mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-28 20:02:17 +00:00
![Suren Baghdasaryan](/assets/img/avatar_default.png)
walk_page_range() and friends often operate under write-locked mmap_lock. With introduction of vma locks, the vmas have to be locked as well during such walks to prevent concurrent page faults in these areas. Add an additional member to mm_walk_ops to indicate locking requirements for the walk. The change ensures that page walks which prevent concurrent page faults by write-locking mmap_lock, operate correctly after introduction of per-vma locks. With per-vma locks page faults can be handled under vma lock without taking mmap_lock at all, so write locking mmap_lock would not stop them. The change ensures vmas are properly locked during such walks. A sample issue this solves is do_mbind() performing queue_pages_range() to queue pages for migration. Without this change a concurrent page can be faulted into the area and be left out of migration. Link: https://lkml.kernel.org/r/20230804152724.3090321-2-surenb@google.com Signed-off-by: Suren Baghdasaryan <surenb@google.com> Suggested-by: Linus Torvalds <torvalds@linuxfoundation.org> Suggested-by: Jann Horn <jannh@google.com> Cc: David Hildenbrand <david@redhat.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Hugh Dickins <hughd@google.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Laurent Dufour <ldufour@linux.ibm.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Michel Lespinasse <michel@lespinasse.org> Cc: Peter Xu <peterx@redhat.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
133 lines
5.2 KiB
C
133 lines
5.2 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_PAGEWALK_H
|
|
#define _LINUX_PAGEWALK_H
|
|
|
|
#include <linux/mm.h>
|
|
|
|
struct mm_walk;
|
|
|
|
/* Locking requirement during a page walk. */
|
|
enum page_walk_lock {
|
|
/* mmap_lock should be locked for read to stabilize the vma tree */
|
|
PGWALK_RDLOCK = 0,
|
|
/* vma will be write-locked during the walk */
|
|
PGWALK_WRLOCK = 1,
|
|
/* vma is expected to be already write-locked during the walk */
|
|
PGWALK_WRLOCK_VERIFY = 2,
|
|
};
|
|
|
|
/**
|
|
* struct mm_walk_ops - callbacks for walk_page_range
|
|
* @pgd_entry: if set, called for each non-empty PGD (top-level) entry
|
|
* @p4d_entry: if set, called for each non-empty P4D entry
|
|
* @pud_entry: if set, called for each non-empty PUD entry
|
|
* @pmd_entry: if set, called for each non-empty PMD entry
|
|
* this handler is required to be able to handle
|
|
* pmd_trans_huge() pmds. They may simply choose to
|
|
* split_huge_page() instead of handling it explicitly.
|
|
* @pte_entry: if set, called for each PTE (lowest-level) entry,
|
|
* including empty ones
|
|
* @pte_hole: if set, called for each hole at all levels,
|
|
* depth is -1 if not known, 0:PGD, 1:P4D, 2:PUD, 3:PMD.
|
|
* Any folded depths (where PTRS_PER_P?D is equal to 1)
|
|
* are skipped.
|
|
* @hugetlb_entry: if set, called for each hugetlb entry. This hook
|
|
* function is called with the vma lock held, in order to
|
|
* protect against a concurrent freeing of the pte_t* or
|
|
* the ptl. In some cases, the hook function needs to drop
|
|
* and retake the vma lock in order to avoid deadlocks
|
|
* while calling other functions. In such cases the hook
|
|
* function must either refrain from accessing the pte or
|
|
* ptl after dropping the vma lock, or else revalidate
|
|
* those items after re-acquiring the vma lock and before
|
|
* accessing them.
|
|
* @test_walk: caller specific callback function to determine whether
|
|
* we walk over the current vma or not. Returning 0 means
|
|
* "do page table walk over the current vma", returning
|
|
* a negative value means "abort current page table walk
|
|
* right now" and returning 1 means "skip the current vma"
|
|
* Note that this callback is not called when the caller
|
|
* passes in a single VMA as for walk_page_vma().
|
|
* @pre_vma: if set, called before starting walk on a non-null vma.
|
|
* @post_vma: if set, called after a walk on a non-null vma, provided
|
|
* that @pre_vma and the vma walk succeeded.
|
|
*
|
|
* p?d_entry callbacks are called even if those levels are folded on a
|
|
* particular architecture/configuration.
|
|
*/
|
|
struct mm_walk_ops {
|
|
int (*pgd_entry)(pgd_t *pgd, unsigned long addr,
|
|
unsigned long next, struct mm_walk *walk);
|
|
int (*p4d_entry)(p4d_t *p4d, unsigned long addr,
|
|
unsigned long next, struct mm_walk *walk);
|
|
int (*pud_entry)(pud_t *pud, unsigned long addr,
|
|
unsigned long next, struct mm_walk *walk);
|
|
int (*pmd_entry)(pmd_t *pmd, unsigned long addr,
|
|
unsigned long next, struct mm_walk *walk);
|
|
int (*pte_entry)(pte_t *pte, unsigned long addr,
|
|
unsigned long next, struct mm_walk *walk);
|
|
int (*pte_hole)(unsigned long addr, unsigned long next,
|
|
int depth, struct mm_walk *walk);
|
|
int (*hugetlb_entry)(pte_t *pte, unsigned long hmask,
|
|
unsigned long addr, unsigned long next,
|
|
struct mm_walk *walk);
|
|
int (*test_walk)(unsigned long addr, unsigned long next,
|
|
struct mm_walk *walk);
|
|
int (*pre_vma)(unsigned long start, unsigned long end,
|
|
struct mm_walk *walk);
|
|
void (*post_vma)(struct mm_walk *walk);
|
|
enum page_walk_lock walk_lock;
|
|
};
|
|
|
|
/*
|
|
* Action for pud_entry / pmd_entry callbacks.
|
|
* ACTION_SUBTREE is the default
|
|
*/
|
|
enum page_walk_action {
|
|
/* Descend to next level, splitting huge pages if needed and possible */
|
|
ACTION_SUBTREE = 0,
|
|
/* Continue to next entry at this level (ignoring any subtree) */
|
|
ACTION_CONTINUE = 1,
|
|
/* Call again for this entry */
|
|
ACTION_AGAIN = 2
|
|
};
|
|
|
|
/**
|
|
* struct mm_walk - walk_page_range data
|
|
* @ops: operation to call during the walk
|
|
* @mm: mm_struct representing the target process of page table walk
|
|
* @pgd: pointer to PGD; only valid with no_vma (otherwise set to NULL)
|
|
* @vma: vma currently walked (NULL if walking outside vmas)
|
|
* @action: next action to perform (see enum page_walk_action)
|
|
* @no_vma: walk ignoring vmas (vma will always be NULL)
|
|
* @private: private data for callbacks' usage
|
|
*
|
|
* (see the comment on walk_page_range() for more details)
|
|
*/
|
|
struct mm_walk {
|
|
const struct mm_walk_ops *ops;
|
|
struct mm_struct *mm;
|
|
pgd_t *pgd;
|
|
struct vm_area_struct *vma;
|
|
enum page_walk_action action;
|
|
bool no_vma;
|
|
void *private;
|
|
};
|
|
|
|
int walk_page_range(struct mm_struct *mm, unsigned long start,
|
|
unsigned long end, const struct mm_walk_ops *ops,
|
|
void *private);
|
|
int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
|
|
unsigned long end, const struct mm_walk_ops *ops,
|
|
pgd_t *pgd,
|
|
void *private);
|
|
int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start,
|
|
unsigned long end, const struct mm_walk_ops *ops,
|
|
void *private);
|
|
int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
|
|
void *private);
|
|
int walk_page_mapping(struct address_space *mapping, pgoff_t first_index,
|
|
pgoff_t nr, const struct mm_walk_ops *ops,
|
|
void *private);
|
|
|
|
#endif /* _LINUX_PAGEWALK_H */
|