linux/arch/s390/include/asm/mmu_context.h
Martin Schwidefsky e12e4044ae s390/mm: fix mis-accounting of pgtable_bytes
In case a fork or a clone system fails in copy_process and the error
handling does the mmput() at the bad_fork_cleanup_mm label, the
following warning messages will appear on the console:

  BUG: non-zero pgtables_bytes on freeing mm: 16384

The reason for that is the tricks we play with mm_inc_nr_puds() and
mm_inc_nr_pmds() in init_new_context().

A normal 64-bit process has 3 levels of page table, the p4d level and
the pud level are folded. On process termination the free_pud_range()
function in mm/memory.c will subtract 16KB from pgtable_bytes with a
mm_dec_nr_puds() call, but there actually is not really a pud table.

One issue with this is the fact that pgtable_bytes is usually off
by a few kilobytes, but the more severe problem is that for a failed
fork or clone the free_pgtables() function is not called. In this case
there is no mm_dec_nr_puds() or mm_dec_nr_pmds() that go together with
the mm_inc_nr_puds() and mm_inc_nr_pmds in init_new_context().
The pgtable_bytes will be off by 16384 or 32768 bytes and we get the
BUG message. The message itself is purely cosmetic, but annoying.

To fix this override the mm_pmd_folded, mm_pud_folded and mm_p4d_folded
function to check for the true size of the address space.

Reported-by: Li Wang <liwang@redhat.com>
Tested-by: Li Wang <liwang@redhat.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
2018-11-02 08:31:55 +01:00

138 lines
3.9 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* 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 <linux/uaccess.h>
#include <linux/mm_types.h>
#include <asm/tlbflush.h>
#include <asm/ctl_reg.h>
#include <asm-generic/mm_hooks.h>
static inline int init_new_context(struct task_struct *tsk,
struct mm_struct *mm)
{
spin_lock_init(&mm->context.lock);
INIT_LIST_HEAD(&mm->context.pgtable_list);
INIT_LIST_HEAD(&mm->context.gmap_list);
cpumask_clear(&mm->context.cpu_attach_mask);
atomic_set(&mm->context.flush_count, 0);
mm->context.gmap_asce = 0;
mm->context.flush_mm = 0;
mm->context.compat_mm = 0;
#ifdef CONFIG_PGSTE
mm->context.alloc_pgste = page_table_allocate_pgste ||
test_thread_flag(TIF_PGSTE) ||
(current->mm && current->mm->context.alloc_pgste);
mm->context.has_pgste = 0;
mm->context.uses_skeys = 0;
mm->context.uses_cmm = 0;
mm->context.allow_gmap_hpage_1m = 0;
#endif
switch (mm->context.asce_limit) {
case _REGION2_SIZE:
/*
* forked 3-level task, fall through to set new asce with new
* mm->pgd
*/
case 0:
/* context created by exec, set asce limit to 4TB */
mm->context.asce_limit = STACK_TOP_MAX;
mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
_ASCE_USER_BITS | _ASCE_TYPE_REGION3;
break;
case -PAGE_SIZE:
/* forked 5-level task, set new asce with new_mm->pgd */
mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
_ASCE_USER_BITS | _ASCE_TYPE_REGION1;
break;
case _REGION1_SIZE:
/* forked 4-level task, set new asce with new mm->pgd */
mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
_ASCE_USER_BITS | _ASCE_TYPE_REGION2;
break;
case _REGION3_SIZE:
/* forked 2-level compat task, set new asce with new mm->pgd */
mm->context.asce = __pa(mm->pgd) | _ASCE_TABLE_LENGTH |
_ASCE_USER_BITS | _ASCE_TYPE_SEGMENT;
}
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;
__ctl_load(S390_lowcore.user_asce, 1, 1);
clear_cpu_flag(CIF_ASCE_PRIMARY);
}
static inline void clear_user_asce(void)
{
S390_lowcore.user_asce = S390_lowcore.kernel_asce;
__ctl_load(S390_lowcore.kernel_asce, 1, 1);
set_cpu_flag(CIF_ASCE_PRIMARY);
}
mm_segment_t enable_sacf_uaccess(void);
void disable_sacf_uaccess(mm_segment_t old_fs);
static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
struct task_struct *tsk)
{
int cpu = smp_processor_id();
if (prev == next)
return;
S390_lowcore.user_asce = next->context.asce;
cpumask_set_cpu(cpu, &next->context.cpu_attach_mask);
/* Clear previous user-ASCE from CR1 and CR7 */
if (!test_cpu_flag(CIF_ASCE_PRIMARY)) {
__ctl_load(S390_lowcore.kernel_asce, 1, 1);
set_cpu_flag(CIF_ASCE_PRIMARY);
}
if (test_cpu_flag(CIF_ASCE_SECONDARY)) {
__ctl_load(S390_lowcore.vdso_asce, 7, 7);
clear_cpu_flag(CIF_ASCE_SECONDARY);
}
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;
if (mm) {
preempt_disable();
while (atomic_read(&mm->context.flush_count))
cpu_relax();
cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
__tlb_flush_mm_lazy(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);
}
#endif /* __S390_MMU_CONTEXT_H */