commit 071b6d4a5d343046f253a5a8835d477d93992002 upstream.
Currently, loading of a task's fpsimd state into the CPU registers
is skipped if that task's state is already present in the registers
of that CPU.
However, the code relies on the struct fpsimd_state * (and by
extension struct task_struct *) to unambiguously identify a task.
There is a particular case in which this doesn't work reliably:
when a task exits, its task_struct may be recycled to describe a
new task.
Consider the following scenario:
1) Task P loads its fpsimd state onto cpu C.
per_cpu(fpsimd_last_state, C) := P;
P->thread.fpsimd_state.cpu := C;
2) Task X is scheduled onto C and loads its fpsimd state on C.
per_cpu(fpsimd_last_state, C) := X;
X->thread.fpsimd_state.cpu := C;
3) X exits, causing X's task_struct to be freed.
4) P forks a new child T, which obtains X's recycled task_struct.
T == X.
T->thread.fpsimd_state.cpu == C (inherited from P).
5) T is scheduled on C.
T's fpsimd state is not loaded, because
per_cpu(fpsimd_last_state, C) == T (== X) &&
T->thread.fpsimd_state.cpu == C.
(This is the check performed by fpsimd_thread_switch().)
So, T gets X's registers because the last registers loaded onto C
were those of X, in (2).
This patch fixes the problem by ensuring that the sched-in check
fails in (5): fpsimd_flush_task_state(T) is called when T is
forked, so that T->thread.fpsimd_state.cpu == C cannot be true.
This relies on the fact that T is not schedulable until after
copy_thread() completes.
Once T's fpsimd state has been loaded on some CPU C there may still
be other cpus D for which per_cpu(fpsimd_last_state, D) ==
&X->thread.fpsimd_state. But D is necessarily != C in this case,
and the check in (5) must fail.
An alternative fix would be to do refcounting on task_struct. This
would result in each CPU holding a reference to the last task whose
fpsimd state was loaded there. It's not clear whether this is
preferable, and it involves higher overhead than the fix proposed
in this patch. It would also move all the task_struct freeing
work into the context switch critical section, or otherwise some
deferred cleanup mechanism would need to be introduced, neither of
which seems obviously justified.
Fixes: 005f78cd88
("arm64: defer reloading a task's FPSIMD state to userland resume")
Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Reviewed-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
[will: word-smithed the comment so it makes more sense]
Signed-off-by: Will Deacon <will.deacon@arm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
384 lines
9.3 KiB
C
384 lines
9.3 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/efi.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 <trace/events/power.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
|
|
|
|
/*
|
|
* 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);
|
|
|
|
/*
|
|
* This is our default idle handler.
|
|
*/
|
|
void arch_cpu_idle(void)
|
|
{
|
|
/*
|
|
* This should do all the clock switching and wait for interrupt
|
|
* tricks
|
|
*/
|
|
trace_cpu_idle_rcuidle(1, smp_processor_id());
|
|
cpu_do_idle();
|
|
local_irq_enable();
|
|
trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
|
|
}
|
|
|
|
#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 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();
|
|
|
|
/*
|
|
* UpdateCapsule() depends on the system being reset via
|
|
* ResetSystem().
|
|
*/
|
|
if (efi_enabled(EFI_RUNTIME_SERVICES))
|
|
efi_reboot(reboot_mode, NULL);
|
|
|
|
/* Now call the architecture specific reboot code. */
|
|
if (arm_pm_restart)
|
|
arm_pm_restart(reboot_mode, cmd);
|
|
else
|
|
do_kernel_restart(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)
|
|
{
|
|
}
|
|
|
|
static void tls_thread_flush(void)
|
|
{
|
|
asm ("msr tpidr_el0, xzr");
|
|
|
|
if (is_compat_task()) {
|
|
current->thread.tp_value = 0;
|
|
|
|
/*
|
|
* We need to ensure ordering between the shadow state and the
|
|
* hardware state, so that we don't corrupt the hardware state
|
|
* with a stale shadow state during context switch.
|
|
*/
|
|
barrier();
|
|
asm ("msr tpidrro_el0, xzr");
|
|
}
|
|
}
|
|
|
|
void flush_thread(void)
|
|
{
|
|
fpsimd_flush_thread();
|
|
tls_thread_flush();
|
|
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)
|
|
{
|
|
if (current->mm)
|
|
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);
|
|
|
|
memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
|
|
|
|
/*
|
|
* In case p was allocated the same task_struct pointer as some
|
|
* other recently-exited task, make sure p is disassociated from
|
|
* any cpu that may have run that now-exited task recently.
|
|
* Otherwise we could erroneously skip reloading the FPSIMD
|
|
* registers for p.
|
|
*/
|
|
fpsimd_flush_task_state(p);
|
|
|
|
if (likely(!(p->flags & PF_KTHREAD))) {
|
|
*childregs = *current_pt_regs();
|
|
childregs->regs[0] = 0;
|
|
|
|
/*
|
|
* 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" (*task_user_tls(p)));
|
|
|
|
if (stack_start) {
|
|
if (is_compat_thread(task_thread_info(p)))
|
|
childregs->compat_sp = stack_start;
|
|
/* 16-byte aligned stack mandatory on AArch64 */
|
|
else if (stack_start & 15)
|
|
return -EINVAL;
|
|
else
|
|
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)
|
|
p->thread.tp_value = 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;
|
|
|
|
ptrace_hw_copy_thread(p);
|
|
|
|
return 0;
|
|
}
|
|
|
|
static void tls_thread_switch(struct task_struct *next)
|
|
{
|
|
unsigned long tpidr, tpidrro;
|
|
|
|
asm("mrs %0, tpidr_el0" : "=r" (tpidr));
|
|
*task_user_tls(current) = tpidr;
|
|
|
|
tpidr = *task_user_tls(next);
|
|
tpidrro = is_compat_thread(task_thread_info(next)) ?
|
|
next->thread.tp_value : 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);
|
|
}
|