summaryrefslogtreecommitdiff
path: root/fs
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 /fs
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 'fs')
-rw-r--r--fs/proc/task_mmu.c5
1 files changed, 5 insertions, 0 deletions
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index fc744964816e..fafff1bd34cd 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -757,12 +757,14 @@ static int smaps_hugetlb_range(pte_t *pte, unsigned long hmask,
static const struct mm_walk_ops smaps_walk_ops = {
.pmd_entry = smaps_pte_range,
.hugetlb_entry = smaps_hugetlb_range,
+ .walk_lock = PGWALK_RDLOCK,
};
static const struct mm_walk_ops smaps_shmem_walk_ops = {
.pmd_entry = smaps_pte_range,
.hugetlb_entry = smaps_hugetlb_range,
.pte_hole = smaps_pte_hole,
+ .walk_lock = PGWALK_RDLOCK,
};
/*
@@ -1244,6 +1246,7 @@ static int clear_refs_test_walk(unsigned long start, unsigned long end,
static const struct mm_walk_ops clear_refs_walk_ops = {
.pmd_entry = clear_refs_pte_range,
.test_walk = clear_refs_test_walk,
+ .walk_lock = PGWALK_WRLOCK,
};
static ssize_t clear_refs_write(struct file *file, const char __user *buf,
@@ -1621,6 +1624,7 @@ static const struct mm_walk_ops pagemap_ops = {
.pmd_entry = pagemap_pmd_range,
.pte_hole = pagemap_pte_hole,
.hugetlb_entry = pagemap_hugetlb_range,
+ .walk_lock = PGWALK_RDLOCK,
};
/*
@@ -1934,6 +1938,7 @@ static int gather_hugetlb_stats(pte_t *pte, unsigned long hmask,
static const struct mm_walk_ops show_numa_ops = {
.hugetlb_entry = gather_hugetlb_stats,
.pmd_entry = gather_pte_stats,
+ .walk_lock = PGWALK_RDLOCK,
};
/*