summaryrefslogtreecommitdiff
path: root/mm/madvise.c
diff options
context:
space:
mode:
authorSuren Baghdasaryan <surenb@google.com>2023-08-04 18:27:19 +0300
committerAndrew Morton <akpm@linux-foundation.org>2023-08-21 23:07:20 +0300
commit49b0638502da097c15d46cd4e871dbaa022caf7c (patch)
treea36bae8bb4dd533dbe491ae25c3e506cd4dfb679 /mm/madvise.c
parent8b9c1cc0418a43196477083e7082568e7a4c9418 (diff)
downloadlinux-49b0638502da097c15d46cd4e871dbaa022caf7c.tar.xz
mm: enable page walking API to lock vmas during the walk
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>
Diffstat (limited to 'mm/madvise.c')
-rw-r--r--mm/madvise.c3
1 files changed, 3 insertions, 0 deletions
diff --git a/mm/madvise.c b/mm/madvise.c
index 886f06066622..bfe0e06427bd 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -233,6 +233,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start,
static const struct mm_walk_ops swapin_walk_ops = {
.pmd_entry = swapin_walk_pmd_entry,
+ .walk_lock = PGWALK_RDLOCK,
};
static void shmem_swapin_range(struct vm_area_struct *vma,
@@ -534,6 +535,7 @@ regular_folio:
static const struct mm_walk_ops cold_walk_ops = {
.pmd_entry = madvise_cold_or_pageout_pte_range,
+ .walk_lock = PGWALK_RDLOCK,
};
static void madvise_cold_page_range(struct mmu_gather *tlb,
@@ -757,6 +759,7 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
static const struct mm_walk_ops madvise_free_walk_ops = {
.pmd_entry = madvise_free_pte_range,
+ .walk_lock = PGWALK_RDLOCK,
};
static int madvise_free_single_vma(struct vm_area_struct *vma,