arm64/kernel/cpuidle.c @@ -9,13 +9,16 @@ * published by the Free Software Foundation. */ +#include <linux/acpi.h> +#include <linux/cpuidle.h> +#include <linux/cpu_pm.h> #include <linux/of.h> #include <linux/of_device.h> #include <asm/cpuidle.h> #include <asm/cpu_ops.h> -int __init arm_cpuidle_init(unsigned int cpu) +int arm_cpuidle_init(unsigned int cpu) { int ret = -EOPNOTSUPP; @@ -39,3 +42,18 @@ int arm_cpuidle_suspend(int index) return cpu_ops[cpu]->cpu_suspend(index); } + +#ifdef CONFIG_ACPI + +#include <acpi/processor.h> + +int acpi_processor_ffh_lpi_probe(unsigned int cpu) +{ + return arm_cpuidle_init(cpu); +} + +int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi) +{ + return CPU_PM_CPU_IDLE_ENTER(arm_cpuidle_suspend, lpi->index); +} +#endif diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index c173d3293..ed1b84fe6 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -183,6 +183,123 @@ const struct seq_operations cpuinfo_op = { .show = c_show }; + +static struct kobj_type cpuregs_kobj_type = { + .sysfs_ops = &kobj_sysfs_ops, +}; + +/* + * The ARM ARM uses the phrase "32-bit register" to describe a register + * whose upper 32 bits are RES0 (per C5.1.1, ARM DDI 0487A.i), however + * no statement is made as to whether the upper 32 bits will or will not + * be made use of in future, and between ARM DDI 0487A.c and ARM DDI + * 0487A.d CLIDR_EL1 was expanded from 32-bit to 64-bit. + * + * Thus, while both MIDR_EL1 and REVIDR_EL1 are described as 32-bit + * registers, we expose them both as 64 bit values to cater for possible + * future expansion without an ABI break. + */ +#define kobj_to_cpuinfo(kobj) container_of(kobj, struct cpuinfo_arm64, kobj) +#define CPUREGS_ATTR_RO(_name, _field) \ + static ssize_t _name##_show(struct kobject *kobj, \ + struct kobj_attribute *attr, char *buf) \ + { \ + struct cpuinfo_arm64 *info = kobj_to_cpuinfo(kobj); \ + \ + if (info->reg_midr) \ + return sprintf(buf, "0x%016x\n", info->reg_##_field); \ + else \ + return 0; \ + } \ + static struct kobj_attribute cpuregs_attr_##_name = __ATTR_RO(_name) + +CPUREGS_ATTR_RO(midr_el1, midr); +CPUREGS_ATTR_RO(revidr_el1, revidr); + +static struct attribute *cpuregs_id_attrs[] = { + &cpuregs_attr_midr_el1.attr, + &cpuregs_attr_revidr_el1.attr, + NULL +}; + +static struct attribute_group cpuregs_attr_group = { + .attrs = cpuregs_id_attrs, + .name = "identification" +}; + +static int cpuid_add_regs(int cpu) +{ + int rc; + struct device *dev; + struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu); + + dev = get_cpu_device(cpu); + if (!dev) { + rc = -ENODEV; + goto out; + } + rc = kobject_add(&info->kobj, &dev->kobj, "regs"); + if (rc) + goto out; + rc = sysfs_create_group(&info->kobj, &cpuregs_attr_group); + if (rc) + kobject_del(&info->kobj); +out: + return rc; +} + +static int cpuid_remove_regs(int cpu) +{ + struct device *dev; + struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu); + + dev = get_cpu_device(cpu); + if (!dev) + return -ENODEV; + if (info->kobj.parent) { + sysfs_remove_group(&info->kobj, &cpuregs_attr_group); + kobject_del(&info->kobj); + } + + return 0; +} + +static int cpuid_callback(struct notifier_block *nb, + unsigned long action, void *hcpu) +{ + int rc = 0; + unsigned long cpu = (unsigned long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_ONLINE: + rc = cpuid_add_regs(cpu); + break; + case CPU_DEAD: + rc = cpuid_remove_regs(cpu); + break; + } + + return notifier_from_errno(rc); +} + +static int __init cpuinfo_regs_init(void) +{ + int cpu; + + cpu_notifier_register_begin(); + + for_each_possible_cpu(cpu) { + struct cpuinfo_arm64 *info = &per_cpu(cpu_data, cpu); + + kobject_init(&info->kobj, &cpuregs_kobj_type); + if (cpu_online(cpu)) + cpuid_add_regs(cpu); + } + __hotcpu_notifier(cpuid_callback, 0); + + cpu_notifier_register_done(); + return 0; +} static void cpuinfo_detect_icache_policy(struct cpuinfo_arm64 *info) { unsigned int cpu = smp_processor_id(); @@ -212,6 +329,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_ctr = read_cpuid_cachetype(); info->reg_dczid = read_cpuid(DCZID_EL0); info->reg_midr = read_cpuid_id(); + info->reg_revidr = read_cpuid(REVIDR_EL1); info->reg_id_aa64dfr0 = read_cpuid(ID_AA64DFR0_EL1); info->reg_id_aa64dfr1 = read_cpuid(ID_AA64DFR1_EL1); @@ -264,3 +382,5 @@ void __init cpuinfo_store_boot_cpu(void) boot_cpu_data = *info; init_cpu_features(&boot_cpu_data); } + +device_initcall(cpuinfo_regs_init); diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c index 0800d23e2..2751ff9c0 100644 --- a/arch/arm64/kernel/debug-monitors.c +++ b/arch/arm64/kernel/debug-monitors.c @@ -23,6 +23,7 @@ #include <linux/hardirq.h> #include <linux/init.h> #include <linux/ptrace.h> +#include <linux/kprobes.h> #include <linux/stat.h> #include <linux/uaccess.h> @@ -48,6 +49,7 @@ static void mdscr_write(u32 mdscr) asm volatile("msr mdscr_el1, %0" :: "r" (mdscr)); local_dbg_restore(flags); } +NOKPROBE_SYMBOL(mdscr_write); static u32 mdscr_read(void) { @@ -55,6 +57,7 @@ static u32 mdscr_read(void) asm volatile("mrs %0, mdscr_el1" : "=r" (mdscr)); return mdscr; } +NOKPROBE_SYMBOL(mdscr_read); /* * Allow root to disable self-hosted debug from userspace. @@ -103,6 +106,7 @@ void enable_debug_monitors(enum dbg_active_el el) mdscr_write(mdscr); } } +NOKPROBE_SYMBOL(enable_debug_monitors); void disable_debug_monitors(enum dbg_active_el el) { @@ -123,6 +127,7 @@ void disable_debug_monitors(enum dbg_active_el el) mdscr_write(mdscr); } } +NOKPROBE_SYMBOL(disable_debug_monitors); /* * OS lock clearing. @@ -165,22 +170,15 @@ postcore_initcall(debug_monitors_init); */ static void set_regs_spsr_ss(struct pt_regs *regs) { - unsigned long spsr; - - spsr = regs->pstate; - spsr &= ~DBG_SPSR_SS; - spsr |= DBG_SPSR_SS; - regs->pstate = spsr; + regs->pstate |= DBG_SPSR_SS; } +NOKPROBE_SYMBOL(set_regs_spsr_ss); static void clear_regs_spsr_ss(struct pt_regs *regs) { - unsigned long spsr; - - spsr = regs->pstate; - spsr &= ~DBG_SPSR_SS; - regs->pstate = spsr; + regs->pstate &= ~DBG_SPSR_SS; } +NOKPROBE_SYMBOL(clear_regs_spsr_ss); /* EL1 Single Step Handler hooks */ static LIST_HEAD(step_hook); @@ -224,6 +222,7 @@ static int call_step_hook(struct pt_regs *regs, unsigned int esr) return retval; } +NOKPROBE_SYMBOL(call_step_hook); static void send_user_sigtrap(int si_code) { @@ -265,6 +264,10 @@ static int single_step_handler(unsigned long addr, unsigned int esr, */ user_rewind_single_step(current); } else { +#ifdef CONFIG_KPROBES + if (kprobe_single_step_handler(regs, esr) == DBG_HOOK_HANDLED) + return 0; +#endif if (call_step_hook(regs, esr) == DBG_HOOK_HANDLED) return 0; @@ -278,6 +281,7 @@ static int single_step_handler(unsigned long addr, unsigned int esr, return 0; } +NOKPROBE_SYMBOL(single_step_handler); /* * Breakpoint handler is re-entrant as another breakpoint can @@ -315,19 +319,28 @@ static int call_break_hook(struct pt_regs *regs, unsigned int esr) return fn ? fn(regs, esr) : DBG_HOOK_ERROR; } +NOKPROBE_SYMBOL(call_break_hook); static int brk_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) { if (user_mode(regs)) { send_user_sigtrap(TRAP_BRKPT); - } else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) { - pr_warning("Unexpected kernel BRK exception at EL1\n"); + } +#ifdef CONFIG_KPROBES + else if ((esr & BRK64_ESR_MASK) == BRK64_ESR_KPROBES) { + if (kprobe_breakpoint_handler(regs, esr) != DBG_HOOK_HANDLED) + return -EFAULT; + } +#endif + else if (call_break_hook(regs, esr) != DBG_HOOK_HANDLED) { + pr_warn("Unexpected kernel BRK exception at EL1\n"); return -EFAULT; } return 0; } +NOKPROBE_SYMBOL(brk_handler); int aarch32_break_handler(struct pt_regs *regs) { @@ -364,6 +377,7 @@ int aarch32_break_handler(struct pt_regs *regs) send_user_sigtrap(TRAP_BRKPT); return 0; } +NOKPROBE_SYMBOL(aarch32_break_handler); static int __init debug_traps_init(void) { @@ -385,6 +399,7 @@ void user_rewind_single_step(struct task_struct *task) if (test_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP)) set_regs_spsr_ss(task_pt_regs(task)); } +NOKPROBE_SYMBOL(user_rewind_single_step); void user_fastforward_single_step(struct task_struct *task) { @@ -400,6 +415,7 @@ void kernel_enable_single_step(struct pt_regs *regs) mdscr_write(mdscr_read() | DBG_MDSCR_SS); enable_debug_monitors(DBG_ACTIVE_EL1); } +NOKPROBE_SYMBOL(kernel_enable_single_step); void kernel_disable_single_step(void) { @@ -407,21 +423,27 @@ void kernel_disable_single_step(void) mdscr_write(mdscr_read() & ~DBG_MDSCR_SS); disable_debug_monitors(DBG_ACTIVE_EL1); } +NOKPROBE_SYMBOL(kernel_disable_single_step); int kernel_active_single_step(void) { WARN_ON(!irqs_disabled()); return mdscr_read() & DBG_MDSCR_SS; } +NOKPROBE_SYMBOL(kernel_active_single_step); /* ptrace API */ void user_enable_single_step(struct task_struct *task) { - set_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP); - set_regs_spsr_ss(task_pt_regs(task)); + struct thread_info *ti = task_thread_info(task); + + if (!test_and_set_ti_thread_flag(ti, TIF_SINGLESTEP)) + set_regs_spsr_ss(task_pt_regs(task)); } +NOKPROBE_SYMBOL(user_enable_single_step); void user_disable_single_step(struct task_struct *task) { clear_ti_thread_flag(task_thread_info(task), TIF_SINGLESTEP); } +NOKPROBE_SYMBOL(user_disable_single_step); diff --git a/arch/arm64/kernel/efi.c b/arch/arm64/kernel/efi.c index 78f52488f..ba9bee389 100644 --- a/arch/arm64/kernel/efi.c +++ b/arch/arm64/kernel/efi.c @@ -62,13 +62,61 @@ struct screen_info screen_info __section(.data); int __init efi_create_mapping(struct mm_struct *mm, efi_memory_desc_t *md) { pteval_t prot_val = create_mapping_protection(md); + bool allow_block_mappings = (md->type != EFI_RUNTIME_SERVICES_CODE && + md->type != EFI_RUNTIME_SERVICES_DATA); + + if (!PAGE_ALIGNED(md->phys_addr) || + !PAGE_ALIGNED(md->num_pages << EFI_PAGE_SHIFT)) { + /* + * If the end address of this region is not aligned to page + * size, the mapping is rounded up, and may end up sharing a + * page frame with the next UEFI memory region. If we create + * a block entry now, we may need to split it again when mapping + * the next region, and support for that is going to be removed + * from the MMU routines. So avoid block mappings altogether in + * that case. + */ + allow_block_mappings = false; + } create_pgd_mapping(mm, md->phys_addr, md->virt_addr, md->num_pages << EFI_PAGE_SHIFT, - __pgprot(prot_val | PTE_NG)); + __pgprot(prot_val | PTE_NG), allow_block_mappings); + return 0; +} + +static int __init set_permissions(pte_t *ptep, pgtable_t token, + 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(PTE_RDONLY)); + if (md->attribute & EFI_MEMORY_XP) + pte = set_pte_bit(pte, __pgprot(PTE_PXN)); + set_pte(ptep, pte); return 0; } +int __init efi_set_mapping_permissions(struct mm_struct *mm, + efi_memory_desc_t *md) +{ + BUG_ON(md->type != EFI_RUNTIME_SERVICES_CODE && + md->type != EFI_RUNTIME_SERVICES_DATA); + + /* + * Calling apply_to_page_range() is only safe on regions that are + * guaranteed to be mapped down to pages. Since we are only called + * for regions that have been mapped using efi_create_mapping() above + * (and this is checked by the generic Memory Attributes table parsing + * routines), there is no need to check that again here. + */ + return apply_to_page_range(mm, md->virt_addr, + md->num_pages << EFI_PAGE_SHIFT, + set_permissions, md); +} + static int __init arm64_dmi_init(void) { /* diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 6c3b7345a..441420ca7 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -258,6 +258,7 @@ tsk .req x28 // current thread_info /* * Exception vectors. */ + .pushsection ".entry.text", "ax" .align 11 ENTRY(vectors) @@ -352,6 +353,8 @@ el1_sync: lsr x24, x1, #ESR_ELx_EC_SHIFT // exception class cmp x24, #ESR_ELx_EC_DABT_CUR // data abort in EL1 b.eq el1_da + cmp x24, #ESR_ELx_EC_IABT_CUR // instruction abort in EL1 + b.eq el1_ia cmp x24, #ESR_ELx_EC_SYS64 // configurable trap b.eq el1_undef cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception @@ -363,6 +366,11 @@ el1_sync: cmp x24, #ESR_ELx_EC_BREAKPT_CUR // debug exception in EL1 b.ge el1_dbg b el1_inv + +el1_ia: + /* + * Fall through to the Data abort case + */ el1_da: /* * Data abort handling @@ -466,7 +474,7 @@ el0_sync: cmp x24, #ESR_ELx_EC_FP_EXC64 // FP/ASIMD exception b.eq el0_fpsimd_exc cmp x24, #ESR_ELx_EC_SYS64 // configurable trap - b.eq el0_undef + b.eq el0_sys cmp x24, #ESR_ELx_EC_SP_ALIGN // stack alignment exception b.eq el0_sp_pc cmp x24, #ESR_ELx_EC_PC_ALIGN // pc alignment exception @@ -547,7 +555,7 @@ el0_ia: enable_dbg_and_irq ct_user_exit mov x0, x26 - orr x1, x25, #1 << 24 // use reserved ISS bit for instruction aborts + mov x1, x25 mov x2, sp bl do_mem_abort b ret_to_user @@ -594,6 +602,16 @@ el0_undef: mov x0, sp bl do_undefinstr b ret_to_user +el0_sys: + /* + * System instructions, for trapped cache maintenance instructions + */ + enable_dbg_and_irq + ct_user_exit + mov x0, x25 + mov x1, sp + bl do_sysinstr + b ret_to_user el0_dbg: /* * Debug exception handling @@ -789,6 +807,8 @@ __ni_sys_trace: bl do_ni_syscall b __sys_trace_return + .popsection // .entry.text + /* * Special system call wrappers. */ diff --git a/arch/arm64/kernel/head.S b/arch/arm64/kernel/head.S index aa68aadcd..3e7b050e9 100644 --- a/arch/arm64/kernel/head.S +++ b/arch/arm64/kernel/head.S @@ -784,40 +784,25 @@ __primary_switch: * Iterate over each entry in the relocation table, and apply the * relocations in place. */ - ldr w8, =__dynsym_offset // offset to symbol table ldr w9, =__rela_offset // offset to reloc table ldr w10, =__rela_size // size of reloc table mov_q x11, KIMAGE_VADDR // default virtual offset add x11, x11, x23 // actual virtual offset - add x8, x8, x11 // __va(.dynsym) add x9, x9, x11 // __va(.rela) add x10, x9, x10 // __va(.rela) + sizeof(.rela) 0: cmp x9, x10 - b.hs 2f + b.hs 1f ldp x11, x12, [x9], #24 ldr x13, [x9, #-8] cmp w12, #R_AARCH64_RELATIVE - b.ne 1f + b.ne 0b add x13, x13, x23 // relocate str x13, [x11, x23] b 0b -1: cmp w12, #R_AARCH64_ABS64 - b.ne 0b - add x12, x12, x12, lsl #1 // symtab offset: 24x top word - add x12, x8, x12, lsr #(32 - 3) // ... shifted into bottom word - ldrsh w14, [x12, #6] // Elf64_Sym::st_shndx - ldr x15, [x12, #8] // Elf64_Sym::st_value - cmp w14, #-0xf // SHN_ABS (0xfff1) ? - add x14, x15, x23 // relocate - csel x15, x14, x15, ne - add x15, x13, x15 - str x15, [x11, x23] - b 0b - -2: +1: #endif ldr x8, =__primary_switched br x8 diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c index ce21aa882..26a6bf77d 100644 --- a/arch/arm64/kernel/hw_breakpoint.c +++ b/arch/arm64/kernel/hw_breakpoint.c @@ -24,6 +24,7 @@ #include <linux/cpu_pm.h> #include <linux/errno.h> #include <linux/hw_breakpoint.h> +#include <linux/kprobes.h> #include <linux/perf_event.h> #include <linux/ptrace.h> #include <linux/smp.h> @@ -127,6 +128,7 @@ static u64 read_wb_reg(int reg, int n) return val; } +NOKPROBE_SYMBOL(read_wb_reg); static void write_wb_reg(int reg, int n, u64 val) { @@ -140,6 +142,7 @@ static void write_wb_reg(int reg, int n, u64 val) } isb(); } +NOKPROBE_SYMBOL(write_wb_reg); /* * Convert a breakpoint privilege level to the corresponding exception @@ -157,6 +160,7 @@ static enum dbg_active_el debug_exception_level(int privilege) return -EINVAL; } } +NOKPROBE_SYMBOL(debug_exception_level); enum hw_breakpoint_ops { HW_BREAKPOINT_INSTALL, @@ -575,6 +579,7 @@ static void toggle_bp_registers(int reg, enum dbg_active_el el, int enable) write_wb_reg(reg, i, ctrl); } } +NOKPROBE_SYMBOL(toggle_bp_registers); /* * Debug exception handlers. @@ -654,6 +659,7 @@ unlock: return 0; } +NOKPROBE_SYMBOL(breakpoint_handler); static int watchpoint_handler(unsigned long addr, unsigned int esr, struct pt_regs *regs) @@ -756,6 +762,7 @@ unlock: return 0; } +NOKPROBE_SYMBOL(watchpoint_handler); /* * Handle single-step exception. @@ -813,6 +820,7 @@ int reinstall_suspended_bps(struct pt_regs *regs) return !handled_exception; } +NOKPROBE_SYMBOL(reinstall_suspended_bps); /* * Context-switcher for restoring suspended breakpoints. diff --git a/arch/arm64/kernel/hyp-stub.S b/arch/arm64/kernel/hyp-stub.S index 8727f4490..d3b5f75e6 100644 --- a/arch/arm64/kernel/hyp-stub.S +++ b/arch/arm64/kernel/hyp-stub.S @@ -71,8 +71,16 @@ el1_sync: msr vbar_el2, x1 b 9f +2: cmp x0, #HVC_SOFT_RESTART + b.ne 3f + mov x0, x2 + mov x2, x4 + mov x4, x1 + mov x1, x3 + br x4 // no return + /* Someone called kvm_call_hyp() against the hyp-stub... */ -2: mov x0, #ARM_EXCEPTION_HYP_GONE +3: mov x0, #ARM_EXCEPTION_HYP_GONE 9: eret ENDPROC(el1_sync) diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c index 368c08290..63f9432d0 100644 --- a/arch/arm64/kernel/insn.c +++ b/arch/arm64/kernel/insn.c @@ -30,6 +30,7 @@ #include <asm/cacheflush.h> #include <asm/debug-monitors.h> #include <asm/fixmap.h> +#include <asm/opcodes.h> #include <asm/insn.h> #define AARCH64_INSN_SF_BIT BIT(31) @@ -162,6 +163,32 @@ static bool __kprobes __aarch64_insn_hotpatch_safe(u32 insn) aarch64_insn_is_nop(insn); } +bool __kprobes aarch64_insn_uses_literal(u32 insn) +{ + /* ldr/ldrsw (literal), prfm */ + + return aarch64_insn_is_ldr_lit(insn) || + aarch64_insn_is_ldrsw_lit(insn) || + aarch64_insn_is_adr_adrp(insn) || + aarch64_insn_is_prfm_lit(insn); +} + +bool __kprobes aarch64_insn_is_branch(u32 insn) +{ + /* b, bl, cb*, tb*, b.cond, br, blr */ + + return aarch64_insn_is_b(insn) || + aarch64_insn_is_bl(insn) || + aarch64_insn_is_cbz(insn) || + aarch64_insn_is_cbnz(insn) || + aarch64_insn_is_tbz(insn) || + aarch64_insn_is_tbnz(insn) || + aarch64_insn_is_ret(insn) || + aarch64_insn_is_br(insn) || + aarch64_insn_is_blr(insn) || + aarch64_insn_is_bcond(insn); +} + /* * ARM Architecture Reference Manual for ARMv8 Profile-A, Issue A.a * Section B2.6.5 "Concurrent modification and execution of instructions": @@ -1175,6 +1202,14 @@ u32 aarch64_set_branch_offset(u32 insn, s32 offset) BUG(); } +/* + * Extract the Op/CR data from a msr/mrs instruction. + */ +u32 aarch64_insn_extract_system_reg(u32 insn) +{ + return (insn & 0x1FFFE0) >> 5; +} + bool aarch32_insn_is_wide(u32 insn) { return insn >= 0xe800; @@ -1200,3 +1235,101 @@ u32 aarch32_insn_mcr_extract_crm(u32 insn) { return insn & CRM_MASK; } + +static bool __kprobes __check_eq(unsigned long pstate) +{ + return (pstate & PSR_Z_BIT) != 0; +} + +static bool __kprobes __check_ne(unsigned long pstate) +{ + return (pstate & PSR_Z_BIT) == 0; +} + +static bool __kprobes __check_cs(unsigned long pstate) +{ + return (pstate & PSR_C_BIT) != 0; +} + +static bool __kprobes __check_cc(unsigned long pstate) +{ + return (pstate & PSR_C_BIT) == 0; +} + +static bool __kprobes __check_mi(unsigned long pstate) +{ + return (pstate & PSR_N_BIT) != 0; +} + +static bool __kprobes __check_pl(unsigned long pstate) +{ + return (pstate & PSR_N_BIT) == 0; +} + +static bool __kprobes __check_vs(unsigned long pstate) +{ + return (pstate & PSR_V_BIT) != 0; +} + +static bool __kprobes __check_vc(unsigned long pstate) +{ + return (pstate & PSR_V_BIT) == 0; +} + +static bool __kprobes __check_hi(unsigned long pstate) +{ + pstate &= ~(pstate >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ + return (pstate & PSR_C_BIT) != 0; +} + +static bool __kprobes __check_ls(unsigned long pstate) +{ + pstate &= ~(pstate >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */ + return (pstate & PSR_C_BIT) == 0; +} + +static bool __kprobes __check_ge(unsigned long pstate) +{ + pstate ^= (pstate << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + return (pstate & PSR_N_BIT) == 0; +} + +static bool __kprobes __check_lt(unsigned long pstate) +{ + pstate ^= (pstate << 3); /* PSR_N_BIT ^= PSR_V_BIT */ + return (pstate & PSR_N_BIT) != 0; +} + +static bool __kprobes __check_gt(unsigned long pstate) +{ + /*PSR_N_BIT ^= PSR_V_BIT */ + unsigned long temp = pstate ^ (pstate << 3); + + temp |= (pstate << 1); /*PSR_N_BIT |= PSR_Z_BIT */ + return (temp & PSR_N_BIT) == 0; +} + +static bool __kprobes __check_le(unsigned long pstate) +{ + /*PSR_N_BIT ^= PSR_V_BIT */ + unsigned long temp = pstate ^ (pstate << 3); + + temp |= (pstate << 1); /*PSR_N_BIT |= PSR_Z_BIT */ + return (temp & PSR_N_BIT) != 0; +} + +static bool __kprobes __check_al(unsigned long pstate) +{ + return true; +} + +/* + * Note that the ARMv8 ARM calls condition code 0b1111 "nv", but states that + * it behaves identically to 0b1110 ("al"). + */ +pstate_check_t * const aarch32_opcode_cond_checks[16] = { + __check_eq, __check_ne, __check_cs, __check_cc, + __check_mi, __check_pl, __check_vs, __check_vc, + __check_hi, __check_ls, __check_ge, __check_lt, + __check_gt, __check_le, __check_al, __check_al +}; diff --git a/arch/arm64/kernel/kgdb.c b/arch/arm64/kernel/kgdb.c index b5f063e5e..e017a9493 100644 --- a/arch/arm64/kernel/kgdb.c +++ b/arch/arm64/kernel/kgdb.c @@ -19,9 +19,13 @@ * along with this program. If not, see <http://www.gnu.org/licenses/>. */ +#include <linux/bug.h> #include <linux/irq.h> #include <linux/kdebug.h> #include <linux/kgdb.h> +#include <linux/kprobes.h> +#include <asm/debug-monitors.h> +#include <asm/insn.h> #include <asm/traps.h> struct dbg_reg_def_t dbg_reg_def[DBG_MAX_REG_NUM] = { @@ -230,6 +234,7 @@ static int kgdb_brk_fn(struct pt_regs *regs, unsigned int esr) kgdb_handle_exception(1, SIGTRAP, 0, regs); return 0; } +NOKPROBE_SYMBOL(kgdb_brk_fn) static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr) { @@ -238,12 +243,14 @@ static int kgdb_compiled_brk_fn(struct pt_regs *regs, unsigned int esr) return 0; } +NOKPROBE_SYMBOL(kgdb_compiled_brk_fn); static int kgdb_step_brk_fn(struct pt_regs *regs, unsigned int esr) { kgdb_handle_exception(1, SIGTRAP, 0, regs); return 0; } +NOKPROBE_SYMBOL(kgdb_step_brk_fn); static struct break_hook kgdb_brkpt_hook = { .esr_mask = 0xffffffff, @@ -334,15 +341,24 @@ void kgdb_arch_exit(void) unregister_die_notifier(&kgdb_notifier); } -/* - * ARM instructions are always in LE. - * Break instruction is encoded in LE format - */ -struct kgdb_arch arch_kgdb_ops = { - .gdb_bpt_instr = { - KGDB_DYN_BRK_INS_BYTE(0), - KGDB_DYN_BRK_INS_BYTE(1), - KGDB_DYN_BRK_INS_BYTE(2), - KGDB_DYN_BRK_INS_BYTE(3), - } -}; +struct kgdb_arch arch_kgdb_ops; + +int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt) +{ + int err; + + BUILD_BUG_ON(AARCH64_INSN_SIZE != BREAK_INSTR_SIZE); + + err = aarch64_insn_read((void *)bpt->bpt_addr, (u32 *)bpt->saved_instr); + if (err) + return err; + + return aarch64_insn_write((void *)bpt->bpt_addr, + (u32)AARCH64_BREAK_KGDB_DYN_DBG); +} + +int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt) +{ + return aarch64_insn_write((void *)bpt->bpt_addr, + *(u32 *)bpt->saved_instr); +} diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c new file mode 100644 index 000000000..bc96c8a7f --- /dev/null +++ b/arch/arm64/kernel/machine_kexec.c @@ -0,0 +1,212 @@ +/* + * kexec for arm64 + * + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kexec.h> +#include <linux/smp.h> + +#include <asm/cacheflush.h> +#include <asm/cpu_ops.h> +#include <asm/mmu_context.h> + +#include "cpu-reset.h" + +/* Global variables for the arm64_relocate_new_kernel routine. */ +extern const unsigned char arm64_relocate_new_kernel[]; +extern const unsigned long arm64_relocate_new_kernel_size; + +static unsigned long kimage_start; + +/** + * kexec_image_info - For debugging output. + */ +#define kexec_image_info(_i) _kexec_image_info(__func__, __LINE__, _i) +static void _kexec_image_info(const char *func, int line, + const struct kimage *kimage) +{ + unsigned long i; + + pr_debug("%s:%d:\n", func, line); + pr_debug(" kexec kimage info:\n"); + pr_debug(" type: %d\n", kimage->type); + pr_debug(" start: %lx\n", kimage->start); + pr_debug(" head: %lx\n", kimage->head); + pr_debug(" nr_segments: %lu\n", kimage->nr_segments); + + for (i = 0; i < kimage->nr_segments; i++) { + pr_debug(" segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n", + i, + kimage->segment[i].mem, + kimage->segment[i].mem + kimage->segment[i].memsz, + kimage->segment[i].memsz, + kimage->segment[i].memsz / PAGE_SIZE); + } +} + +void machine_kexec_cleanup(struct kimage *kimage) +{ + /* Empty routine needed to avoid build errors. */ +} + +/** + * machine_kexec_prepare - Prepare for a kexec reboot. + * + * Called from the core kexec code when a kernel image is loaded. + * Forbid loading a kexec kernel if we have no way of hotplugging cpus or cpus + * are stuck in the kernel. This avoids a panic once we hit machine_kexec(). + */ +int machine_kexec_prepare(struct kimage *kimage) +{ + kimage_start = kimage->start; + + kexec_image_info(kimage); + + if (kimage->type != KEXEC_TYPE_CRASH && cpus_are_stuck_in_kernel()) { + pr_err("Can't kexec: CPUs are stuck in the kernel.\n"); + return -EBUSY; + } + + return 0; +} + +/** + * kexec_list_flush - Helper to flush the kimage list and source pages to PoC. + */ +static void kexec_list_flush(struct kimage *kimage) +{ + kimage_entry_t *entry; + + for (entry = &kimage->head; ; entry++) { + unsigned int flag; + void *addr; + + /* flush the list entries. */ + __flush_dcache_area(entry, sizeof(kimage_entry_t)); + + flag = *entry & IND_FLAGS; + if (flag == IND_DONE) + break; + + addr = phys_to_virt(*entry & PAGE_MASK); + + switch (flag) { + case IND_INDIRECTION: + /* Set entry point just before the new list page. */ + entry = (kimage_entry_t *)addr - 1; + break; + case IND_SOURCE: + /* flush the source pages. */ + __flush_dcache_area(addr, PAGE_SIZE); + break; + case IND_DESTINATION: + break; + default: + BUG(); + } + } +} + +/** + * kexec_segment_flush - Helper to flush the kimage segments to PoC. + */ +static void kexec_segment_flush(const struct kimage *kimage) +{ + unsigned long i; + + pr_debug("%s:\n", __func__); + + for (i = 0; i < kimage->nr_segments; i++) { + pr_debug(" segment[%lu]: %016lx - %016lx, 0x%lx bytes, %lu pages\n", + i, + kimage->segment[i].mem, + kimage->segment[i].mem + kimage->segment[i].memsz, + kimage->segment[i].memsz, + kimage->segment[i].memsz / PAGE_SIZE); + + __flush_dcache_area(phys_to_virt(kimage->segment[i].mem), + kimage->segment[i].memsz); + } +} + +/** + * machine_kexec - Do the kexec reboot. + * + * Called from the core kexec code for a sys_reboot with LINUX_REBOOT_CMD_KEXEC. + */ +void machine_kexec(struct kimage *kimage) +{ + phys_addr_t reboot_code_buffer_phys; + void *reboot_code_buffer; + + /* + * New cpus may have become stuck_in_kernel after we loaded the image. + */ + BUG_ON(cpus_are_stuck_in_kernel() || (num_online_cpus() > 1)); + + reboot_code_buffer_phys = page_to_phys(kimage->control_code_page); + reboot_code_buffer = phys_to_virt(reboot_code_buffer_phys); + + kexec_image_info(kimage); + + pr_debug("%s:%d: control_code_page: %p\n", __func__, __LINE__, + kimage->control_code_page); + pr_debug("%s:%d: reboot_code_buffer_phys: %pa\n", __func__, __LINE__, + &reboot_code_buffer_phys); + pr_debug("%s:%d: reboot_code_buffer: %p\n", __func__, __LINE__, + reboot_code_buffer); + pr_debug("%s:%d: relocate_new_kernel: %p\n", __func__, __LINE__, + arm64_relocate_new_kernel); + pr_debug("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n", + __func__, __LINE__, arm64_relocate_new_kernel_size, + arm64_relocate_new_kernel_size); + + /* + * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use + * after the kernel is shut down. + */ + memcpy(reboot_code_buffer, arm64_relocate_new_kernel, + arm64_relocate_new_kernel_size); + + /* Flush the reboot_code_buffer in preparation for its execution. */ + __flush_dcache_area(reboot_code_buffer, arm64_relocate_new_kernel_size); + flush_icache_range((uintptr_t)reboot_code_buffer, + arm64_relocate_new_kernel_size); + + /* Flush the kimage list and its buffers. */ + kexec_list_flush(kimage); + + /* Flush the new image if already in place. */ + if (kimage->head & IND_DONE) + kexec_segment_flush(kimage); + + pr_info("Bye!\n"); + + /* Disable all DAIF exceptions. */ + asm volatile ("msr daifset, #0xf" : : : "memory"); + + /* + * cpu_soft_restart will shutdown the MMU, disable data caches, then + * transfer control to the reboot_code_buffer which contains a copy of + * the arm64_relocate_new_kernel routine. arm64_relocate_new_kernel + * uses physical addressing to relocate the new image to its final + * position and transfers control to the image entry point when the + * relocation is complete. + */ + + cpu_soft_restart(1, reboot_code_buffer_phys, kimage->head, + kimage_start, 0); + + BUG(); /* Should never get here. */ +} + +void machine_crash_shutdown(struct pt_regs *regs) +{ + /* Empty routine needed to avoid build errors. */ +} diff --git a/arch/arm64/kernel/pci.c b/arch/arm64/kernel/pci.c index 3c4e308b4..acf387224 100644 --- a/arch/arm64/kernel/pci.c +++ b/arch/arm64/kernel/pci.c @@ -17,6 +17,9 @@ #include <linux/mm.h> #include <linux/of_pci.h> #include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/pci-acpi.h> +#include <linux/pci-ecam.h> #include <linux/slab.h> /* @@ -36,25 +39,17 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res, return res->start; } -/** - * pcibios_enable_device - Enable I/O and memory. - * @dev: PCI device to be enabled - * @mask: bitmask of BARs to enable - */ -int pcibios_enable_device(struct pci_dev *dev, int mask) -{ - if (pci_has_flag(PCI_PROBE_ONLY)) - return 0; - - return pci_enable_resources(dev, mask); -} - /* - * Try to assign the IRQ number from DT when adding a new device + * Try to assign the IRQ number when probing a new device */ -int pcibios_add_device(struct pci_dev *dev) +int pcibios_alloc_irq(struct pci_dev *dev) { - dev->irq = of_irq_parse_and_map_pci(dev, 0, 0); + if (acpi_disabled) + dev->irq = of_irq_parse_and_map_pci(dev, 0, 0); +#ifdef CONFIG_ACPI + else + return acpi_pci_irq_enable(dev); +#endif return 0; } @@ -65,13 +60,21 @@ int pcibios_add_device(struct pci_dev *dev) int raw_pci_read(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 *val) { - return -ENXIO; + struct pci_bus *b = pci_find_bus(domain, bus); + + if (!b) + return PCIBIOS_DEVICE_NOT_FOUND; + return b->ops->read(b, devfn, reg, len, val); } int raw_pci_write(unsigned int domain, unsigned int bus, unsigned int devfn, int reg, int len, u32 val) { - return -ENXIO; + struct pci_bus *b = pci_find_bus(domain, bus); + + if (!b) + return PCIBIOS_DEVICE_NOT_FOUND; + return b->ops->write(b, devfn, reg, len, val); } #ifdef CONFIG_NUMA @@ -85,10 +88,124 @@ EXPORT_SYMBOL(pcibus_to_node); #endif #ifdef CONFIG_ACPI -/* Root bridge scanning */ + +struct acpi_pci_generic_root_info { + struct acpi_pci_root_info common; + struct pci_config_window *cfg; /* config space mapping */ +}; + +int acpi_pci_bus_find_domain_nr(struct pci_bus *bus) +{ + struct pci_config_window *cfg = bus->sysdata; + struct acpi_device *adev = to_acpi_device(cfg->parent); + struct acpi_pci_root *root = acpi_driver_data(adev); + + return root->segment; +} + +int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge) +{ + if (!acpi_disabled) { + struct pci_config_window *cfg = bridge->bus->sysdata; + struct acpi_device *adev = to_acpi_device(cfg->parent); + ACPI_COMPANION_SET(&bridge->dev, adev); + } + + return 0; +} + +/* + * Lookup the bus range for the domain in MCFG, and set up config space + * mapping. + */ +static struct pci_config_window * +pci_acpi_setup_ecam_mapping(struct acpi_pci_root *root) +{ + struct resource *bus_res = &root->secondary; + u16 seg = root->segment; + struct pci_config_window *cfg; + struct resource cfgres; + unsigned int bsz; + + /* Use address from _CBA if present, otherwise lookup MCFG */ + if (!root->mcfg_addr) + root->mcfg_addr = pci_mcfg_lookup(seg, bus_res); + + if (!root->mcfg_addr) { + dev_err(&root->device->dev, "%04x:%pR ECAM region not found\n", + seg, bus_res); + return NULL; + } + + bsz = 1 << pci_generic_ecam_ops.bus_shift; + cfgres.start = root->mcfg_addr + bus_res->start * bsz; + cfgres.end = cfgres.start + resource_size(bus_res) * bsz - 1; + cfgres.flags = IORESOURCE_MEM; + cfg = pci_ecam_create(&root->device->dev, &cfgres, bus_res, + &pci_generic_ecam_ops); + if (IS_ERR(cfg)) { + dev_err(&root->device->dev, "%04x:%pR error %ld mapping ECAM\n", + seg, bus_res, PTR_ERR(cfg)); + return NULL; + } + + return cfg; +} + +/* release_info: free resources allocated by init_info */ +static void pci_acpi_generic_release_info(struct acpi_pci_root_info *ci) +{ + struct acpi_pci_generic_root_info *ri; + + ri = container_of(ci, struct acpi_pci_generic_root_info, common); + pci_ecam_free(ri->cfg); + kfree(ri); +} + +static struct acpi_pci_root_ops acpi_pci_root_ops = { + .release_info = pci_acpi_generic_release_info, +}; + +/* Interface called from ACPI code to setup PCI host controller */ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) { - /* TODO: Should be revisited when implementing PCI on ACPI */ - return NULL; + int node = acpi_get_node(root->device->handle); + struct acpi_pci_generic_root_info *ri; + struct pci_bus *bus, *child; + + ri = kzalloc_node(sizeof(*ri), GFP_KERNEL, node); + if (!ri) + return NULL; + + ri->cfg = pci_acpi_setup_ecam_mapping(root); + if (!ri->cfg) { + kfree(ri); + return NULL; + } + + acpi_pci_root_ops.pci_ops = &ri->cfg->ops->pci_ops; + bus = acpi_pci_root_create(root, &acpi_pci_root_ops, &ri->common, + ri->cfg); + if (!bus) + return NULL; + + pci_bus_size_bridges(bus); + pci_bus_assign_resources(bus); + + list_for_each_entry(child, &bus->children, node) + pcie_bus_configure_settings(child); + + return bus; } + +void pcibios_add_bus(struct pci_bus *bus) +{ + acpi_pci_add_bus(bus); +} + +void pcibios_remove_bus(struct pci_bus *bus) +{ + acpi_pci_remove_bus(bus); +} + #endif diff --git a/arch/arm64/kernel/probes/Makefile b/arch/arm64/kernel/probes/Makefile new file mode 100644 index 000000000..ce06312e3 --- /dev/null +++ b/arch/arm64/kernel/probes/Makefile @@ -0,0 +1,3 @@ +obj-$(CONFIG_KPROBES) += kprobes.o decode-insn.o \ + kprobes_trampoline.o \ + simulate-insn.o diff --git a/arch/arm64/kernel/probes/decode-insn.c b/arch/arm64/kernel/probes/decode-insn.c new file mode 100644 index 000000000..37e47a9d6 --- /dev/null +++ b/arch/arm64/kernel/probes/decode-insn.c @@ -0,0 +1,174 @@ +/* + * arch/arm64/kernel/probes/decode-insn.c + * + * Copyright (C) 2013 Linaro Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/kprobes.h> +#include <linux/module.h> +#include <asm/kprobes.h> +#include <asm/insn.h> +#include <asm/sections.h> + +#include "decode-insn.h" +#include "simulate-insn.h" + +static bool __kprobes aarch64_insn_is_steppable(u32 insn) +{ + /* + * Branch instructions will write a new value into the PC which is + * likely to be relative to the XOL address and therefore invalid. + * Deliberate generation of an exception during stepping is also not + * currently safe. Lastly, MSR instructions can do any number of nasty + * things we can't handle during single-stepping. + */ + if (aarch64_get_insn_class(insn) == AARCH64_INSN_CLS_BR_SYS) { + if (aarch64_insn_is_branch(insn) || + aarch64_insn_is_msr_imm(insn) || + aarch64_insn_is_msr_reg(insn) || + aarch64_insn_is_exception(insn) || + aarch64_insn_is_eret(insn)) + return false; + + /* + * The MRS instruction may not return a correct value when + * executing in the single-stepping environment. We do make one + * exception, for reading the DAIF bits. + */ + if (aarch64_insn_is_mrs(insn)) + return aarch64_insn_extract_system_reg(insn) + != AARCH64_INSN_SPCLREG_DAIF; + + /* + * The HINT instruction is is problematic when single-stepping, + * except for the NOP case. + */ + if (aarch64_insn_is_hint(insn)) + return aarch64_insn_is_nop(insn); + + return true; + } + + /* + * Instructions which load PC relative literals are not going to work + * when executed from an XOL slot. Instructions doing an exclusive + * load/store are not going to complete successfully when single-step + * exception handling happens in the middle of the sequence. + */ + if (aarch64_insn_uses_literal(insn) || + aarch64_insn_is_exclusive(insn)) + return false; + + return true; +} + +/* Return: + * INSN_REJECTED If instruction is one not allowed to kprobe, + * INSN_GOOD If instruction is supported and uses instruction slot, + * INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot. + */ +static enum kprobe_insn __kprobes +arm_probe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi) +{ + /* + * Instructions reading or modifying the PC won't work from the XOL + * slot. + */ + if (aarch64_insn_is_steppable(insn)) + return INSN_GOOD; + + if (aarch64_insn_is_bcond(insn)) { + asi->handler = simulate_b_cond; + } else if (aarch64_insn_is_cbz(insn) || + aarch64_insn_is_cbnz(insn)) { + asi->handler = simulate_cbz_cbnz; + } else if (aarch64_insn_is_tbz(insn) || + aarch64_insn_is_tbnz(insn)) { + asi->handler = simulate_tbz_tbnz; + } else if (aarch64_insn_is_adr_adrp(insn)) { + asi->handler = simulate_adr_adrp; + } else if (aarch64_insn_is_b(insn) || + aarch64_insn_is_bl(insn)) { + asi->handler = simulate_b_bl; + } else if (aarch64_insn_is_br(insn) || + aarch64_insn_is_blr(insn) || + aarch64_insn_is_ret(insn)) { + asi->handler = simulate_br_blr_ret; + } else if (aarch64_insn_is_ldr_lit(insn)) { + asi->handler = simulate_ldr_literal; + } else if (aarch64_insn_is_ldrsw_lit(insn)) { + asi->handler = simulate_ldrsw_literal; + } else { + /* + * Instruction cannot be stepped out-of-line and we don't + * (yet) simulate it. + */ + return INSN_REJECTED; + } + + return INSN_GOOD_NO_SLOT; +} + +static bool __kprobes +is_probed_address_atomic(kprobe_opcode_t *scan_start, kprobe_opcode_t *scan_end) +{ + while (scan_start > scan_end) { + /* + * atomic region starts from exclusive load and ends with + * exclusive store. + */ + if (aarch64_insn_is_store_ex(le32_to_cpu(*scan_start))) + return false; + else if (aarch64_insn_is_load_ex(le32_to_cpu(*scan_start))) + return true; + scan_start--; + } + + return false; +} + +enum kprobe_insn __kprobes +arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi) +{ + enum kprobe_insn decoded; + kprobe_opcode_t insn = le32_to_cpu(*addr); + kprobe_opcode_t *scan_start = addr - 1; + kprobe_opcode_t *scan_end = addr - MAX_ATOMIC_CONTEXT_SIZE; +#if defined(CONFIG_MODULES) && defined(MODULES_VADDR) + struct module *mod; +#endif + + if (addr >= (kprobe_opcode_t *)_text && + scan_end < (kprobe_opcode_t *)_text) + scan_end = (kprobe_opcode_t *)_text; +#if defined(CONFIG_MODULES) && defined(MODULES_VADDR) + else { + preempt_disable(); + mod = __module_address((unsigned long)addr); + if (mod && within_module_init((unsigned long)addr, mod) && + !within_module_init((unsigned long)scan_end, mod)) + scan_end = (kprobe_opcode_t *)mod->init_layout.base; + else if (mod && within_module_core((unsigned long)addr, mod) && + !within_module_core((unsigned long)scan_end, mod)) + scan_end = (kprobe_opcode_t *)mod->core_layout.base; + preempt_enable(); + } +#endif + decoded = arm_probe_decode_insn(insn, asi); + + if (decoded == INSN_REJECTED || + is_probed_address_atomic(scan_start, scan_end)) + return INSN_REJECTED; + + return decoded; +} diff --git a/arch/arm64/kernel/probes/decode-insn.h b/arch/arm64/kernel/probes/decode-insn.h new file mode 100644 index 000000000..d43828964 --- /dev/null +++ b/arch/arm64/kernel/probes/decode-insn.h @@ -0,0 +1,35 @@ +/* + * arch/arm64/kernel/probes/decode-insn.h + * + * Copyright (C) 2013 Linaro Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef _ARM_KERNEL_KPROBES_ARM64_H +#define _ARM_KERNEL_KPROBES_ARM64_H + +/* + * ARM strongly recommends a limit of 128 bytes between LoadExcl and + * StoreExcl instructions in a single thread of execution. So keep the + * max atomic context size as 32. + */ +#define MAX_ATOMIC_CONTEXT_SIZE (128 / sizeof(kprobe_opcode_t)) + +enum kprobe_insn { + INSN_REJECTED, + INSN_GOOD_NO_SLOT, + INSN_GOOD, +}; + +enum kprobe_insn __kprobes +arm_kprobe_decode_insn(kprobe_opcode_t *addr, struct arch_specific_insn *asi); + +#endif /* _ARM_KERNEL_KPROBES_ARM64_H */ diff --git a/arch/arm64/kernel/probes/kprobes.c b/arch/arm64/kernel/probes/kprobes.c new file mode 100644 index 000000000..c6b0f4062 --- /dev/null +++ b/arch/arm64/kernel/probes/kprobes.c @@ -0,0 +1,665 @@ +/* + * arch/arm64/kernel/probes/kprobes.c + * + * Kprobes support for ARM64 + * + * Copyright (C) 2013 Linaro Limited. + * Author: Sandeepa Prabhu <sandeepa.prabhu@linaro.org> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + * + */ +#include <linux/kasan.h> +#include <linux/kernel.h> +#include <linux/kprobes.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/stop_machine.h> +#include <linux/stringify.h> +#include <asm/traps.h> +#include <asm/ptrace.h> +#include <asm/cacheflush.h> +#include <asm/debug-monitors.h> +#include <asm/system_misc.h> +#include <asm/insn.h> +#include <asm/uaccess.h> +#include <asm/irq.h> +#include <asm-generic/sections.h> + +#include "decode-insn.h" + +DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL; +DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk); + +static void __kprobes +post_kprobe_handler(struct kprobe_ctlblk *, struct pt_regs *); + +static void __kprobes arch_prepare_ss_slot(struct kprobe *p) +{ + /* prepare insn slot */ + p->ainsn.insn[0] = cpu_to_le32(p->opcode); + + flush_icache_range((uintptr_t) (p->ainsn.insn), + (uintptr_t) (p->ainsn.insn) + + MAX_INSN_SIZE * sizeof(kprobe_opcode_t)); + + /* + * Needs restoring of return address after stepping xol. + */ + p->ainsn.restore = (unsigned long) p->addr + + sizeof(kprobe_opcode_t); +} + +static void __kprobes arch_prepare_simulate(struct kprobe *p) +{ + /* This instructions is not executed xol. No need to adjust the PC */ + p->ainsn.restore = 0; +} + +static void __kprobes arch_simulate_insn(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + if (p->ainsn.handler) + p->ainsn.handler((u32)p->opcode, (long)p->addr, regs); + + /* single step simulated, now go for post processing */ + post_kprobe_handler(kcb, regs); +} + +int __kprobes arch_prepare_kprobe(struct kprobe *p) +{ + unsigned long probe_addr = (unsigned long)p->addr; + extern char __start_rodata[]; + extern char __end_rodata[]; + + if (probe_addr & 0x3) + return -EINVAL; + + /* copy instruction */ + p->opcode = le32_to_cpu(*p->addr); + + if (in_exception_text(probe_addr)) + return -EINVAL; + if (probe_addr >= (unsigned long) __start_rodata && + probe_addr <= (unsigned long) __end_rodata) + return -EINVAL; + + /* decode instruction */ + switch (arm_kprobe_decode_insn(p->addr, &p->ainsn)) { + case INSN_REJECTED: /* insn not supported */ + return -EINVAL; + + case INSN_GOOD_NO_SLOT: /* insn need simulation */ + p->ainsn.insn = NULL; + break; + + case INSN_GOOD: /* instruction uses slot */ + p->ainsn.insn = get_insn_slot(); + if (!p->ainsn.insn) + return -ENOMEM; + break; + }; + + /* prepare the instruction */ + if (p->ainsn.insn) + arch_prepare_ss_slot(p); + else + arch_prepare_simulate(p); + + return 0; +} + +static int __kprobes patch_text(kprobe_opcode_t *addr, u32 opcode) +{ + void *addrs[1]; + u32 insns[1]; + + addrs[0] = (void *)addr; + insns[0] = (u32)opcode; + + return aarch64_insn_patch_text(addrs, insns, 1); +} + +/* arm kprobe: install breakpoint in text */ +void __kprobes arch_arm_kprobe(struct kprobe *p) +{ + patch_text(p->addr, BRK64_OPCODE_KPROBES); +} + +/* disarm kprobe: remove breakpoint from text */ +void __kprobes arch_disarm_kprobe(struct kprobe *p) +{ + patch_text(p->addr, p->opcode); +} + +void __kprobes arch_remove_kprobe(struct kprobe *p) +{ + if (p->ainsn.insn) { + free_insn_slot(p->ainsn.insn, 0); + p->ainsn.insn = NULL; + } +} + +static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + kcb->prev_kprobe.kp = kprobe_running(); + kcb->prev_kprobe.status = kcb->kprobe_status; +} + +static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb) +{ + __this_cpu_write(current_kprobe, kcb->prev_kprobe.kp); + kcb->kprobe_status = kcb->prev_kprobe.status; +} + +static void __kprobes set_current_kprobe(struct kprobe *p) +{ + __this_cpu_write(current_kprobe, p); +} + +/* + * The D-flag (Debug mask) is set (masked) upon debug exception entry. + * Kprobes needs to clear (unmask) D-flag -ONLY- in case of recursive + * probe i.e. when probe hit from kprobe handler context upon + * executing the pre/post handlers. In this case we return with + * D-flag clear so that single-stepping can be carried-out. + * + * Leave D-flag set in all other cases. + */ +static void __kprobes +spsr_set_debug_flag(struct pt_regs *regs, int mask) +{ + unsigned long spsr = regs->pstate; + + if (mask) + spsr |= PSR_D_BIT; + else + spsr &= ~PSR_D_BIT; + + regs->pstate = spsr; +} + +/* + * Interrupts need to be disabled before single-step mode is set, and not + * reenabled until after single-step mode ends. + * Without disabling interrupt on local CPU, there is a chance of + * interrupt occurrence in the period of exception return and start of + * out-of-line single-step, that result in wrongly single stepping + * into the interrupt handler. + */ +static void __kprobes kprobes_save_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + kcb->saved_irqflag = regs->pstate; + regs->pstate |= PSR_I_BIT; +} + +static void __kprobes kprobes_restore_local_irqflag(struct kprobe_ctlblk *kcb, + struct pt_regs *regs) +{ + if (kcb->saved_irqflag & PSR_I_BIT) + regs->pstate |= PSR_I_BIT; + else + regs->pstate &= ~PSR_I_BIT; +} + +static void __kprobes +set_ss_context(struct kprobe_ctlblk *kcb, unsigned long addr) +{ + kcb->ss_ctx.ss_pending = true; + kcb->ss_ctx.match_addr = addr + sizeof(kprobe_opcode_t); +} + +static void __kprobes clear_ss_context(struct kprobe_ctlblk *kcb) +{ + kcb->ss_ctx.ss_pending = false; + kcb->ss_ctx.match_addr = 0; +} + +static void __kprobes setup_singlestep(struct kprobe *p, + struct pt_regs *regs, + struct kprobe_ctlblk *kcb, int reenter) +{ + unsigned long slot; + + if (reenter) { + save_previous_kprobe(kcb); + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_REENTER; + } else { + kcb->kprobe_status = KPROBE_HIT_SS; + } + + + if (p->ainsn.insn) { + /* prepare for single stepping */ + slot = (unsigned long)p->ainsn.insn; + + set_ss_context(kcb, slot); /* mark pending ss */ + + if (kcb->kprobe_status == KPROBE_REENTER) + spsr_set_debug_flag(regs, 0); + else + WARN_ON(regs->pstate & PSR_D_BIT); + + /* IRQs and single stepping do not mix well. */ + kprobes_save_local_irqflag(kcb, regs); + kernel_enable_single_step(regs); + instruction_pointer_set(regs, slot); + } else { + /* insn simulation */ + arch_simulate_insn(p, regs); + } +} + +static int __kprobes reenter_kprobe(struct kprobe *p, + struct pt_regs *regs, + struct kprobe_ctlblk *kcb) +{ + switch (kcb->kprobe_status) { + case KPROBE_HIT_SSDONE: + case KPROBE_HIT_ACTIVE: + kprobes_inc_nmissed_count(p); + setup_singlestep(p, regs, kcb, 1); + break; + case KPROBE_HIT_SS: + case KPROBE_REENTER: + pr_warn("Unrecoverable kprobe detected at %p.\n", p->addr); + dump_kprobe(p); + BUG(); + break; + default: + WARN_ON(1); + return 0; + } + + return 1; +} + +static void __kprobes +post_kprobe_handler(struct kprobe_ctlblk *kcb, struct pt_regs *regs) +{ + struct kprobe *cur = kprobe_running(); + + if (!cur) + return; + + /* return addr restore if non-branching insn */ + if (cur->ainsn.restore != 0) + instruction_pointer_set(regs, cur->ainsn.restore); + + /* restore back original saved kprobe variables and continue */ + if (kcb->kprobe_status == KPROBE_REENTER) { + restore_previous_kprobe(kcb); + return; + } + /* call post handler */ + kcb->kprobe_status = KPROBE_HIT_SSDONE; + if (cur->post_handler) { + /* post_handler can hit breakpoint and single step + * again, so we enable D-flag for recursive exception. + */ + cur->post_handler(cur, regs, 0); + } + + reset_current_kprobe(); +} + +int __kprobes kprobe_fault_handler(struct pt_regs *regs, unsigned int fsr) +{ + struct kprobe *cur = kprobe_running(); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + switch (kcb->kprobe_status) { + case KPROBE_HIT_SS: + case KPROBE_REENTER: + /* + * We are here because the instruction being single + * stepped caused a page fault. We reset the current + * kprobe and the ip points back to the probe address + * and allow the page fault handler to continue as a + * normal page fault. + */ + instruction_pointer_set(regs, (unsigned long) cur->addr); + if (!instruction_pointer(regs)) + BUG(); + + kernel_disable_single_step(); + if (kcb->kprobe_status == KPROBE_REENTER) + spsr_set_debug_flag(regs, 1); + + if (kcb->kprobe_status == KPROBE_REENTER) + restore_previous_kprobe(kcb); + else + reset_current_kprobe(); + + break; + case KPROBE_HIT_ACTIVE: + case KPROBE_HIT_SSDONE: + /* + * We increment the nmissed count for accounting, + * we can also use npre/npostfault count for accounting + * these specific fault cases. + */ + kprobes_inc_nmissed_count(cur); + + /* + * We come here because instructions in the pre/post + * handler caused the page_fault, this could happen + * if handler tries to access user space by + * copy_from_user(), get_user() etc. Let the + * user-specified handler try to fix it first. + */ + if (cur->fault_handler && cur->fault_handler(cur, regs, fsr)) + return 1; + + /* + * In case the user-specified fault handler returned + * zero, try to fix up. + */ + if (fixup_exception(regs)) + return 1; + } + return 0; +} + +int __kprobes kprobe_exceptions_notify(struct notifier_block *self, + unsigned long val, void *data) +{ + return NOTIFY_DONE; +} + +static void __kprobes kprobe_handler(struct pt_regs *regs) +{ + struct kprobe *p, *cur_kprobe; + struct kprobe_ctlblk *kcb; + unsigned long addr = instruction_pointer(regs); + + kcb = get_kprobe_ctlblk(); + cur_kprobe = kprobe_running(); + + p = get_kprobe((kprobe_opcode_t *) addr); + + if (p) { + if (cur_kprobe) { + if (reenter_kprobe(p, regs, kcb)) + return; + } else { + /* Probe hit */ + set_current_kprobe(p); + kcb->kprobe_status = KPROBE_HIT_ACTIVE; + + /* + * If we have no pre-handler or it returned 0, we + * continue with normal processing. If we have a + * pre-handler and it returned non-zero, it prepped + * for calling the break_handler below on re-entry, + * so get out doing nothing more here. + * + * pre_handler can hit a breakpoint and can step thru + * before return, keep PSTATE D-flag enabled until + * pre_handler return back. + */ + if (!p->pre_handler || !p->pre_handler(p, regs)) { + setup_singlestep(p, regs, kcb, 0); + return; + } + } + } else if ((le32_to_cpu(*(kprobe_opcode_t *) addr) == + BRK64_OPCODE_KPROBES) && cur_kprobe) { + /* We probably hit a jprobe. Call its break handler. */ + if (cur_kprobe->break_handler && + cur_kprobe->break_handler(cur_kprobe, regs)) { + setup_singlestep(cur_kprobe, regs, kcb, 0); + return; + } + } + /* + * The breakpoint instruction was removed right + * after we hit it. Another cpu has removed + * either a probepoint or a debugger breakpoint + * at this address. In either case, no further + * handling of this interrupt is appropriate. + * Return back to original instruction, and continue. + */ +} + +static int __kprobes +kprobe_ss_hit(struct kprobe_ctlblk *kcb, unsigned long addr) +{ + if ((kcb->ss_ctx.ss_pending) + && (kcb->ss_ctx.match_addr == addr)) { + clear_ss_context(kcb); /* clear pending ss */ + return DBG_HOOK_HANDLED; + } + /* not ours, kprobes should ignore it */ + return DBG_HOOK_ERROR; +} + +int __kprobes +kprobe_single_step_handler(struct pt_regs *regs, unsigned int esr) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + int retval; + + /* return error if this is not our step */ + retval = kprobe_ss_hit(kcb, instruction_pointer(regs)); + + if (retval == DBG_HOOK_HANDLED) { + kprobes_restore_local_irqflag(kcb, regs); + kernel_disable_single_step(); + + if (kcb->kprobe_status == KPROBE_REENTER) + spsr_set_debug_flag(regs, 1); + + post_kprobe_handler(kcb, regs); + } + + return retval; +} + +int __kprobes +kprobe_breakpoint_handler(struct pt_regs *regs, unsigned int esr) +{ + kprobe_handler(regs); + return DBG_HOOK_HANDLED; +} + +int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct jprobe *jp = container_of(p, struct jprobe, kp); + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + kcb->jprobe_saved_regs = *regs; + /* + * Since we can't be sure where in the stack frame "stacked" + * pass-by-value arguments are stored we just don't try to + * duplicate any of the stack. Do not use jprobes on functions that + * use more than 64 bytes (after padding each to an 8 byte boundary) + * of arguments, or pass individual arguments larger than 16 bytes. + */ + + instruction_pointer_set(regs, (unsigned long) jp->entry); + preempt_disable(); + pause_graph_tracing(); + return 1; +} + +void __kprobes jprobe_return(void) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + + /* + * Jprobe handler return by entering break exception, + * encoded same as kprobe, but with following conditions + * -a special PC to identify it from the other kprobes. + * -restore stack addr to original saved pt_regs + */ + asm volatile(" mov sp, %0 \n" + "jprobe_return_break: brk %1 \n" + : + : "r" (kcb->jprobe_saved_regs.sp), + "I" (BRK64_ESR_KPROBES) + : "memory"); + + unreachable(); +} + +int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs) +{ + struct kprobe_ctlblk *kcb = get_kprobe_ctlblk(); + long stack_addr = kcb->jprobe_saved_regs.sp; + long orig_sp = kernel_stack_pointer(regs); + struct jprobe *jp = container_of(p, struct jprobe, kp); + extern const char jprobe_return_break[]; + + if (instruction_pointer(regs) != (u64) jprobe_return_break) + return 0; + + if (orig_sp != stack_addr) { + struct pt_regs *saved_regs = + (struct pt_regs *)kcb->jprobe_saved_regs.sp; + pr_err("current sp %lx does not match saved sp %lx\n", + orig_sp, stack_addr); + pr_err("Saved registers for jprobe %p\n", jp); + show_regs(saved_regs); + pr_err("Current registers\n"); + show_regs(regs); + BUG(); + } + unpause_graph_tracing(); + *regs = kcb->jprobe_saved_regs; + preempt_enable_no_resched(); + return 1; +} + +bool arch_within_kprobe_blacklist(unsigned long addr) +{ + extern char __idmap_text_start[], __idmap_text_end[]; + extern char __hyp_idmap_text_start[], __hyp_idmap_text_end[]; + + if ((addr >= (unsigned long)__kprobes_text_start && + addr < (unsigned long)__kprobes_text_end) || + (addr >= (unsigned long)__entry_text_start && + addr < (unsigned long)__entry_text_end) || + (addr >= (unsigned long)__idmap_text_start && + addr < (unsigned long)__idmap_text_end) || + !!search_exception_tables(addr)) + return true; + + if (!is_kernel_in_hyp_mode()) { + if ((addr >= (unsigned long)__hyp_text_start && + addr < (unsigned long)__hyp_text_end) || + (addr >= (unsigned long)__hyp_idmap_text_start && + addr < (unsigned long)__hyp_idmap_text_end)) + return true; + } + + return false; +} + +void __kprobes __used *trampoline_probe_handler(struct pt_regs *regs) +{ + struct kretprobe_instance *ri = NULL; + struct hlist_head *head, empty_rp; + struct hlist_node *tmp; + unsigned long flags, orig_ret_address = 0; + unsigned long trampoline_address = + (unsigned long)&kretprobe_trampoline; + kprobe_opcode_t *correct_ret_addr = NULL; + + INIT_HLIST_HEAD(&empty_rp); + kretprobe_hash_lock(current, &head, &flags); + + /* + * It is possible to have multiple instances associated with a given + * task either because multiple functions in the call path have + * return probes installed on them, and/or more than one + * return probe was registered for a target function. + * + * We can handle this because: + * - instances are always pushed into the head of the list + * - when multiple return probes are registered for the same + * function, the (chronologically) first instance's ret_addr + * will be the real return address, and all the rest will + * point to kretprobe_trampoline. + */ + hlist_for_each_entry_safe(ri, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; + + orig_ret_address = (unsigned long)ri->ret_addr; + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; + } + + kretprobe_assert(ri, orig_ret_address, trampoline_address); + + correct_ret_addr = ri->ret_addr; + hlist_for_each_entry_safe(ri, tmp, head, hlist) { + if (ri->task != current) + /* another task is sharing our hash bucket */ + continue; + + orig_ret_address = (unsigned long)ri->ret_addr; + if (ri->rp && ri->rp->handler) { + __this_cpu_write(current_kprobe, &ri->rp->kp); + get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE; + ri->ret_addr = correct_ret_addr; + ri->rp->handler(ri, regs); + __this_cpu_write(current_kprobe, NULL); + } + + recycle_rp_inst(ri, &empty_rp); + + if (orig_ret_address != trampoline_address) + /* + * This is the real return address. Any other + * instances associated with this task are for + * other calls deeper on the call stack + */ + break; + } + + kretprobe_hash_unlock(current, &flags); + + hlist_for_each_entry_safe(ri, tmp, &empty_rp, hlist) { + hlist_del(&ri->hlist); + kfree(ri); + } + return (void *)orig_ret_address; +} + +void __kprobes arch_prepare_kretprobe(struct kretprobe_instance *ri, + struct pt_regs *regs) +{ + ri->ret_addr = (kprobe_opcode_t *)regs->regs[30]; + + /* replace return addr (x30) with trampoline */ + regs->regs[30] = (long)&kretprobe_trampoline; +} + +int __kprobes arch_trampoline_kprobe(struct kprobe *p) +{ + return 0; +} + +int __init arch_init_kprobes(void) +{ + return 0; +} diff --git a/arch/arm64/kernel/probes/kprobes_trampoline.S b/arch/arm64/kernel/probes/kprobes_trampoline.S new file mode 100644 index 000000000..5d6e7f146 --- /dev/null +++ b/arch/arm64/kernel/probes/kprobes_trampoline.S @@ -0,0 +1,81 @@ +/* + * trampoline entry and return code for kretprobes. + */ + +#include <linux/linkage.h> +#include <asm/asm-offsets.h> +#include <asm/assembler.h> + + .text + + .macro save_all_base_regs + stp x0, x1, [sp, #S_X0] + stp x2, x3, [sp, #S_X2] + stp x4, x5, [sp, #S_X4] + stp x6, x7, [sp, #S_X6] + stp x8, x9, [sp, #S_X8] + stp x10, x11, [sp, #S_X10] + stp x12, x13, [sp, #S_X12] + stp x14, x15, [sp, #S_X14] + stp x16, x17, [sp, #S_X16] + stp x18, x19, [sp, #S_X18] + stp x20, x21, [sp, #S_X20] + stp x22, x23, [sp, #S_X22] + stp x24, x25, [sp, #S_X24] + stp x26, x27, [sp, #S_X26] + stp x28, x29, [sp, #S_X28] + add x0, sp, #S_FRAME_SIZE + stp lr, x0, [sp, #S_LR] + /* + * Construct a useful saved PSTATE + */ + mrs x0, nzcv + mrs x1, daif + orr x0, x0, x1 + mrs x1, CurrentEL + orr x0, x0, x1 + mrs x1, SPSel + orr x0, x0, x1 + stp xzr, x0, [sp, #S_PC] + .endm + + .macro restore_all_base_regs + ldr x0, [sp, #S_PSTATE] + and x0, x0, #(PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT) + msr nzcv, x0 + ldp x0, x1, [sp, #S_X0] + ldp x2, x3, [sp, #S_X2] + ldp x4, x5, [sp, #S_X4] + ldp x6, x7, [sp, #S_X6] + ldp x8, x9, [sp, #S_X8] + ldp x10, x11, [sp, #S_X10] + ldp x12, x13, [sp, #S_X12] + ldp x14, x15, [sp, #S_X14] + ldp x16, x17, [sp, #S_X16] + ldp x18, x19, [sp, #S_X18] + ldp x20, x21, [sp, #S_X20] + ldp x22, x23, [sp, #S_X22] + ldp x24, x25, [sp, #S_X24] + ldp x26, x27, [sp, #S_X26] + ldp x28, x29, [sp, #S_X28] + .endm + +ENTRY(kretprobe_trampoline) + sub sp, sp, #S_FRAME_SIZE + + save_all_base_regs + + mov x0, sp + bl trampoline_probe_handler + /* + * Replace trampoline address in lr with actual orig_ret_addr return + * address. + */ + mov lr, x0 + + restore_all_base_regs + + add sp, sp, #S_FRAME_SIZE + ret + +ENDPROC(kretprobe_trampoline) diff --git a/arch/arm64/kernel/probes/simulate-insn.c b/arch/arm64/kernel/probes/simulate-insn.c new file mode 100644 index 000000000..8977ce9d0 --- /dev/null +++ b/arch/arm64/kernel/probes/simulate-insn.c @@ -0,0 +1,217 @@ +/* + * arch/arm64/kernel/probes/simulate-insn.c + * + * Copyright (C) 2013 Linaro Limited. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#include <linux/kernel.h> +#include <linux/kprobes.h> + +#include "simulate-insn.h" + +#define sign_extend(x, signbit) \ + ((x) | (0 - ((x) & (1 << (signbit))))) + +#define bbl_displacement(insn) \ + sign_extend(((insn) & 0x3ffffff) << 2, 27) + +#define bcond_displacement(insn) \ + sign_extend(((insn >> 5) & 0x7ffff) << 2, 20) + +#define cbz_displacement(insn) \ + sign_extend(((insn >> 5) & 0x7ffff) << 2, 20) + +#define tbz_displacement(insn) \ + sign_extend(((insn >> 5) & 0x3fff) << 2, 15) + +#define ldr_displacement(insn) \ + sign_extend(((insn >> 5) & 0x7ffff) << 2, 20) + +static inline void set_x_reg(struct pt_regs *regs, int reg, u64 val) +{ + if (reg < 31) + regs->regs[reg] = val; +} + +static inline void set_w_reg(struct pt_regs *regs, int reg, u64 val) +{ + if (reg < 31) + regs->regs[reg] = lower_32_bits(val); +} + +static inline u64 get_x_reg(struct pt_regs *regs, int reg) +{ + if (reg < 31) + return regs->regs[reg]; + else + return 0; +} + +static inline u32 get_w_reg(struct pt_regs *regs, int reg) +{ + if (reg < 31) + return lower_32_bits(regs->regs[reg]); + else + return 0; +} + +static bool __kprobes check_cbz(u32 opcode, struct pt_regs *regs) +{ + int xn = opcode & 0x1f; + + return (opcode & (1 << 31)) ? + (get_x_reg(regs, xn) == 0) : (get_w_reg(regs, xn) == 0); +} + +static bool __kprobes check_cbnz(u32 opcode, struct pt_regs *regs) +{ + int xn = opcode & 0x1f; + + return (opcode & (1 << 31)) ? + (get_x_reg(regs, xn) != 0) : (get_w_reg(regs, xn) != 0); +} + +static bool __kprobes check_tbz(u32 opcode, struct pt_regs *regs) +{ + int xn = opcode & 0x1f; + int bit_pos = ((opcode & (1 << 31)) >> 26) | ((opcode >> 19) & 0x1f); + + return ((get_x_reg(regs, xn) >> bit_pos) & 0x1) == 0; +} + +static bool __kprobes check_tbnz(u32 opcode, struct pt_regs *regs) +{ + int xn = opcode & 0x1f; + int bit_pos = ((opcode & (1 << 31)) >> 26) | ((opcode >> 19) & 0x1f); + + return ((get_x_reg(regs, xn) >> bit_pos) & 0x1) != 0; +} + +/* + * instruction simulation functions + */ +void __kprobes +simulate_adr_adrp(u32 opcode, long addr, struct pt_regs *regs) +{ + long imm, xn, val; + + xn = opcode & 0x1f; + imm = ((opcode >> 3) & 0x1ffffc) | ((opcode >> 29) & 0x3); + imm = sign_extend(imm, 20); + if (opcode & 0x80000000) + val = (imm<<12) + (addr & 0xfffffffffffff000); + else + val = imm + addr; + + set_x_reg(regs, xn, val); + + instruction_pointer_set(regs, instruction_pointer(regs) + 4); +} + +void __kprobes +simulate_b_bl(u32 opcode, long addr, struct pt_regs *regs) +{ + int disp = bbl_displacement(opcode); + + /* Link register is x30 */ + if (opcode & (1 << 31)) + set_x_reg(regs, 30, addr + 4); + + instruction_pointer_set(regs, addr + disp); +} + +void __kprobes +simulate_b_cond(u32 opcode, long addr, struct pt_regs *regs) +{ + int disp = 4; + + if (aarch32_opcode_cond_checks[opcode & 0xf](regs->pstate & 0xffffffff)) + disp = bcond_displacement(opcode); + + instruction_pointer_set(regs, addr + disp); +} + +void __kprobes +simulate_br_blr_ret(u32 opcode, long addr, struct pt_regs *regs) +{ + int xn = (opcode >> 5) & 0x1f; + + /* update pc first in case we're doing a "blr lr" */ + instruction_pointer_set(regs, get_x_reg(regs, xn)); + + /* Link register is x30 */ + if (((opcode >> 21) & 0x3) == 1) + set_x_reg(regs, 30, addr + 4); +} + +void __kprobes +simulate_cbz_cbnz(u32 opcode, long addr, struct pt_regs *regs) +{ + int disp = 4; + + if (opcode & (1 << 24)) { + if (check_cbnz(opcode, regs)) + disp = cbz_displacement(opcode); + } else { + if (check_cbz(opcode, regs)) + disp = cbz_displacement(opcode); + } + instruction_pointer_set(regs, addr + disp); +} + +void __kprobes +simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs) +{ + int disp = 4; + + if (opcode & (1 << 24)) { + if (check_tbnz(opcode, regs)) + disp = tbz_displacement(opcode); + } else { + if (check_tbz(opcode, regs)) + disp = tbz_displacement(opcode); + } + instruction_pointer_set(regs, addr + disp); +} + +void __kprobes +simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs) +{ + u64 *load_addr; + int xn = opcode & 0x1f; + int disp; + + disp = ldr_displacement(opcode); + load_addr = (u64 *) (addr + disp); + + if (opcode & (1 << 30)) /* x0-x30 */ + set_x_reg(regs, xn, *load_addr); + else /* w0-w30 */ + set_w_reg(regs, xn, *load_addr); + + instruction_pointer_set(regs, instruction_pointer(regs) + 4); +} + +void __kprobes +simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs) +{ + s32 *load_addr; + int xn = opcode & 0x1f; + int disp; + + disp = ldr_displacement(opcode); + load_addr = (s32 *) (addr + disp); + + set_x_reg(regs, xn, *load_addr); + + instruction_pointer_set(regs, instruction_pointer(regs) + 4); +} diff --git a/arch/arm64/kernel/probes/simulate-insn.h b/arch/arm64/kernel/probes/simulate-insn.h new file mode 100644 index 000000000..050bde683 --- /dev/null +++ b/arch/arm64/kernel/probes/simulate-insn.h @@ -0,0 +1,28 @@ +/* + * arch/arm64/kernel/probes/simulate-insn.h + * + * Copyright (C) 2013 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License for more details. + */ + +#ifndef _ARM_KERNEL_KPROBES_SIMULATE_INSN_H +#define _ARM_KERNEL_KPROBES_SIMULATE_INSN_H + +void simulate_adr_adrp(u32 opcode, long addr, struct pt_regs *regs); +void simulate_b_bl(u32 opcode, long addr, struct pt_regs *regs); +void simulate_b_cond(u32 opcode, long addr, struct pt_regs *regs); +void simulate_br_blr_ret(u32 opcode, long addr, struct pt_regs *regs); +void simulate_cbz_cbnz(u32 opcode, long addr, struct pt_regs *regs); +void simulate_tbz_tbnz(u32 opcode, long addr, struct pt_regs *regs); +void simulate_ldr_literal(u32 opcode, long addr, struct pt_regs *regs); +void simulate_ldrsw_literal(u32 opcode, long addr, struct pt_regs *regs); + +#endif /* _ARM_KERNEL_KPROBES_SIMULATE_INSN_H */ diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 3f6cd5c52..e0c81da60 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -48,6 +48,107 @@ #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> +struct pt_regs_offset { + const char *name; + int offset; +}; + +#define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} +#define REG_OFFSET_END {.name = NULL, .offset = 0} +#define GPR_OFFSET_NAME(r) \ + {.name = "x" #r, .offset = offsetof(struct pt_regs, regs[r])} + +static const struct pt_regs_offset regoffset_table[] = { + GPR_OFFSET_NAME(0), + GPR_OFFSET_NAME(1), + GPR_OFFSET_NAME(2), + GPR_OFFSET_NAME(3), + GPR_OFFSET_NAME(4), + GPR_OFFSET_NAME(5), + GPR_OFFSET_NAME(6), + GPR_OFFSET_NAME(7), + GPR_OFFSET_NAME(8), + GPR_OFFSET_NAME(9), + GPR_OFFSET_NAME(10), + GPR_OFFSET_NAME(11), + GPR_OFFSET_NAME(12), + GPR_OFFSET_NAME(13), + GPR_OFFSET_NAME(14), + GPR_OFFSET_NAME(15), + GPR_OFFSET_NAME(16), + GPR_OFFSET_NAME(17), + GPR_OFFSET_NAME(18), + GPR_OFFSET_NAME(19), + GPR_OFFSET_NAME(20), + GPR_OFFSET_NAME(21), + GPR_OFFSET_NAME(22), + GPR_OFFSET_NAME(23), + GPR_OFFSET_NAME(24), + GPR_OFFSET_NAME(25), + GPR_OFFSET_NAME(26), + GPR_OFFSET_NAME(27), + GPR_OFFSET_NAME(28), + GPR_OFFSET_NAME(29), + GPR_OFFSET_NAME(30), + {.name = "lr", .offset = offsetof(struct pt_regs, regs[30])}, + REG_OFFSET_NAME(sp), + REG_OFFSET_NAME(pc), + REG_OFFSET_NAME(pstate), + 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_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. + */ +static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) +{ + return ((addr & ~(THREAD_SIZE - 1)) == + (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) || + on_irq_stack(addr, raw_smp_processor_id()); +} + +/** + * 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; +} + /* * TODO: does not yet catch signals sent when the child dies. * in exit.c or in signal.c. @@ -1246,13 +1347,13 @@ static void tracehook_report_syscall(struct pt_regs *regs, asmlinkage int syscall_trace_enter(struct pt_regs *regs) { - /* Do the secure computing check first; failures should be fast. */ - if (secure_computing() == -1) - return -1; - if (test_thread_flag(TIF_SYSCALL_TRACE)) tracehook_report_syscall(regs, PTRACE_SYSCALL_ENTER); + /* Do the secure computing after ptrace; failures should be fast. */ + if (secure_computing(NULL) == -1) + return -1; + if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, regs->syscallno); diff --git a/arch/arm64/kernel/relocate_kernel.S b/arch/arm64/kernel/relocate_kernel.S new file mode 100644 index 000000000..51b73cdde --- /dev/null +++ b/arch/arm64/kernel/relocate_kernel.S @@ -0,0 +1,130 @@ +/* + * kexec for arm64 + * + * Copyright (C) Linaro. + * Copyright (C) Huawei Futurewei Technologies. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/kexec.h> +#include <linux/linkage.h> + +#include <asm/assembler.h> +#include <asm/kexec.h> +#include <asm/page.h> +#include <asm/sysreg.h> + +/* + * arm64_relocate_new_kernel - Put a 2nd stage image in place and boot it. + * + * The memory that the old kernel occupies may be overwritten when coping the + * new image to its final location. To assure that the + * arm64_relocate_new_kernel routine which does that copy is not overwritten, + * all code and data needed by arm64_relocate_new_kernel must be between the + * symbols arm64_relocate_new_kernel and arm64_relocate_new_kernel_end. The + * machine_kexec() routine will copy arm64_relocate_new_kernel to the kexec + * control_code_page, a special page which has been set up to be preserved + * during the copy operation. + */ +ENTRY(arm64_relocate_new_kernel) + + /* Setup the list loop variables. */ + mov x17, x1 /* x17 = kimage_start */ + mov x16, x0 /* x16 = kimage_head */ + dcache_line_size x15, x0 /* x15 = dcache line size */ + mov x14, xzr /* x14 = entry ptr */ + mov x13, xzr /* x13 = copy dest */ + + /* Clear the sctlr_el2 flags. */ + mrs x0, CurrentEL + cmp x0, #CurrentEL_EL2 + b.ne 1f + mrs x0, sctlr_el2 + ldr x1, =SCTLR_ELx_FLAGS + bic x0, x0, x1 + msr sctlr_el2, x0 + isb +1: + + /* Check if the new image needs relocation. */ + tbnz x16, IND_DONE_BIT, .Ldone + +.Lloop: + and x12, x16, PAGE_MASK /* x12 = addr */ + + /* Test the entry flags. */ +.Ltest_source: + tbz x16, IND_SOURCE_BIT, .Ltest_indirection + + /* Invalidate dest page to PoC. */ + mov x0, x13 + add x20, x0, #PAGE_SIZE + sub x1, x15, #1 + bic x0, x0, x1 +2: dc ivac, x0 + add x0, x0, x15 + cmp x0, x20 + b.lo 2b + dsb sy + + mov x20, x13 + mov x21, x12 + copy_page x20, x21, x0, x1, x2, x3, x4, x5, x6, x7 + + /* dest += PAGE_SIZE */ + add x13, x13, PAGE_SIZE + b .Lnext + +.Ltest_indirection: + tbz x16, IND_INDIRECTION_BIT, .Ltest_destination + + /* ptr = addr */ + mov x14, x12 + b .Lnext + +.Ltest_destination: + tbz x16, IND_DESTINATION_BIT, .Lnext + + /* dest = addr */ + mov x13, x12 + +.Lnext: + /* entry = *ptr++ */ + ldr x16, [x14], #8 + + /* while (!(entry & DONE)) */ + tbz x16, IND_DONE_BIT, .Lloop + +.Ldone: + /* wait for writes from copy_page to finish */ + dsb nsh + ic iallu + dsb nsh + isb + + /* Start new image. */ + mov x0, xzr + mov x1, xzr + mov x2, xzr + mov x3, xzr + br x17 + +ENDPROC(arm64_relocate_new_kernel) + +.ltorg + +.align 3 /* To keep the 64-bit values below naturally aligned. */ + +.Lcopy_end: +.org KEXEC_CONTROL_PAGE_SIZE + +/* + * arm64_relocate_new_kernel_size - Number of bytes to copy to the + * control_code_page. + */ +.globl arm64_relocate_new_kernel_size +arm64_relocate_new_kernel_size: + .quad .Lcopy_end - arm64_relocate_new_kernel diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 3279defab..536dce22f 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -39,9 +39,7 @@ #include <linux/fs.h> #include <linux/proc_fs.h> #include <linux/memblock.h> -#include <linux/of_iommu.h> #include <linux/of_fdt.h> -#include <linux/of_platform.h> #include <linux/efi.h> #include <linux/psci.h> @@ -202,7 +200,7 @@ static void __init request_standard_resources(void) struct resource *res; kernel_code.start = virt_to_phys(_text); - kernel_code.end = virt_to_phys(_etext - 1); + kernel_code.end = virt_to_phys(__init_begin - 1); kernel_data.start = virt_to_phys(_sdata); kernel_data.end = virt_to_phys(_end - 1); @@ -257,14 +255,17 @@ void __init setup_arch(char **cmdline_p) */ cpu_uninstall_idmap(); + xen_early_init(); efi_init(); arm64_memblock_init(); + paging_init(); + + acpi_table_upgrade(); + /* Parse the ACPI tables for possible boot-time configuration */ acpi_boot_table_init(); - paging_init(); - if (acpi_disabled) unflatten_device_tree(); @@ -281,8 +282,6 @@ void __init setup_arch(char **cmdline_p) else psci_acpi_init(); - xen_early_init(); - cpu_read_bootcpu_ops(); smp_init_cpus(); smp_build_mpidr_hash(); @@ -302,19 +301,6 @@ void __init setup_arch(char **cmdline_p) } } -static int __init arm64_device_init(void) -{ - if (of_have_populated_dt()) { - of_iommu_init(); - of_platform_populate(NULL, of_default_bus_match_table, - NULL, NULL); - } else if (acpi_disabled) { - pr_crit("Device tree not populated\n"); - } - return 0; -} -arch_initcall_sync(arm64_device_init); - static int __init topology_init(void) { int i; diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c index 95e32d9c6..3ff173e92 100644 --- a/arch/arm64/kernel/smp.c +++ b/arch/arm64/kernel/smp.c @@ -553,6 +553,8 @@ acpi_map_gic_cpu_interface(struct acpi_madt_generic_interrupt *processor) */ acpi_set_mailbox_entry(cpu_count, processor); + early_map_cpu_to_node(cpu_count, acpi_numa_get_nid(cpu_count, hwid)); + cpu_count++; } @@ -653,9 +655,9 @@ void __init smp_init_cpus(void) acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, acpi_parse_gic_cpu_interface, 0); - if (cpu_count > NR_CPUS) - pr_warn("no. of cores (%d) greater than configured maximum of %d - clipping\n", - cpu_count, NR_CPUS); + if (cpu_count > nr_cpu_ids) + pr_warn("Number of cores (%d) exceeds configured maximum of %d - clipping\n", + cpu_count, nr_cpu_ids); if (!bootcpu_valid) { pr_err("missing boot CPU MPIDR, not enabling secondaries\n"); @@ -669,7 +671,7 @@ void __init smp_init_cpus(void) * with entries in cpu_logical_map while initializing the cpus. * If the cpu set-up fails, invalidate the cpu_logical_map entry. */ - for (i = 1; i < NR_CPUS; i++) { + for (i = 1; i < nr_cpu_ids; i++) { if (cpu_logical_map(i) != INVALID_HWID) { if (smp_cpu_setup(i)) cpu_logical_map(i) = INVALID_HWID; diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index d9751a476..d34fd7217 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -43,6 +43,9 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) unsigned long fp = frame->fp; unsigned long irq_stack_ptr; + if (!tsk) + tsk = current; + /* * Switching between stacks is valid when tracing current and in * non-preemptible context. @@ -67,7 +70,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame) frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8)); #ifdef CONFIG_FUNCTION_GRAPH_TRACER - if (tsk && tsk->ret_stack && + if (tsk->ret_stack && (frame->pc == (unsigned long)return_to_handler)) { /* * This is a case where function graph tracer has diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 2a4301261..df0675084 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -41,6 +41,7 @@ #include <asm/stacktrace.h> #include <asm/exception.h> #include <asm/system_misc.h> +#include <asm/sysreg.h> static const char *handler[]= { "Synchronous Abort", @@ -52,15 +53,14 @@ static const char *handler[]= { int show_unhandled_signals = 1; /* - * Dump out the contents of some memory nicely... + * Dump out the contents of some kernel memory nicely... */ static void dump_mem(const char *lvl, const char *str, unsigned long bottom, - unsigned long top, bool compat) + unsigned long top) { unsigned long first; mm_segment_t fs; int i; - unsigned int width = compat ? 4 : 8; /* * We need to switch to kernel mode so that we can use __get_user @@ -78,22 +78,15 @@ static void dump_mem(const char *lvl, const char *str, unsigned long bottom, memset(str, ' ', sizeof(str)); str[sizeof(str) - 1] = '\0'; - for (p = first, i = 0; i < (32 / width) - && p < top; i++, p += width) { + for (p = first, i = 0; i < (32 / 8) + && p < top; i++, p += 8) { if (p >= bottom && p < top) { unsigned long val; - if (width == 8) { - if (__get_user(val, (unsigned long *)p) == 0) - sprintf(str + i * 17, " %016lx", val); - else - sprintf(str + i * 17, " ????????????????"); - } else { - if (__get_user(val, (unsigned int *)p) == 0) - sprintf(str + i * 9, " %08lx", val); - else - sprintf(str + i * 9, " ????????"); - } + if (__get_user(val, (unsigned long *)p) == 0) + sprintf(str + i * 17, " %016lx", val); + else + sprintf(str + i * 17, " ????????????????"); } } printk("%s%04lx:%s\n", lvl, first & 0xffff, str); @@ -149,6 +142,11 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) unsigned long irq_stack_ptr; int skip; + pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); + + if (!tsk) + tsk = current; + /* * Switching between stacks is valid when tracing current and in * non-preemptible context. @@ -158,11 +156,6 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) else irq_stack_ptr = 0; - pr_debug("%s(regs = %p tsk = %p)\n", __func__, regs, tsk); - - if (!tsk) - tsk = current; - if (tsk == current) { frame.fp = (unsigned long)__builtin_frame_address(0); frame.sp = current_stack_pointer; @@ -216,7 +209,7 @@ static void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk) stack = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr); dump_mem("", "Exception stack", stack, - stack + sizeof(struct pt_regs), false); + stack + sizeof(struct pt_regs)); } } } @@ -254,10 +247,9 @@ static int __die(const char *str, int err, struct thread_info *thread, pr_emerg("Process %.*s (pid: %d, stack limit = 0x%p)\n", TASK_COMM_LEN, tsk->comm, task_pid_nr(tsk), thread + 1); - if (!user_mode(regs) || in_interrupt()) { + if (!user_mode(regs)) { dump_mem(KERN_EMERG, "Stack: ", regs->sp, - THREAD_SIZE + (unsigned long)task_stack_page(tsk), - compat_user_mode(regs)); + THREAD_SIZE + (unsigned long)task_stack_page(tsk)); dump_backtrace(regs, tsk); dump_instr(KERN_EMERG, regs); } @@ -373,11 +365,59 @@ exit: return fn ? fn(regs, instr) : 1; } -asmlinkage void __exception do_undefinstr(struct pt_regs *regs) +static void force_signal_inject(int signal, int code, struct pt_regs *regs, + unsigned long address) { siginfo_t info; void __user *pc = (void __user *)instruction_pointer(regs); + const char *desc; + + switch (signal) { + case SIGILL: + desc = "undefined instruction"; + break; + case SIGSEGV: + desc = "illegal memory access"; + break; + default: + desc = "bad mode"; + break; + } + + if (unhandled_signal(current, signal) && + show_unhandled_signals_ratelimited()) { + pr_info("%s[%d]: %s: pc=%p\n", + current->comm, task_pid_nr(current), desc, pc); + dump_instr(KERN_INFO, regs); + } + + info.si_signo = signal; + info.si_errno = 0; + info.si_code = code; + info.si_addr = pc; + + arm64_notify_die(desc, regs, &info, 0); +} + +/* + * Set up process info to signal segmentation fault - called on access error. + */ +void arm64_notify_segfault(struct pt_regs *regs, unsigned long addr) +{ + int code; + down_read(¤t->mm->mmap_sem); + if (find_vma(current->mm, addr) == NULL) + code = SEGV_MAPERR; + else + code = SEGV_ACCERR; + up_read(¤t->mm->mmap_sem); + + force_signal_inject(SIGSEGV, code, regs, addr); +} + +asmlinkage void __exception do_undefinstr(struct pt_regs *regs) +{ /* check for AArch32 breakpoint instructions */ if (!aarch32_break_handler(regs)) return; @@ -385,18 +425,66 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs) if (call_undef_hook(regs) == 0) return; - if (unhandled_signal(current, SIGILL) && show_unhandled_signals_ratelimited()) { - pr_info("%s[%d]: undefined instruction: pc=%p\n", - current->comm, task_pid_nr(current), pc); - dump_instr(KERN_INFO, regs); - } + force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0); +} - info.si_signo = SIGILL; - info.si_errno = 0; - info.si_code = ILL_ILLOPC; - info.si_addr = pc; +void cpu_enable_cache_maint_trap(void *__unused) +{ + config_sctlr_el1(SCTLR_EL1_UCI, 0); +} - arm64_notify_die("Oops - undefined instruction", regs, &info, 0); +#define __user_cache_maint(insn, address, res) \ + asm volatile ( \ + "1: " insn ", %1\n" \ + " mov %w0, #0\n" \ + "2:\n" \ + " .pushsection .fixup,\"ax\"\n" \ + " .align 2\n" \ + "3: mov %w0, %w2\n" \ + " b 2b\n" \ + " .popsection\n" \ + _ASM_EXTABLE(1b, 3b) \ + : "=r" (res) \ + : "r" (address), "i" (-EFAULT) ) + +asmlinkage void __exception do_sysinstr(unsigned int esr, struct pt_regs *regs) +{ + unsigned long address; + int ret; + + /* if this is a write with: Op0=1, Op2=1, Op1=3, CRn=7 */ + if ((esr & 0x01fffc01) == 0x0012dc00) { + int rt = (esr >> 5) & 0x1f; + int crm = (esr >> 1) & 0x0f; + + address = (rt == 31) ? 0 : regs->regs[rt]; + + switch (crm) { + case 11: /* DC CVAU, gets promoted */ + __user_cache_maint("dc civac", address, ret); + break; + case 10: /* DC CVAC, gets promoted */ + __user_cache_maint("dc civac", address, ret); + break; + case 14: /* DC CIVAC */ + __user_cache_maint("dc civac", address, ret); + break; + case 5: /* IC IVAU */ + __user_cache_maint("ic ivau", address, ret); + break; + default: + force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0); + return; + } + } else { + force_signal_inject(SIGILL, ILL_ILLOPC, regs, 0); + return; + } + + if (ret) + arm64_notify_segfault(regs, address); + else + regs->pc += 4; } long compat_arm_syscall(struct pt_regs *regs); @@ -465,7 +553,7 @@ static const char *esr_class_str[] = { const char *esr_get_class_string(u32 esr) { - return esr_class_str[esr >> ESR_ELx_EC_SHIFT]; + return esr_class_str[ESR_ELx_EC(esr)]; } /* diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c index 9fefb0058..076312b17 100644 --- a/arch/arm64/kernel/vdso.c +++ b/arch/arm64/kernel/vdso.c @@ -214,10 +214,16 @@ void update_vsyscall(struct timekeeper *tk) vdso_data->wtm_clock_nsec = tk->wall_to_monotonic.tv_nsec; if (!use_syscall) { + /* tkr_mono.cycle_last == tkr_raw.cycle_last */ vdso_data->cs_cycle_last = tk->tkr_mono.cycle_last; + vdso_data->raw_time_sec = tk->raw_time.tv_sec; + vdso_data->raw_time_nsec = tk->raw_time.tv_nsec; vdso_data->xtime_clock_sec = tk->xtime_sec; vdso_data->xtime_clock_nsec = tk->tkr_mono.xtime_nsec; - vdso_data->cs_mult = tk->tkr_mono.mult; + /* tkr_raw.xtime_nsec == 0 */ + vdso_data->cs_mono_mult = tk->tkr_mono.mult; + vdso_data->cs_raw_mult = tk->tkr_raw.mult; + /* tkr_mono.shift == tkr_raw.shift */ vdso_data->cs_shift = tk->tkr_mono.shift; } diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile index b467fd0a3..62c84f7cb 100644 --- a/arch/arm64/kernel/vdso/Makefile +++ b/arch/arm64/kernel/vdso/Makefile @@ -23,7 +23,7 @@ GCOV_PROFILE := n ccflags-y += -Wl,-shared obj-y += vdso.o -extra-y += vdso.lds vdso-offsets.h +extra-y += vdso.lds CPPFLAGS_vdso.lds += -P -C -U$(ARCH) # Force dependency (incbin is bad) @@ -42,11 +42,10 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE gen-vdsosym := $(srctree)/$(src)/gen_vdso_offsets.sh quiet_cmd_vdsosym = VDSOSYM $@ define cmd_vdsosym - $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ && \ - cp $@ include/generated/ + $(NM) $< | $(gen-vdsosym) | LC_ALL=C sort > $@ endef -$(obj)/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE +include/generated/vdso-offsets.h: $(obj)/vdso.so.dbg FORCE $(call if_changed,vdsosym) # Assembly rules for the .S files diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S index efa79e8d4..e00b4671b 100644 --- a/arch/arm64/kernel/vdso/gettimeofday.S +++ b/arch/arm64/kernel/vdso/gettimeofday.S @@ -26,24 +26,109 @@ #define NSEC_PER_SEC_HI16 0x3b9a vdso_data .req x6 -use_syscall .req w7 -seqcnt .req w8 +seqcnt .req w7 +w_tmp .req w8 +x_tmp .req x8 + +/* + * Conventions for macro arguments: + * - An argument is write-only if its name starts with "res". + * - All other arguments are read-only, unless otherwise specified. + */ .macro seqcnt_acquire 9999: ldr seqcnt, [vdso_data, #VDSO_TB_SEQ_COUNT] tbnz seqcnt, #0, 9999b dmb ishld - ldr use_syscall, [vdso_data, #VDSO_USE_SYSCALL] .endm - .macro seqcnt_read, cnt + .macro seqcnt_check fail dmb ishld - ldr \cnt, [vdso_data, #VDSO_TB_SEQ_COUNT] + ldr w_tmp, [vdso_data, #VDSO_TB_SEQ_COUNT] + cmp w_tmp, seqcnt + b.ne \fail .endm - .macro seqcnt_check, cnt, fail - cmp \cnt, seqcnt - b.ne \fail + .macro syscall_check fail + ldr w_tmp, [vdso_data, #VDSO_USE_SYSCALL] + cbnz w_tmp, \fail + .endm + + .macro get_nsec_per_sec res + mov \res, #NSEC_PER_SEC_LO16 + movk \res, #NSEC_PER_SEC_HI16, lsl #16 + .endm + + /* + * Returns the clock delta, in nanoseconds left-shifted by the clock + * shift. + */ + .macro get_clock_shifted_nsec res, cycle_last, mult + /* Read the virtual counter. */ + isb + mrs x_tmp, cntvct_el0 + /* Calculate cycle delta and convert to ns. */ + sub \res, x_tmp, \cycle_last + /* We can only guarantee 56 bits of precision. */ + movn x_tmp, #0xff00, lsl #48 + and \res, x_tmp, \res + mul \res, \res, \mult + .endm + + /* + * Returns in res_{sec,nsec} the REALTIME timespec, based on the + * "wall time" (xtime) and the clock_mono delta. + */ + .macro get_ts_realtime res_sec, res_nsec, \ + clock_nsec, xtime_sec, xtime_nsec, nsec_to_sec + add \res_nsec, \clock_nsec, \xtime_nsec + udiv x_tmp, \res_nsec, \nsec_to_sec + add \res_sec, \xtime_sec, x_tmp + msub \res_nsec, x_tmp, \nsec_to_sec, \res_nsec + .endm + + /* + * Returns in res_{sec,nsec} the timespec based on the clock_raw delta, + * used for CLOCK_MONOTONIC_RAW. + */ + .macro get_ts_clock_raw res_sec, res_nsec, clock_nsec, nsec_to_sec + udiv \res_sec, \clock_nsec, \nsec_to_sec + msub \res_nsec, \res_sec, \nsec_to_sec, \clock_nsec + .endm + + /* sec and nsec are modified in place. */ + .macro add_ts sec, nsec, ts_sec, ts_nsec, nsec_to_sec + /* Add timespec. */ + add \sec, \sec, \ts_sec + add \nsec, \nsec, \ts_nsec + + /* Normalise the new timespec. */ + cmp \nsec, \nsec_to_sec + b.lt 9999f + sub \nsec, \nsec, \nsec_to_sec + add \sec, \sec, #1 +9999: + cmp \nsec, #0 + b.ge 9998f + add \nsec, \nsec, \nsec_to_sec + sub \sec, \sec, #1 +9998: + .endm + + .macro clock_gettime_return, shift=0 + .if \shift == 1 + lsr x11, x11, x12 + .endif + stp x10, x11, [x1, #TSPEC_TV_SEC] + mov x0, xzr + ret + .endm + + .macro jump_slot jumptable, index, label + .if (. - \jumptable) != 4 * (\index) + .error "Jump slot index mismatch" + .endif + b \label .endm .text @@ -51,18 +136,25 @@ seqcnt .req w8 /* int __kernel_gettimeofday(struct timeval *tv, struct timezone *tz); */ ENTRY(__kernel_gettimeofday) .cfi_startproc - mov x2, x30 - .cfi_register x30, x2 - - /* Acquire the sequence counter and get the timespec. */ adr vdso_data, _vdso_data -1: seqcnt_acquire - cbnz use_syscall, 4f - /* If tv is NULL, skip to the timezone code. */ cbz x0, 2f - bl __do_get_tspec - seqcnt_check w9, 1b + + /* Compute the time of day. */ +1: seqcnt_acquire + syscall_check fail=4f + ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] + /* w11 = cs_mono_mult, w12 = cs_shift */ + ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT] + ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] + seqcnt_check fail=1b + + get_nsec_per_sec res=x9 + lsl x9, x9, x12 + + get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 + get_ts_realtime res_sec=x10, res_nsec=x11, \ + clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 /* Convert ns to us. */ mov x13, #1000 @@ -76,95 +168,126 @@ ENTRY(__kernel_gettimeofday) stp w4, w5, [x1, #TZ_MINWEST] 3: mov x0, xzr - ret x2 + ret 4: /* Syscall fallback. */ mov x8, #__NR_gettimeofday svc #0 - ret x2 + ret .cfi_endproc ENDPROC(__kernel_gettimeofday) +#define JUMPSLOT_MAX CLOCK_MONOTONIC_COARSE + /* int __kernel_clock_gettime(clockid_t clock_id, struct timespec *tp); */ ENTRY(__kernel_clock_gettime) .cfi_startproc - cmp w0, #CLOCK_REALTIME - ccmp w0, #CLOCK_MONOTONIC, #0x4, ne - b.ne 2f + cmp w0, #JUMPSLOT_MAX + b.hi syscall + adr vdso_data, _vdso_data + adr x_tmp, jumptable + add x_tmp, x_tmp, w0, uxtw #2 + br x_tmp + + ALIGN +jumptable: + jump_slot jumptable, CLOCK_REALTIME, realtime + jump_slot jumptable, CLOCK_MONOTONIC, monotonic + b syscall + b syscall + jump_slot jumptable, CLOCK_MONOTONIC_RAW, monotonic_raw + jump_slot jumptable, CLOCK_REALTIME_COARSE, realtime_coarse + jump_slot jumptable, CLOCK_MONOTONIC_COARSE, monotonic_coarse + + .if (. - jumptable) != 4 * (JUMPSLOT_MAX + 1) + .error "Wrong jumptable size" + .endif + + ALIGN +realtime: + seqcnt_acquire + syscall_check fail=syscall + ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] + /* w11 = cs_mono_mult, w12 = cs_shift */ + ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT] + ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] + seqcnt_check fail=realtime - mov x2, x30 - .cfi_register x30, x2 + /* All computations are done with left-shifted nsecs. */ + get_nsec_per_sec res=x9 + lsl x9, x9, x12 - /* Get kernel timespec. */ - adr vdso_data, _vdso_data -1: seqcnt_acquire - cbnz use_syscall, 7f + get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 + get_ts_realtime res_sec=x10, res_nsec=x11, \ + clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 + clock_gettime_return, shift=1 - bl __do_get_tspec - seqcnt_check w9, 1b + ALIGN +monotonic: + seqcnt_acquire + syscall_check fail=syscall + ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] + /* w11 = cs_mono_mult, w12 = cs_shift */ + ldp w11, w12, [vdso_data, #VDSO_CS_MONO_MULT] + ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] + ldp x3, x4, [vdso_data, #VDSO_WTM_CLK_SEC] + seqcnt_check fail=monotonic - mov x30, x2 + /* All computations are done with left-shifted nsecs. */ + lsl x4, x4, x12 + get_nsec_per_sec res=x9 + lsl x9, x9, x12 - cmp w0, #CLOCK_MONOTONIC - b.ne 6f + get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 + get_ts_realtime res_sec=x10, res_nsec=x11, \ + clock_nsec=x15, xtime_sec=x13, xtime_nsec=x14, nsec_to_sec=x9 - /* Get wtm timespec. */ - ldp x13, x14, [vdso_data, #VDSO_WTM_CLK_SEC] + add_ts sec=x10, nsec=x11, ts_sec=x3, ts_nsec=x4, nsec_to_sec=x9 + clock_gettime_return, shift=1 - /* Check the sequence counter. */ - seqcnt_read w9 - seqcnt_check w9, 1b - b 4f -2: - cmp w0, #CLOCK_REALTIME_COARSE - ccmp w0, #CLOCK_MONOTONIC_COARSE, #0x4, ne - b.ne 8f + ALIGN +monotonic_raw: + seqcnt_acquire + syscall_check fail=syscall + ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] + /* w11 = cs_raw_mult, w12 = cs_shift */ + ldp w12, w11, [vdso_data, #VDSO_CS_SHIFT] + ldp x13, x14, [vdso_data, #VDSO_RAW_TIME_SEC] + seqcnt_check fail=monotonic_raw - /* xtime_coarse_nsec is already right-shifted */ - mov x12, #0 + /* All computations are done with left-shifted nsecs. */ + lsl x14, x14, x12 + get_nsec_per_sec res=x9 + lsl x9, x9, x12 - /* Get coarse timespec. */ - adr vdso_data, _vdso_data -3: seqcnt_acquire + get_clock_shifted_nsec res=x15, cycle_last=x10, mult=x11 + get_ts_clock_raw res_sec=x10, res_nsec=x11, \ + clock_nsec=x15, nsec_to_sec=x9 + + add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9 + clock_gettime_return, shift=1 + + ALIGN +realtime_coarse: + seqcnt_acquire ldp x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC] + seqcnt_check fail=realtime_coarse + clock_gettime_return - /* Get wtm timespec. */ + ALIGN +monotonic_coarse: + seqcnt_acquire + ldp x10, x11, [vdso_data, #VDSO_XTIME_CRS_SEC] ldp x13, x14, [vdso_data, #VDSO_WTM_CLK_SEC] + seqcnt_check fail=monotonic_coarse - /* Check the sequence counter. */ - seqcnt_read w9 - seqcnt_check w9, 3b + /* Computations are done in (non-shifted) nsecs. */ + get_nsec_per_sec res=x9 + add_ts sec=x10, nsec=x11, ts_sec=x13, ts_nsec=x14, nsec_to_sec=x9 + clock_gettime_return - cmp w0, #CLOCK_MONOTONIC_COARSE - b.ne 6f -4: - /* Add on wtm timespec. */ - add x10, x10, x13 - lsl x14, x14, x12 - add x11, x11, x14 - - /* Normalise the new timespec. */ - mov x15, #NSEC_PER_SEC_LO16 - movk x15, #NSEC_PER_SEC_HI16, lsl #16 - lsl x15, x15, x12 - cmp x11, x15 - b.lt 5f - sub x11, x11, x15 - add x10, x10, #1 -5: - cmp x11, #0 - b.ge 6f - add x11, x11, x15 - sub x10, x10, #1 - -6: /* Store to the user timespec. */ - lsr x11, x11, x12 - stp x10, x11, [x1, #TSPEC_TV_SEC] - mov x0, xzr - ret -7: - mov x30, x2 -8: /* Syscall fallback. */ + ALIGN +syscall: /* Syscall fallback. */ mov x8, #__NR_clock_gettime svc #0 ret @@ -176,6 +299,7 @@ ENTRY(__kernel_clock_getres) .cfi_startproc cmp w0, #CLOCK_REALTIME ccmp w0, #CLOCK_MONOTONIC, #0x4, ne + ccmp w0, #CLOCK_MONOTONIC_RAW, #0x4, ne b.ne 1f ldr x2, 5f @@ -203,46 +327,3 @@ ENTRY(__kernel_clock_getres) .quad CLOCK_COARSE_RES .cfi_endproc ENDPROC(__kernel_clock_getres) - -/* - * Read the current time from the architected counter. - * Expects vdso_data to be initialised. - * Clobbers the temporary registers (x9 - x15). - * Returns: - * - w9 = vDSO sequence counter - * - (x10, x11) = (ts->tv_sec, shifted ts->tv_nsec) - * - w12 = cs_shift - */ -ENTRY(__do_get_tspec) - .cfi_startproc - - /* Read from the vDSO data page. */ - ldr x10, [vdso_data, #VDSO_CS_CYCLE_LAST] - ldp x13, x14, [vdso_data, #VDSO_XTIME_CLK_SEC] - ldp w11, w12, [vdso_data, #VDSO_CS_MULT] - seqcnt_read w9 - - /* Read the virtual counter. */ - isb - mrs x15, cntvct_el0 - - /* Calculate cycle delta and convert to ns. */ - sub x10, x15, x10 - /* We can only guarantee 56 bits of precision. */ - movn x15, #0xff00, lsl #48 - and x10, x15, x10 - mul x10, x10, x11 - - /* Use the kernel time to calculate the new timespec. */ - mov x11, #NSEC_PER_SEC_LO16 - movk x11, #NSEC_PER_SEC_HI16, lsl #16 - lsl x11, x11, x12 - add x15, x10, x14 - udiv x14, x15, x11 - add x10, x13, x14 - mul x13, x14, x11 - sub x11, x15, x13 - - ret - .cfi_endproc -ENDPROC(__do_get_tspec) diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S index e564d4595..659963d40 100644 --- a/arch/arm64/kernel/vmlinux.lds.S +++ b/arch/arm64/kernel/vmlinux.lds.S @@ -103,6 +103,7 @@ SECTIONS *(.discard) *(.discard.*) *(.interp .dynamic) + *(.dynsym .dynstr .hash) } . = KIMAGE_VADDR + TEXT_OFFSET; @@ -118,9 +119,11 @@ SECTIONS __exception_text_end = .; IRQENTRY_TEXT SOFTIRQENTRY_TEXT + ENTRY_TEXT TEXT_TEXT SCHED_TEXT LOCK_TEXT + KPROBES_TEXT HYPERVISOR_TEXT IDMAP_TEXT HIBERNATE_TEXT @@ -131,12 +134,13 @@ SECTIONS } . = ALIGN(SEGMENT_ALIGN); - RO_DATA(PAGE_SIZE) /* everything from this point to */ - EXCEPTION_TABLE(8) /* _etext will be marked RO NX */ + _etext = .; /* End of text section */ + + RO_DATA(PAGE_SIZE) /* everything from this point to */ + EXCEPTION_TABLE(8) /* __init_begin will be marked RO NX */ NOTES . = ALIGN(SEGMENT_ALIGN); - _etext = .; /* End of text and rodata section */ __init_begin = .; INIT_TEXT_SECTION(8) @@ -171,19 +175,9 @@ SECTIONS .rela : ALIGN(8) { *(.rela .rela*) } - .dynsym : ALIGN(8) { - *(.dynsym) - } - .dynstr : { - *(.dynstr) - } - .hash : { - *(.hash) - } __rela_offset = ABSOLUTE(ADDR(.rela) - KIMAGE_VADDR); __rela_size = SIZEOF(.rela); - __dynsym_offset = ABSOLUTE(ADDR(.dynsym) - KIMAGE_VADDR); . = ALIGN(SEGMENT_ALIGN); __init_end = .; |