Files
android_kernel_xiaomi_sm8450/arch/s390/include/asm/mmu_context.h
Dave Hansen 33a709b25a mm/gup, x86/mm/pkeys: Check VMAs and PTEs for protection keys
Today, for normal faults and page table walks, we check the VMA
and/or PTE to ensure that it is compatible with the action.  For
instance, if we get a write fault on a non-writeable VMA, we
SIGSEGV.

We try to do the same thing for protection keys.  Basically, we
try to make sure that if a user does this:

	mprotect(ptr, size, PROT_NONE);
	*ptr = foo;

they see the same effects with protection keys when they do this:

	mprotect(ptr, size, PROT_READ|PROT_WRITE);
	set_pkey(ptr, size, 4);
	wrpkru(0xffffff3f); // access disable pkey 4
	*ptr = foo;

The state to do that checking is in the VMA, but we also
sometimes have to do it on the page tables only, like when doing
a get_user_pages_fast() where we have no VMA.

We add two functions and expose them to generic code:

	arch_pte_access_permitted(pte_flags, write)
	arch_vma_access_permitted(vma, write)

These are, of course, backed up in x86 arch code with checks
against the PTE or VMA's protection key.

But, there are also cases where we do not want to respect
protection keys.  When we ptrace(), for instance, we do not want
to apply the tracer's PKRU permissions to the PTEs from the
process being traced.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Alexey Kardashevskiy <aik@ozlabs.ru>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Boaz Harrosh <boaz@plexistor.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: David Gibson <david@gibson.dropbear.id.au>
Cc: David Hildenbrand <dahi@linux.vnet.ibm.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Dominik Dingel <dingel@linux.vnet.ibm.com>
Cc: Dominik Vogt <vogt@linux.vnet.ibm.com>
Cc: Guan Xuetao <gxt@mprc.pku.edu.cn>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jason Low <jason.low2@hp.com>
Cc: Jerome Marchand <jmarchan@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Laurent Dufour <ldufour@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mikulas Patocka <mpatocka@redhat.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Sasha Levin <sasha.levin@oracle.com>
Cc: Shachar Raindel <raindel@mellanox.com>
Cc: Stephen Smalley <sds@tycho.nsa.gov>
Cc: Toshi Kani <toshi.kani@hpe.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: linux-arch@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: linux-mm@kvack.org
Cc: linux-s390@vger.kernel.org
Cc: linuxppc-dev@lists.ozlabs.org
Link: http://lkml.kernel.org/r/20160212210219.14D5D715@viggo.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-18 09:32:44 +01:00

145 lines
3.6 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;
mm->context.asce_bits |= _ASCE_TYPE_REGION3;
#ifdef CONFIG_PGSTE
mm->context.alloc_pgste = page_table_allocate_pgste;
mm->context.has_pgste = 0;
mm->context.use_skey = 0;
#endif
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)
{
if (oldmm->context.asce_limit < mm->context.asce_limit)
crst_table_downgrade(mm, oldmm->context.asce_limit);
}
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)
{
}
static inline bool arch_vma_access_permitted(struct vm_area_struct *vma, bool write)
{
/* by default, allow everything */
return true;
}
static inline bool arch_pte_access_permitted(pte_t pte, bool write)
{
/* by default, allow everything */
return true;
}
#endif /* __S390_MMU_CONTEXT_H */