summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorHugh Dickins <hughd@google.com>2021-09-02 14:54:34 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-09-03 09:58:12 -0700
commitacdd9f8e0fed9f1bd7e83a8ff934694bb4c9a72b (patch)
tree4fb4fd74ae8c1086a715d7515a2d7187b20190c5
parentc852023e6fd4fa5f75175729e0b55abb062ca799 (diff)
huge tmpfs: SGP_NOALLOC to stop collapse_file() on race
khugepaged's collapse_file() currently uses SGP_NOHUGE to tell shmem_getpage() not to try allocating a huge page, in the very unlikely event that a racing hole-punch removes the swapped or fallocated page as soon as i_pages lock is dropped. We want to consolidate shmem's huge decisions, removing SGP_HUGE and SGP_NOHUGE; but cannot quite persuade ourselves that it's okay to regress the protection in this case - Yang Shi points out that the huge page would remain indefinitely, charged to root instead of the intended memcg. collapse_file() should not even allocate a small page in this case: why proceed if someone is punching a hole? SGP_READ is almost the right flag here, except that it optimizes away from a fallocated page, with NULL to tell caller to fill with zeroes (like a hole); whereas collapse_file()'s sequence relies on using a cache page. Add SGP_NOALLOC just for this. There are too many consecutive "if (page"s there in shmem_getpage_gfp(): group it better; and fix the outdated "bring it back from swap" comment. Link: https://lkml.kernel.org/r/1355343b-acf-4653-ef79-6aee40214ac5@google.com Signed-off-by: Hugh Dickins <hughd@google.com> Reviewed-by: Yang Shi <shy828301@gmail.com> Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com> Cc: Matthew Wilcox <willy@infradead.org> Cc: Miaohe Lin <linmiaohe@huawei.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Rik van Riel <riel@surriel.com> Cc: Shakeel Butt <shakeelb@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
-rw-r--r--include/linux/shmem_fs.h1
-rw-r--r--mm/khugepaged.c2
-rw-r--r--mm/shmem.c29
3 files changed, 19 insertions, 13 deletions
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index bfc5899d18e0..a3f4502ec8a9 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -94,6 +94,7 @@ extern unsigned long shmem_partial_swap_usage(struct address_space *mapping,
/* Flag allocation requirements to shmem_getpage */
enum sgp_type {
SGP_READ, /* don't exceed i_size, don't allocate page */
+ SGP_NOALLOC, /* similar, but fail on hole or use fallocated page */
SGP_CACHE, /* don't exceed i_size, may allocate page */
SGP_NOHUGE, /* like SGP_CACHE, but no huge pages */
SGP_HUGE, /* like SGP_CACHE, huge pages preferred */
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index b0412be08fa2..045cc579f724 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1721,7 +1721,7 @@ static void collapse_file(struct mm_struct *mm,
xas_unlock_irq(&xas);
/* swap in or instantiate fallocated page */
if (shmem_getpage(mapping->host, index, &page,
- SGP_NOHUGE)) {
+ SGP_NOALLOC)) {
result = SCAN_FAIL;
goto xa_unlocked;
}
diff --git a/mm/shmem.c b/mm/shmem.c
index 2df6a5370cd7..867cb404090a 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1854,26 +1854,31 @@ repeat:
return error;
}
- if (page)
+ if (page) {
hindex = page->index;
- if (page && sgp == SGP_WRITE)
- mark_page_accessed(page);
-
- /* fallocated page? */
- if (page && !PageUptodate(page)) {
+ if (sgp == SGP_WRITE)
+ mark_page_accessed(page);
+ if (PageUptodate(page))
+ goto out;
+ /* fallocated page */
if (sgp != SGP_READ)
goto clear;
unlock_page(page);
put_page(page);
- page = NULL;
- hindex = index;
}
- if (page || sgp == SGP_READ)
- goto out;
/*
- * Fast cache lookup did not find it:
- * bring it back from swap or allocate.
+ * SGP_READ: succeed on hole, with NULL page, letting caller zero.
+ * SGP_NOALLOC: fail on hole, with NULL page, letting caller fail.
+ */
+ *pagep = NULL;
+ if (sgp == SGP_READ)
+ return 0;
+ if (sgp == SGP_NOALLOC)
+ return -ENOENT;
+
+ /*
+ * Fast cache lookup and swap lookup did not find it: allocate.
*/
if (vma && userfaultfd_missing(vma)) {