mirror_ubuntu-kernels/arch/arm/kernel/process.c
Ard Biesheuvel 50596b7559 ARM: smp: Store current pointer in TPIDRURO register if available
Now that the user space TLS register is assigned on every return to user
space, we can use it to keep the 'current' pointer while running in the
kernel. This removes the need to access it via thread_info, which is
located at the base of the stack, but will be moved out of there in a
subsequent patch.

Use the __builtin_thread_pointer() helper when available - this will
help GCC understand that reloading the value within the same function is
not necessary, even when using the per-task stack protector (which also
generates accesses via the TLS register). For example, the generated
code below loads TPIDRURO only once, and uses it to access both the
stack canary and the preempt_count fields.

<do_one_initcall>:
       e92d 41f0       stmdb   sp!, {r4, r5, r6, r7, r8, lr}
       ee1d 4f70       mrc     15, 0, r4, cr13, cr0, {3}
       4606            mov     r6, r0
       b094            sub     sp, #80 ; 0x50
       f8d4 34e8       ldr.w   r3, [r4, #1256] ; 0x4e8  <- stack canary
       9313            str     r3, [sp, #76]   ; 0x4c
       f8d4 8004       ldr.w   r8, [r4, #4]             <- preempt count

Co-developed-by: Keith Packard <keithpac@amazon.com>
Signed-off-by: Keith Packard <keithpac@amazon.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Tested-by: Amit Daniel Kachhap <amit.kachhap@arm.com>
2021-09-27 16:54:02 +02:00

444 lines
10 KiB
C

// SPDX-License-Identifier: GPL-2.0-only
/*
* linux/arch/arm/kernel/process.c
*
* Copyright (C) 1996-2000 Russell King - Converted to ARM.
* Original Copyright (C) 1995 Linus Torvalds
*/
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
#include <linux/sched/task.h>
#include <linux/sched/task_stack.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/user.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/elfcore.h>
#include <linux/pm.h>
#include <linux/tick.h>
#include <linux/utsname.h>
#include <linux/uaccess.h>
#include <linux/random.h>
#include <linux/hw_breakpoint.h>
#include <linux/leds.h>
#include <asm/processor.h>
#include <asm/thread_notify.h>
#include <asm/stacktrace.h>
#include <asm/system_misc.h>
#include <asm/mach/time.h>
#include <asm/tls.h>
#include <asm/vdso.h>
#include "signal.h"
#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
DEFINE_PER_CPU(struct task_struct *, __entry_task);
#endif
#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
#include <linux/stackprotector.h>
unsigned long __stack_chk_guard __read_mostly;
EXPORT_SYMBOL(__stack_chk_guard);
#endif
static const char *processor_modes[] __maybe_unused = {
"USER_26", "FIQ_26" , "IRQ_26" , "SVC_26" , "UK4_26" , "UK5_26" , "UK6_26" , "UK7_26" ,
"UK8_26" , "UK9_26" , "UK10_26", "UK11_26", "UK12_26", "UK13_26", "UK14_26", "UK15_26",
"USER_32", "FIQ_32" , "IRQ_32" , "SVC_32" , "UK4_32" , "UK5_32" , "MON_32" , "ABT_32" ,
"UK8_32" , "UK9_32" , "HYP_32", "UND_32" , "UK12_32", "UK13_32", "UK14_32", "SYS_32"
};
static const char *isa_modes[] __maybe_unused = {
"ARM" , "Thumb" , "Jazelle", "ThumbEE"
};
/*
* This is our default idle handler.
*/
void (*arm_pm_idle)(void);
/*
* Called from the core idle loop.
*/
void arch_cpu_idle(void)
{
if (arm_pm_idle)
arm_pm_idle();
else
cpu_do_idle();
raw_local_irq_enable();
}
void arch_cpu_idle_prepare(void)
{
local_fiq_enable();
}
void arch_cpu_idle_enter(void)
{
ledtrig_cpu(CPU_LED_IDLE_START);
#ifdef CONFIG_PL310_ERRATA_769419
wmb();
#endif
}
void arch_cpu_idle_exit(void)
{
ledtrig_cpu(CPU_LED_IDLE_END);
}
void __show_regs_alloc_free(struct pt_regs *regs)
{
int i;
/* check for r0 - r12 only */
for (i = 0; i < 13; i++) {
pr_alert("Register r%d information:", i);
mem_dump_obj((void *)regs->uregs[i]);
}
}
void __show_regs(struct pt_regs *regs)
{
unsigned long flags;
char buf[64];
#ifndef CONFIG_CPU_V7M
unsigned int domain;
#ifdef CONFIG_CPU_SW_DOMAIN_PAN
/*
* Get the domain register for the parent context. In user
* mode, we don't save the DACR, so lets use what it should
* be. For other modes, we place it after the pt_regs struct.
*/
if (user_mode(regs)) {
domain = DACR_UACCESS_ENABLE;
} else {
domain = to_svc_pt_regs(regs)->dacr;
}
#else
domain = get_domain();
#endif
#endif
show_regs_print_info(KERN_DEFAULT);
printk("PC is at %pS\n", (void *)instruction_pointer(regs));
printk("LR is at %pS\n", (void *)regs->ARM_lr);
printk("pc : [<%08lx>] lr : [<%08lx>] psr: %08lx\n",
regs->ARM_pc, regs->ARM_lr, regs->ARM_cpsr);
printk("sp : %08lx ip : %08lx fp : %08lx\n",
regs->ARM_sp, regs->ARM_ip, regs->ARM_fp);
printk("r10: %08lx r9 : %08lx r8 : %08lx\n",
regs->ARM_r10, regs->ARM_r9,
regs->ARM_r8);
printk("r7 : %08lx r6 : %08lx r5 : %08lx r4 : %08lx\n",
regs->ARM_r7, regs->ARM_r6,
regs->ARM_r5, regs->ARM_r4);
printk("r3 : %08lx r2 : %08lx r1 : %08lx r0 : %08lx\n",
regs->ARM_r3, regs->ARM_r2,
regs->ARM_r1, regs->ARM_r0);
flags = regs->ARM_cpsr;
buf[0] = flags & PSR_N_BIT ? 'N' : 'n';
buf[1] = flags & PSR_Z_BIT ? 'Z' : 'z';
buf[2] = flags & PSR_C_BIT ? 'C' : 'c';
buf[3] = flags & PSR_V_BIT ? 'V' : 'v';
buf[4] = '\0';
#ifndef CONFIG_CPU_V7M
{
const char *segment;
if ((domain & domain_mask(DOMAIN_USER)) ==
domain_val(DOMAIN_USER, DOMAIN_NOACCESS))
segment = "none";
else
segment = "user";
printk("Flags: %s IRQs o%s FIQs o%s Mode %s ISA %s Segment %s\n",
buf, interrupts_enabled(regs) ? "n" : "ff",
fast_interrupts_enabled(regs) ? "n" : "ff",
processor_modes[processor_mode(regs)],
isa_modes[isa_mode(regs)], segment);
}
#else
printk("xPSR: %08lx\n", regs->ARM_cpsr);
#endif
#ifdef CONFIG_CPU_CP15
{
unsigned int ctrl;
buf[0] = '\0';
#ifdef CONFIG_CPU_CP15_MMU
{
unsigned int transbase;
asm("mrc p15, 0, %0, c2, c0\n\t"
: "=r" (transbase));
snprintf(buf, sizeof(buf), " Table: %08x DAC: %08x",
transbase, domain);
}
#endif
asm("mrc p15, 0, %0, c1, c0\n" : "=r" (ctrl));
printk("Control: %08x%s\n", ctrl, buf);
}
#endif
}
void show_regs(struct pt_regs * regs)
{
__show_regs(regs);
dump_stack();
}
ATOMIC_NOTIFIER_HEAD(thread_notify_head);
EXPORT_SYMBOL_GPL(thread_notify_head);
/*
* Free current thread data structures etc..
*/
void exit_thread(struct task_struct *tsk)
{
thread_notify(THREAD_NOTIFY_EXIT, task_thread_info(tsk));
}
void flush_thread(void)
{
struct thread_info *thread = current_thread_info();
struct task_struct *tsk = current;
flush_ptrace_hw_breakpoint(tsk);
memset(thread->used_cp, 0, sizeof(thread->used_cp));
memset(&tsk->thread.debug, 0, sizeof(struct debug_info));
memset(&thread->fpstate, 0, sizeof(union fp_state));
flush_tls();
thread_notify(THREAD_NOTIFY_FLUSH, thread);
}
void release_thread(struct task_struct *dead_task)
{
}
asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
int copy_thread(unsigned long clone_flags, unsigned long stack_start,
unsigned long stk_sz, struct task_struct *p, unsigned long tls)
{
struct thread_info *thread = task_thread_info(p);
struct pt_regs *childregs = task_pt_regs(p);
memset(&thread->cpu_context, 0, sizeof(struct cpu_context_save));
#ifdef CONFIG_CPU_USE_DOMAINS
/*
* Copy the initial value of the domain access control register
* from the current thread: thread->addr_limit will have been
* copied from the current thread via setup_thread_stack() in
* kernel/fork.c
*/
thread->cpu_domain = get_domain();
#endif
if (likely(!(p->flags & (PF_KTHREAD | PF_IO_WORKER)))) {
*childregs = *current_pt_regs();
childregs->ARM_r0 = 0;
if (stack_start)
childregs->ARM_sp = stack_start;
} else {
memset(childregs, 0, sizeof(struct pt_regs));
thread->cpu_context.r4 = stk_sz;
thread->cpu_context.r5 = stack_start;
childregs->ARM_cpsr = SVC_MODE;
}
thread->cpu_context.pc = (unsigned long)ret_from_fork;
thread->cpu_context.sp = (unsigned long)childregs;
clear_ptrace_hw_breakpoint(p);
if (clone_flags & CLONE_SETTLS)
thread->tp_value[0] = tls;
thread->tp_value[1] = get_tpuser();
thread_notify(THREAD_NOTIFY_COPY, thread);
return 0;
}
unsigned long get_wchan(struct task_struct *p)
{
struct stackframe frame;
unsigned long stack_page;
int count = 0;
if (!p || p == current || task_is_running(p))
return 0;
frame.fp = thread_saved_fp(p);
frame.sp = thread_saved_sp(p);
frame.lr = 0; /* recovered from the stack */
frame.pc = thread_saved_pc(p);
stack_page = (unsigned long)task_stack_page(p);
do {
if (frame.sp < stack_page ||
frame.sp >= stack_page + THREAD_SIZE ||
unwind_frame(&frame) < 0)
return 0;
if (!in_sched_functions(frame.pc))
return frame.pc;
} while (count ++ < 16);
return 0;
}
#ifdef CONFIG_MMU
#ifdef CONFIG_KUSER_HELPERS
/*
* The vectors page is always readable from user space for the
* atomic helpers. Insert it into the gate_vma so that it is visible
* through ptrace and /proc/<pid>/mem.
*/
static struct vm_area_struct gate_vma;
static int __init gate_vma_init(void)
{
vma_init(&gate_vma, NULL);
gate_vma.vm_page_prot = PAGE_READONLY_EXEC;
gate_vma.vm_start = 0xffff0000;
gate_vma.vm_end = 0xffff0000 + PAGE_SIZE;
gate_vma.vm_flags = VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYEXEC;
return 0;
}
arch_initcall(gate_vma_init);
struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
{
return &gate_vma;
}
int in_gate_area(struct mm_struct *mm, unsigned long addr)
{
return (addr >= gate_vma.vm_start) && (addr < gate_vma.vm_end);
}
int in_gate_area_no_mm(unsigned long addr)
{
return in_gate_area(NULL, addr);
}
#define is_gate_vma(vma) ((vma) == &gate_vma)
#else
#define is_gate_vma(vma) 0
#endif
const char *arch_vma_name(struct vm_area_struct *vma)
{
return is_gate_vma(vma) ? "[vectors]" : NULL;
}
/* If possible, provide a placement hint at a random offset from the
* stack for the sigpage and vdso pages.
*/
static unsigned long sigpage_addr(const struct mm_struct *mm,
unsigned int npages)
{
unsigned long offset;
unsigned long first;
unsigned long last;
unsigned long addr;
unsigned int slots;
first = PAGE_ALIGN(mm->start_stack);
last = TASK_SIZE - (npages << PAGE_SHIFT);
/* No room after stack? */
if (first > last)
return 0;
/* Just enough room? */
if (first == last)
return first;
slots = ((last - first) >> PAGE_SHIFT) + 1;
offset = get_random_int() % slots;
addr = first + (offset << PAGE_SHIFT);
return addr;
}
static struct page *signal_page;
extern struct page *get_signal_page(void);
static int sigpage_mremap(const struct vm_special_mapping *sm,
struct vm_area_struct *new_vma)
{
current->mm->context.sigpage = new_vma->vm_start;
return 0;
}
static const struct vm_special_mapping sigpage_mapping = {
.name = "[sigpage]",
.pages = &signal_page,
.mremap = sigpage_mremap,
};
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma;
unsigned long npages;
unsigned long addr;
unsigned long hint;
int ret = 0;
if (!signal_page)
signal_page = get_signal_page();
if (!signal_page)
return -ENOMEM;
npages = 1; /* for sigpage */
npages += vdso_total_pages;
if (mmap_write_lock_killable(mm))
return -EINTR;
hint = sigpage_addr(mm, npages);
addr = get_unmapped_area(NULL, hint, npages << PAGE_SHIFT, 0, 0);
if (IS_ERR_VALUE(addr)) {
ret = addr;
goto up_fail;
}
vma = _install_special_mapping(mm, addr, PAGE_SIZE,
VM_READ | VM_EXEC | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC,
&sigpage_mapping);
if (IS_ERR(vma)) {
ret = PTR_ERR(vma);
goto up_fail;
}
mm->context.sigpage = addr;
/* Unlike the sigpage, failure to install the vdso is unlikely
* to be fatal to the process, so no error check needed
* here.
*/
arm_install_vdso(mm, addr + PAGE_SIZE);
up_fail:
mmap_write_unlock(mm);
return ret;
}
#endif