linux/arch/arm64/kernel/process.c
Arun Chandran 5e05153144 arm64: convert part of soft_restart() to assembly
The current soft_restart() and setup_restart implementations incorrectly
assume that compiler will not spill/fill values to/from stack. However
this assumption seems to be wrong, revealed by the disassembly of the
currently existing code (v3.16) built with Linaro GCC 4.9-2014.05.

ffffffc000085224 <soft_restart>:
ffffffc000085224:  a9be7bfd  stp    x29, x30, [sp,#-32]!
ffffffc000085228:  910003fd  mov    x29, sp
ffffffc00008522c:  f9000fa0  str    x0, [x29,#24]
ffffffc000085230:  94003d21  bl     ffffffc0000946b4 <setup_mm_for_reboot>
ffffffc000085234:  94003b33  bl     ffffffc000093f00 <flush_cache_all>
ffffffc000085238:  94003dfa  bl     ffffffc000094a20 <cpu_cache_off>
ffffffc00008523c:  94003b31  bl     ffffffc000093f00 <flush_cache_all>
ffffffc000085240:  b0003321  adrp   x1, ffffffc0006ea000 <reset_devices>

ffffffc000085244:  f9400fa0  ldr    x0, [x29,#24] ----> spilled addr
ffffffc000085248:  f942fc22  ldr    x2, [x1,#1528] ----> global memstart_addr

ffffffc00008524c:  f0000061  adrp   x1, ffffffc000094000 <__inval_cache_range+0x40>
ffffffc000085250:  91290021  add    x1, x1, #0xa40
ffffffc000085254:  8b010041  add    x1, x2, x1
ffffffc000085258:  d2c00802  mov    x2, #0x4000000000           // #274877906944
ffffffc00008525c:  8b020021  add    x1, x1, x2
ffffffc000085260:  d63f0020  blr    x1
...

Here the compiler generates memory accesses after the cache is disabled,
loading stale values for the spilled value and global variable. As we cannot
control when the compiler will access memory we must rewrite the
functions in assembly to stash values we need in registers prior to
disabling the cache, avoiding the use of memory.

Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Arun Chandran <achandran@mvista.com>
Signed-off-by: Will Deacon <will.deacon@arm.com>
2014-09-08 14:39:18 +01:00

367 lines
8.8 KiB
C

/*
* Based on arch/arm/kernel/process.c
*
* Original Copyright (C) 1995 Linus Torvalds
* Copyright (C) 1996-2000 Russell King - Converted to ARM.
* Copyright (C) 2012 ARM Ltd.
*
* 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.
*
* You should have received a copy of the GNU General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <stdarg.h>
#include <linux/compat.h>
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/user.h>
#include <linux/delay.h>
#include <linux/reboot.h>
#include <linux/interrupt.h>
#include <linux/kallsyms.h>
#include <linux/init.h>
#include <linux/cpu.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/personality.h>
#include <linux/notifier.h>
#include <asm/compat.h>
#include <asm/cacheflush.h>
#include <asm/fpsimd.h>
#include <asm/mmu_context.h>
#include <asm/processor.h>
#include <asm/stacktrace.h>
#ifdef CONFIG_CC_STACKPROTECTOR
#include <linux/stackprotector.h>
unsigned long __stack_chk_guard __read_mostly;
EXPORT_SYMBOL(__stack_chk_guard);
#endif
void soft_restart(unsigned long addr)
{
setup_mm_for_reboot();
cpu_soft_restart(virt_to_phys(cpu_reset), addr);
/* Should never get here */
BUG();
}
/*
* Function pointers to optional machine specific functions
*/
void (*pm_power_off)(void);
EXPORT_SYMBOL_GPL(pm_power_off);
void (*arm_pm_restart)(enum reboot_mode reboot_mode, const char *cmd);
EXPORT_SYMBOL_GPL(arm_pm_restart);
/*
* This is our default idle handler.
*/
void arch_cpu_idle(void)
{
/*
* This should do all the clock switching and wait for interrupt
* tricks
*/
cpu_do_idle();
local_irq_enable();
}
#ifdef CONFIG_HOTPLUG_CPU
void arch_cpu_idle_dead(void)
{
cpu_die();
}
#endif
/*
* Called by kexec, immediately prior to machine_kexec().
*
* This must completely disable all secondary CPUs; simply causing those CPUs
* to execute e.g. a RAM-based pin loop is not sufficient. This allows the
* kexec'd kernel to use any and all RAM as it sees fit, without having to
* avoid any code or data used by any SW CPU pin loop. The CPU hotplug
* functionality embodied in disable_nonboot_cpus() to achieve this.
*/
void machine_shutdown(void)
{
disable_nonboot_cpus();
}
/*
* Halting simply requires that the secondary CPUs stop performing any
* activity (executing tasks, handling interrupts). smp_send_stop()
* achieves this.
*/
void machine_halt(void)
{
local_irq_disable();
smp_send_stop();
while (1);
}
/*
* Power-off simply requires that the secondary CPUs stop performing any
* activity (executing tasks, handling interrupts). smp_send_stop()
* achieves this. When the system power is turned off, it will take all CPUs
* with it.
*/
void machine_power_off(void)
{
local_irq_disable();
smp_send_stop();
if (pm_power_off)
pm_power_off();
}
/*
* Restart requires that the secondary CPUs stop performing any activity
* while the primary CPU resets the system. Systems with a single CPU can
* use soft_restart() as their machine descriptor's .restart hook, since that
* will cause the only available CPU to reset. Systems with multiple CPUs must
* provide a HW restart implementation, to ensure that all CPUs reset at once.
* This is required so that any code running after reset on the primary CPU
* doesn't have to co-ordinate with other CPUs to ensure they aren't still
* executing pre-reset code, and using RAM that the primary CPU's code wishes
* to use. Implementing such co-ordination would be essentially impossible.
*/
void machine_restart(char *cmd)
{
/* Disable interrupts first */
local_irq_disable();
smp_send_stop();
/* Now call the architecture specific reboot code. */
if (arm_pm_restart)
arm_pm_restart(reboot_mode, cmd);
/*
* Whoops - the architecture was unable to reboot.
*/
printk("Reboot failed -- System halted\n");
while (1);
}
void __show_regs(struct pt_regs *regs)
{
int i, top_reg;
u64 lr, sp;
if (compat_user_mode(regs)) {
lr = regs->compat_lr;
sp = regs->compat_sp;
top_reg = 12;
} else {
lr = regs->regs[30];
sp = regs->sp;
top_reg = 29;
}
show_regs_print_info(KERN_DEFAULT);
print_symbol("PC is at %s\n", instruction_pointer(regs));
print_symbol("LR is at %s\n", lr);
printk("pc : [<%016llx>] lr : [<%016llx>] pstate: %08llx\n",
regs->pc, lr, regs->pstate);
printk("sp : %016llx\n", sp);
for (i = top_reg; i >= 0; i--) {
printk("x%-2d: %016llx ", i, regs->regs[i]);
if (i % 2 == 0)
printk("\n");
}
printk("\n");
}
void show_regs(struct pt_regs * regs)
{
printk("\n");
__show_regs(regs);
}
/*
* Free current thread data structures etc..
*/
void exit_thread(void)
{
}
void flush_thread(void)
{
fpsimd_flush_thread();
flush_ptrace_hw_breakpoint(current);
}
void release_thread(struct task_struct *dead_task)
{
}
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
fpsimd_preserve_current_state();
*dst = *src;
return 0;
}
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)
{
struct pt_regs *childregs = task_pt_regs(p);
unsigned long tls = p->thread.tp_value;
memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
if (likely(!(p->flags & PF_KTHREAD))) {
*childregs = *current_pt_regs();
childregs->regs[0] = 0;
if (is_compat_thread(task_thread_info(p))) {
if (stack_start)
childregs->compat_sp = stack_start;
} else {
/*
* Read the current TLS pointer from tpidr_el0 as it may be
* out-of-sync with the saved value.
*/
asm("mrs %0, tpidr_el0" : "=r" (tls));
if (stack_start) {
/* 16-byte aligned stack mandatory on AArch64 */
if (stack_start & 15)
return -EINVAL;
childregs->sp = stack_start;
}
}
/*
* If a TLS pointer was passed to clone (4th argument), use it
* for the new thread.
*/
if (clone_flags & CLONE_SETTLS)
tls = childregs->regs[3];
} else {
memset(childregs, 0, sizeof(struct pt_regs));
childregs->pstate = PSR_MODE_EL1h;
p->thread.cpu_context.x19 = stack_start;
p->thread.cpu_context.x20 = stk_sz;
}
p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
p->thread.cpu_context.sp = (unsigned long)childregs;
p->thread.tp_value = tls;
ptrace_hw_copy_thread(p);
return 0;
}
static void tls_thread_switch(struct task_struct *next)
{
unsigned long tpidr, tpidrro;
if (!is_compat_task()) {
asm("mrs %0, tpidr_el0" : "=r" (tpidr));
current->thread.tp_value = tpidr;
}
if (is_compat_thread(task_thread_info(next))) {
tpidr = 0;
tpidrro = next->thread.tp_value;
} else {
tpidr = next->thread.tp_value;
tpidrro = 0;
}
asm(
" msr tpidr_el0, %0\n"
" msr tpidrro_el0, %1"
: : "r" (tpidr), "r" (tpidrro));
}
/*
* Thread switching.
*/
struct task_struct *__switch_to(struct task_struct *prev,
struct task_struct *next)
{
struct task_struct *last;
fpsimd_thread_switch(next);
tls_thread_switch(next);
hw_breakpoint_thread_switch(next);
contextidr_thread_switch(next);
/*
* Complete any pending TLB or cache maintenance on this CPU in case
* the thread migrates to a different CPU.
*/
dsb(ish);
/* the actual thread switch */
last = cpu_switch_to(prev, next);
return last;
}
unsigned long get_wchan(struct task_struct *p)
{
struct stackframe frame;
unsigned long stack_page;
int count = 0;
if (!p || p == current || p->state == TASK_RUNNING)
return 0;
frame.fp = thread_saved_fp(p);
frame.sp = thread_saved_sp(p);
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))
return 0;
if (!in_sched_functions(frame.pc))
return frame.pc;
} while (count ++ < 16);
return 0;
}
unsigned long arch_align_stack(unsigned long sp)
{
if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
sp -= get_random_int() & ~PAGE_MASK;
return sp & ~0xf;
}
static unsigned long randomize_base(unsigned long base)
{
unsigned long range_end = base + (STACK_RND_MASK << PAGE_SHIFT) + 1;
return randomize_range(base, range_end, 0) ? : base;
}
unsigned long arch_randomize_brk(struct mm_struct *mm)
{
return randomize_base(mm->brk);
}
unsigned long randomize_et_dyn(unsigned long base)
{
return randomize_base(base);
}