mirror of
https://github.com/torvalds/linux.git
synced 2024-12-16 08:02:17 +00:00
1de4fa14ee
The previous patch allocates bounds tables on-demand. As noted in
an earlier description, these can add up to *HUGE* amounts of
memory. This has caused OOMs in practice when running tests.
This patch adds support for freeing bounds tables when they are no
longer in use.
There are two types of mappings in play when unmapping tables:
1. The mapping with the actual data, which userspace is
munmap()ing or brk()ing away, etc...
2. The mapping for the bounds table *backing* the data
(is tagged with VM_MPX, see the patch "add MPX specific
mmap interface").
If userspace use the prctl() indroduced earlier in this patchset
to enable the management of bounds tables in kernel, when it
unmaps the first type of mapping with the actual data, the kernel
needs to free the mapping for the bounds table backing the data.
This patch hooks in at the very end of do_unmap() to do so.
We look at the addresses being unmapped and find the bounds
directory entries and tables which cover those addresses. If
an entire table is unused, we clear associated directory entry
and free the table.
Once we unmap the bounds table, we would have a bounds directory
entry pointing at empty address space. That address space might
now be allocated for some other (random) use, and the MPX
hardware might now try to walk it as if it were a bounds table.
That would be bad. So any unmapping of an enture bounds table
has to be accompanied by a corresponding write to the bounds
directory entry to invalidate it. That write to the bounds
directory can fault, which causes the following problem:
Since we are doing the freeing from munmap() (and other paths
like it), we hold mmap_sem for write. If we fault, the page
fault handler will attempt to acquire mmap_sem for read and
we will deadlock. To avoid the deadlock, we pagefault_disable()
when touching the bounds directory entry and use a
get_user_pages() to resolve the fault.
The unmapping of bounds tables happends under vm_munmap(). We
also (indirectly) call vm_munmap() to _do_ the unmapping of the
bounds tables. We avoid unbounded recursion by disallowing
freeing of bounds tables *for* bounds tables. This would not
occur normally, so should not have any practical impact. Being
strict about it here helps ensure that we do not have an
exploitable stack overflow.
Based-on-patch-by: Qiaowei Ren <qiaowei.ren@intel.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: linux-mm@kvack.org
Cc: linux-mips@linux-mips.org
Cc: Dave Hansen <dave@sr71.net>
Link: http://lkml.kernel.org/r/20141114151831.E4531C4A@viggo.jf.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
119 lines
2.9 KiB
C
119 lines
2.9 KiB
C
#ifndef _ASM_X86_MMU_CONTEXT_H
|
|
#define _ASM_X86_MMU_CONTEXT_H
|
|
|
|
#include <asm/desc.h>
|
|
#include <linux/atomic.h>
|
|
#include <linux/mm_types.h>
|
|
|
|
#include <trace/events/tlb.h>
|
|
|
|
#include <asm/pgalloc.h>
|
|
#include <asm/tlbflush.h>
|
|
#include <asm/paravirt.h>
|
|
#include <asm/mpx.h>
|
|
#ifndef CONFIG_PARAVIRT
|
|
#include <asm-generic/mm_hooks.h>
|
|
|
|
static inline void paravirt_activate_mm(struct mm_struct *prev,
|
|
struct mm_struct *next)
|
|
{
|
|
}
|
|
#endif /* !CONFIG_PARAVIRT */
|
|
|
|
/*
|
|
* Used for LDT copy/destruction.
|
|
*/
|
|
int init_new_context(struct task_struct *tsk, struct mm_struct *mm);
|
|
void destroy_context(struct mm_struct *mm);
|
|
|
|
|
|
static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
|
|
{
|
|
#ifdef CONFIG_SMP
|
|
if (this_cpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
|
|
this_cpu_write(cpu_tlbstate.state, TLBSTATE_LAZY);
|
|
#endif
|
|
}
|
|
|
|
static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
|
|
struct task_struct *tsk)
|
|
{
|
|
unsigned cpu = smp_processor_id();
|
|
|
|
if (likely(prev != next)) {
|
|
#ifdef CONFIG_SMP
|
|
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
|
|
this_cpu_write(cpu_tlbstate.active_mm, next);
|
|
#endif
|
|
cpumask_set_cpu(cpu, mm_cpumask(next));
|
|
|
|
/* Re-load page tables */
|
|
load_cr3(next->pgd);
|
|
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
|
|
|
|
/* Stop flush ipis for the previous mm */
|
|
cpumask_clear_cpu(cpu, mm_cpumask(prev));
|
|
|
|
/* Load the LDT, if the LDT is different: */
|
|
if (unlikely(prev->context.ldt != next->context.ldt))
|
|
load_LDT_nolock(&next->context);
|
|
}
|
|
#ifdef CONFIG_SMP
|
|
else {
|
|
this_cpu_write(cpu_tlbstate.state, TLBSTATE_OK);
|
|
BUG_ON(this_cpu_read(cpu_tlbstate.active_mm) != next);
|
|
|
|
if (!cpumask_test_cpu(cpu, mm_cpumask(next))) {
|
|
/*
|
|
* On established mms, the mm_cpumask is only changed
|
|
* from irq context, from ptep_clear_flush() while in
|
|
* lazy tlb mode, and here. Irqs are blocked during
|
|
* schedule, protecting us from simultaneous changes.
|
|
*/
|
|
cpumask_set_cpu(cpu, mm_cpumask(next));
|
|
/*
|
|
* We were in lazy tlb mode and leave_mm disabled
|
|
* tlb flush IPI delivery. We must reload CR3
|
|
* to make sure to use no freed page tables.
|
|
*/
|
|
load_cr3(next->pgd);
|
|
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
|
|
load_LDT_nolock(&next->context);
|
|
}
|
|
}
|
|
#endif
|
|
}
|
|
|
|
#define activate_mm(prev, next) \
|
|
do { \
|
|
paravirt_activate_mm((prev), (next)); \
|
|
switch_mm((prev), (next), NULL); \
|
|
} while (0);
|
|
|
|
#ifdef CONFIG_X86_32
|
|
#define deactivate_mm(tsk, mm) \
|
|
do { \
|
|
lazy_load_gs(0); \
|
|
} while (0)
|
|
#else
|
|
#define deactivate_mm(tsk, mm) \
|
|
do { \
|
|
load_gs_index(0); \
|
|
loadsegment(fs, 0); \
|
|
} while (0)
|
|
#endif
|
|
|
|
static inline void arch_bprm_mm_init(struct mm_struct *mm,
|
|
struct vm_area_struct *vma)
|
|
{
|
|
mpx_mm_init(mm);
|
|
}
|
|
|
|
static inline void arch_unmap(struct mm_struct *mm, struct vm_area_struct *vma,
|
|
unsigned long start, unsigned long end)
|
|
{
|
|
mpx_notify_unmap(mm, vma, start, end);
|
|
}
|
|
|
|
#endif /* _ASM_X86_MMU_CONTEXT_H */
|