android_kernel_xiaomi_sm8450/include/linux/rmap.h
Andi Kleen 6a46079cf5 HWPOISON: The high level memory error handler in the VM v7
Add the high level memory handler that poisons pages
that got corrupted by hardware (typically by a two bit flip in a DIMM
or a cache) on the Linux level. The goal is to prevent everyone
from accessing these pages in the future.

This done at the VM level by marking a page hwpoisoned
and doing the appropriate action based on the type of page
it is.

The code that does this is portable and lives in mm/memory-failure.c

To quote the overview comment:

High level machine check handler. Handles pages reported by the
hardware as being corrupted usually due to a 2bit ECC memory or cache
failure.

This focuses on pages detected as corrupted in the background.
When the current CPU tries to consume corruption the currently
running process can just be killed directly instead. This implies
that if the error cannot be handled for some reason it's safe to
just ignore it because no corruption has been consumed yet. Instead
when that happens another machine check will happen.

Handles page cache pages in various states. The tricky part
here is that we can access any page asynchronous to other VM
users, because memory failures could happen anytime and anywhere,
possibly violating some of their assumptions. This is why this code
has to be extremely careful. Generally it tries to use normal locking
rules, as in get the standard locks, even if that means the
error handling takes potentially a long time.

Some of the operations here are somewhat inefficient and have non
linear algorithmic complexity, because the data structures have not
been optimized for this case. This is in particular the case
for the mapping from a vma to a process. Since this case is expected
to be rare we hope we can get away with this.

There are in principle two strategies to kill processes on poison:
- just unmap the data and wait for an actual reference before
killing
- kill as soon as corruption is detected.
Both have advantages and disadvantages and should be used
in different situations. Right now both are implemented and can
be switched with a new sysctl vm.memory_failure_early_kill
The default is early kill.

The patch does some rmap data structure walking on its own to collect
processes to kill. This is unusual because normally all rmap data structure
knowledge is in rmap.c only. I put it here for now to keep
everything together and rmap knowledge has been seeping out anyways

Includes contributions from Johannes Weiner, Chris Mason, Fengguang Wu,
Nick Piggin (who did a lot of great work) and others.

Cc: npiggin@suse.de
Cc: riel@redhat.com
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Hidehiro Kawai <hidehiro.kawai.ez@hitachi.com>
2009-09-16 11:50:15 +02:00

167 lines
4.6 KiB
C

#ifndef _LINUX_RMAP_H
#define _LINUX_RMAP_H
/*
* Declarations for Reverse Mapping functions in mm/rmap.c
*/
#include <linux/list.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/spinlock.h>
#include <linux/memcontrol.h>
/*
* The anon_vma heads a list of private "related" vmas, to scan if
* an anonymous page pointing to this anon_vma needs to be unmapped:
* the vmas on the list will be related by forking, or by splitting.
*
* Since vmas come and go as they are split and merged (particularly
* in mprotect), the mapping field of an anonymous page cannot point
* directly to a vma: instead it points to an anon_vma, on whose list
* the related vmas can be easily linked or unlinked.
*
* After unlinking the last vma on the list, we must garbage collect
* the anon_vma object itself: we're guaranteed no page can be
* pointing to this anon_vma once its vma list is empty.
*/
struct anon_vma {
spinlock_t lock; /* Serialize access to vma list */
/*
* NOTE: the LSB of the head.next is set by
* mm_take_all_locks() _after_ taking the above lock. So the
* head must only be read/written after taking the above lock
* to be sure to see a valid next pointer. The LSB bit itself
* is serialized by a system wide lock only visible to
* mm_take_all_locks() (mm_all_locks_mutex).
*/
struct list_head head; /* List of private "related" vmas */
};
#ifdef CONFIG_MMU
static inline void anon_vma_lock(struct vm_area_struct *vma)
{
struct anon_vma *anon_vma = vma->anon_vma;
if (anon_vma)
spin_lock(&anon_vma->lock);
}
static inline void anon_vma_unlock(struct vm_area_struct *vma)
{
struct anon_vma *anon_vma = vma->anon_vma;
if (anon_vma)
spin_unlock(&anon_vma->lock);
}
/*
* anon_vma helper functions.
*/
void anon_vma_init(void); /* create anon_vma_cachep */
int anon_vma_prepare(struct vm_area_struct *);
void __anon_vma_merge(struct vm_area_struct *, struct vm_area_struct *);
void anon_vma_unlink(struct vm_area_struct *);
void anon_vma_link(struct vm_area_struct *);
void __anon_vma_link(struct vm_area_struct *);
/*
* rmap interfaces called when adding or removing pte of page
*/
void page_add_anon_rmap(struct page *, struct vm_area_struct *, unsigned long);
void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned long);
void page_add_file_rmap(struct page *);
void page_remove_rmap(struct page *);
#ifdef CONFIG_DEBUG_VM
void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address);
#else
static inline void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address)
{
atomic_inc(&page->_mapcount);
}
#endif
/*
* Called from mm/vmscan.c to handle paging out
*/
int page_referenced(struct page *, int is_locked,
struct mem_cgroup *cnt, unsigned long *vm_flags);
enum ttu_flags {
TTU_UNMAP = 0, /* unmap mode */
TTU_MIGRATION = 1, /* migration mode */
TTU_MUNLOCK = 2, /* munlock mode */
TTU_ACTION_MASK = 0xff,
TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */
TTU_IGNORE_ACCESS = (1 << 9), /* don't age */
TTU_IGNORE_HWPOISON = (1 << 10),/* corrupted page is recoverable */
};
#define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
int try_to_unmap(struct page *, enum ttu_flags flags);
/*
* Called from mm/filemap_xip.c to unmap empty zero page
*/
pte_t *page_check_address(struct page *, struct mm_struct *,
unsigned long, spinlock_t **, int);
/*
* Used by swapoff to help locate where page is expected in vma.
*/
unsigned long page_address_in_vma(struct page *, struct vm_area_struct *);
/*
* Cleans the PTEs of shared mappings.
* (and since clean PTEs should also be readonly, write protects them too)
*
* returns the number of cleaned PTEs.
*/
int page_mkclean(struct page *);
/*
* called in munlock()/munmap() path to check for other vmas holding
* the page mlocked.
*/
int try_to_munlock(struct page *);
/*
* Called by memory-failure.c to kill processes.
*/
struct anon_vma *page_lock_anon_vma(struct page *page);
void page_unlock_anon_vma(struct anon_vma *anon_vma);
int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
#else /* !CONFIG_MMU */
#define anon_vma_init() do {} while (0)
#define anon_vma_prepare(vma) (0)
#define anon_vma_link(vma) do {} while (0)
static inline int page_referenced(struct page *page, int is_locked,
struct mem_cgroup *cnt,
unsigned long *vm_flags)
{
*vm_flags = 0;
return TestClearPageReferenced(page);
}
#define try_to_unmap(page, refs) SWAP_FAIL
static inline int page_mkclean(struct page *page)
{
return 0;
}
#endif /* CONFIG_MMU */
/*
* Return values of try_to_unmap
*/
#define SWAP_SUCCESS 0
#define SWAP_AGAIN 1
#define SWAP_FAIL 2
#define SWAP_MLOCK 3
#endif /* _LINUX_RMAP_H */