linux_dsm_epyc7002/arch/s390/include/asm/mmu_context.h
Martin Schwidefsky 691d526415 s390/mm: fix incorrect ASCE after crst_table_downgrade
The switch_mm function does nothing in case the prev and next mm
are the same. It can happen that a crst_table_downgrade has changed
the top-level pgd in the meantime on a different CPU. Always store
the new ASCE to be picked up in entry.S.

[heiko.carstens@de.ibm.com]: Bug was introduced with git commit
53e857f308 ("s390/mm,tlb: race of lazy TLB flush vs. recreation
of TLB entries") and causes random crashes due to broken page tables
being used.

Reported-by: Dominik Vogt <vogt@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
2015-03-02 11:35:57 -08:00

135 lines
3.4 KiB
C

/*
* S390 version
*
* Derived from "include/asm-i386/mmu_context.h"
*/
#ifndef __S390_MMU_CONTEXT_H
#define __S390_MMU_CONTEXT_H
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/tlbflush.h>
#include <asm/ctl_reg.h>
static inline int init_new_context(struct task_struct *tsk,
struct mm_struct *mm)
{
cpumask_clear(&mm->context.cpu_attach_mask);
atomic_set(&mm->context.attach_count, 0);
mm->context.flush_mm = 0;
mm->context.asce_bits = _ASCE_TABLE_LENGTH | _ASCE_USER_BITS;
#ifdef CONFIG_64BIT
mm->context.asce_bits |= _ASCE_TYPE_REGION3;
#endif
mm->context.has_pgste = 0;
mm->context.use_skey = 0;
mm->context.asce_limit = STACK_TOP_MAX;
crst_table_init((unsigned long *) mm->pgd, pgd_entry_type(mm));
return 0;
}
#define destroy_context(mm) do { } while (0)
static inline void set_user_asce(struct mm_struct *mm)
{
S390_lowcore.user_asce = mm->context.asce_bits | __pa(mm->pgd);
if (current->thread.mm_segment.ar4)
__ctl_load(S390_lowcore.user_asce, 7, 7);
set_cpu_flag(CIF_ASCE);
}
static inline void clear_user_asce(void)
{
S390_lowcore.user_asce = S390_lowcore.kernel_asce;
__ctl_load(S390_lowcore.user_asce, 1, 1);
__ctl_load(S390_lowcore.user_asce, 7, 7);
}
static inline void load_kernel_asce(void)
{
unsigned long asce;
__ctl_store(asce, 1, 1);
if (asce != S390_lowcore.kernel_asce)
__ctl_load(S390_lowcore.kernel_asce, 1, 1);
set_cpu_flag(CIF_ASCE);
}
static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
int cpu = smp_processor_id();
S390_lowcore.user_asce = next->context.asce_bits | __pa(next->pgd);
if (prev == next)
return;
if (MACHINE_HAS_TLB_LC)
cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
/* Clear old ASCE by loading the kernel ASCE. */
__ctl_load(S390_lowcore.kernel_asce, 1, 1);
__ctl_load(S390_lowcore.kernel_asce, 7, 7);
atomic_inc(&next->context.attach_count);
atomic_dec(&prev->context.attach_count);
if (MACHINE_HAS_TLB_LC)
cpumask_clear_cpu(cpu, &prev->context.cpu_attach_mask);
}
#define finish_arch_post_lock_switch finish_arch_post_lock_switch
static inline void finish_arch_post_lock_switch(void)
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
load_kernel_asce();
if (mm) {
preempt_disable();
while (atomic_read(&mm->context.attach_count) >> 16)
cpu_relax();
cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
if (mm->context.flush_mm)
__tlb_flush_mm(mm);
preempt_enable();
}
set_fs(current->thread.mm_segment);
}
#define enter_lazy_tlb(mm,tsk) do { } while (0)
#define deactivate_mm(tsk,mm) do { } while (0)
static inline void activate_mm(struct mm_struct *prev,
struct mm_struct *next)
{
switch_mm(prev, next, current);
cpumask_set_cpu(smp_processor_id(), mm_cpumask(next));
set_user_asce(next);
}
static inline void arch_dup_mmap(struct mm_struct *oldmm,
struct mm_struct *mm)
{
#ifdef CONFIG_64BIT
if (oldmm->context.asce_limit < mm->context.asce_limit)
crst_table_downgrade(mm, oldmm->context.asce_limit);
#endif
}
static inline void arch_exit_mmap(struct mm_struct *mm)
{
}
static inline void arch_unmap(struct mm_struct *mm,
struct vm_area_struct *vma,
unsigned long start, unsigned long end)
{
}
static inline void arch_bprm_mm_init(struct mm_struct *mm,
struct vm_area_struct *vma)
{
}
#endif /* __S390_MMU_CONTEXT_H */