@@ -389,14 +389,14 @@ mlocked, munlock_vma_page() updates that
mlocked pages. Note, however, that at this point we haven't checked whether
the page is mapped by other VM_LOCKED VMAs.
-We can't call try_to_munlock(), the function that walks the reverse map to
+We can't call page_mlock(), the function that walks the reverse map to
check for other VM_LOCKED VMAs, without first isolating the page from the LRU.
-try_to_munlock() is a variant of try_to_unmap() and thus requires that the page
+page_mlock() is a variant of try_to_unmap() and thus requires that the page
not be on an LRU list [more on these below]. However, the call to
-isolate_lru_page() could fail, in which case we couldn't try_to_munlock(). So,
+isolate_lru_page() could fail, in which case we can't call page_mlock(). So,
we go ahead and clear PG_mlocked up front, as this might be the only chance we
-have. If we can successfully isolate the page, we go ahead and
-try_to_munlock(), which will restore the PG_mlocked flag and update the zone
+have. If we can successfully isolate the page, we go ahead and call
+page_mlock(), which will restore the PG_mlocked flag and update the zone
page statistics if it finds another VMA holding the page mlocked. If we fail
to isolate the page, we'll have left a potentially mlocked page on the LRU.
This is fine, because we'll catch it later if and if vmscan tries to reclaim
@@ -545,31 +545,24 @@ munlock or munmap system calls, mm teard
holepunching, and truncation of file pages and their anonymous COWed pages.
-try_to_munlock() Reverse Map Scan
+page_mlock() Reverse Map Scan
---------------------------------
-.. warning::
- [!] TODO/FIXME: a better name might be page_mlocked() - analogous to the
- page_referenced() reverse map walker.
-
When munlock_vma_page() [see section :ref:`munlock()/munlockall() System Call
Handling <munlock_munlockall_handling>` above] tries to munlock a
page, it needs to determine whether or not the page is mapped by any
VM_LOCKED VMA without actually attempting to unmap all PTEs from the
page. For this purpose, the unevictable/mlock infrastructure
-introduced a variant of try_to_unmap() called try_to_munlock().
+introduced a variant of try_to_unmap() called page_mlock().
-try_to_munlock() calls the same functions as try_to_unmap() for anonymous and
-mapped file and KSM pages with a flag argument specifying unlock versus unmap
-processing. Again, these functions walk the respective reverse maps looking
-for VM_LOCKED VMAs. When such a VMA is found, as in the try_to_unmap() case,
-the functions mlock the page via mlock_vma_page() and return SWAP_MLOCK. This
-undoes the pre-clearing of the page's PG_mlocked done by munlock_vma_page.
+page_mlock() walks the respective reverse maps looking for VM_LOCKED VMAs. When
+such a VMA is found the page is mlocked via mlock_vma_page(). This undoes the
+pre-clearing of the page's PG_mlocked done by munlock_vma_page.
-Note that try_to_munlock()'s reverse map walk must visit every VMA in a page's
+Note that page_mlock()'s reverse map walk must visit every VMA in a page's
reverse map to determine that a page is NOT mapped into any VM_LOCKED VMA.
However, the scan can terminate when it encounters a VM_LOCKED VMA.
-Although try_to_munlock() might be called a great many times when munlocking a
+Although page_mlock() might be called a great many times when munlocking a
large region or tearing down a large address space that has been mlocked via
mlockall(), overall this is a fairly rare event.
@@ -602,7 +595,7 @@ inactive lists to the appropriate node's
shrink_inactive_list() should only see SHM_LOCK'd pages that became SHM_LOCK'd
after shrink_active_list() had moved them to the inactive list, or pages mapped
into VM_LOCKED VMAs that munlock_vma_page() couldn't isolate from the LRU to
-recheck via try_to_munlock(). shrink_inactive_list() won't notice the latter,
+recheck via page_mlock(). shrink_inactive_list() won't notice the latter,
but will pass on to shrink_page_list().
shrink_page_list() again culls obviously unevictable pages that it could
@@ -87,7 +87,6 @@ struct anon_vma_chain {
enum ttu_flags {
TTU_MIGRATION = 0x1, /* migration mode */
- TTU_MUNLOCK = 0x2, /* munlock mode */
TTU_SPLIT_HUGE_PMD = 0x4, /* split huge PMD if any */
TTU_IGNORE_MLOCK = 0x8, /* ignore mlock */
@@ -240,7 +239,7 @@ int page_mkclean(struct page *);
* called in munlock()/munmap() path to check for other vmas holding
* the page mlocked.
*/
-void try_to_munlock(struct page *);
+void page_mlock(struct page *page);
void remove_migration_ptes(struct page *old, struct page *new, bool locked);
@@ -108,7 +108,7 @@ void mlock_vma_page(struct page *page)
/*
* Finish munlock after successful page isolation
*
- * Page must be locked. This is a wrapper for try_to_munlock()
+ * Page must be locked. This is a wrapper for page_mlock()
* and putback_lru_page() with munlock accounting.
*/
static void __munlock_isolated_page(struct page *page)
@@ -118,7 +118,7 @@ static void __munlock_isolated_page(stru
* and we don't need to check all the other vmas.
*/
if (page_mapcount(page) > 1)
- try_to_munlock(page);
+ page_mlock(page);
/* Did try_to_unlock() succeed or punt? */
if (!PageMlocked(page))
@@ -158,7 +158,7 @@ static void __munlock_isolation_failed(s
* munlock()ed or munmap()ed, we want to check whether other vmas hold the
* page locked so that we can leave it on the unevictable lru list and not
* bother vmscan with it. However, to walk the page's rmap list in
- * try_to_munlock() we must isolate the page from the LRU. If some other
+ * page_mlock() we must isolate the page from the LRU. If some other
* task has removed the page from the LRU, we won't be able to do that.
* So we clear the PageMlocked as we might not get another chance. If we
* can't isolate the page, we leave it for putback_lru_page() and vmscan
@@ -168,7 +168,7 @@ unsigned int munlock_vma_page(struct pag
{
int nr_pages;
- /* For try_to_munlock() and to serialize with page migration */
+ /* For page_mlock() and to serialize with page migration */
BUG_ON(!PageLocked(page));
VM_BUG_ON_PAGE(PageTail(page), page);
@@ -205,7 +205,7 @@ static int __mlock_posix_error_return(lo
*
* The fast path is available only for evictable pages with single mapping.
* Then we can bypass the per-cpu pvec and get better performance.
- * when mapcount > 1 we need try_to_munlock() which can fail.
+ * when mapcount > 1 we need page_mlock() which can fail.
* when !page_evictable(), we need the full redo logic of putback_lru_page to
* avoid leaving evictable page in unevictable list.
*
@@ -414,7 +414,7 @@ static unsigned long __munlock_pagevec_f
*
* We don't save and restore VM_LOCKED here because pages are
* still on lru. In unmap path, pages might be scanned by reclaim
- * and re-mlocked by try_to_{munlock|unmap} before we unmap and
+ * and re-mlocked by page_mlock/try_to_unmap before we unmap and
* free them. This will result in freeing mlocked pages.
*/
void munlock_vma_pages_range(struct vm_area_struct *vma,
@@ -1411,10 +1411,6 @@ static bool try_to_unmap_one(struct page
if (flags & TTU_SYNC)
pvmw.flags = PVMW_SYNC;
- /* munlock has nothing to gain from examining un-locked vmas */
- if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
- return true;
-
if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) &&
is_zone_device_page(page) && !is_device_private_page(page))
return true;
@@ -1476,8 +1472,6 @@ static bool try_to_unmap_one(struct page
page_vma_mapped_walk_done(&pvmw);
break;
}
- if (flags & TTU_MUNLOCK)
- continue;
}
/* Unexpected PMD-mapped THP? */
@@ -1790,20 +1784,58 @@ void try_to_unmap(struct page *page, enu
rmap_walk(page, &rwc);
}
+/*
+ * Walks the vma's mapping a page and mlocks the page if any locked vma's are
+ * found. Once one is found the page is locked and the scan can be terminated.
+ */
+static bool page_mlock_one(struct page *page, struct vm_area_struct *vma,
+ unsigned long address, void *unused)
+{
+ struct page_vma_mapped_walk pvmw = {
+ .page = page,
+ .vma = vma,
+ .address = address,
+ };
+
+ /* An un-locked vma doesn't have any pages to lock, continue the scan */
+ if (!(vma->vm_flags & VM_LOCKED))
+ return true;
+
+ while (page_vma_mapped_walk(&pvmw)) {
+ /*
+ * Need to recheck under the ptl to serialise with
+ * __munlock_pagevec_fill() after VM_LOCKED is cleared in
+ * munlock_vma_pages_range().
+ */
+ if (vma->vm_flags & VM_LOCKED) {
+ /* PTE-mapped THP are never mlocked */
+ if (!PageTransCompound(page))
+ mlock_vma_page(page);
+ page_vma_mapped_walk_done(&pvmw);
+ }
+
+ /*
+ * no need to continue scanning other vma's if the page has
+ * been locked.
+ */
+ return false;
+ }
+
+ return true;
+}
+
/**
- * try_to_munlock - try to munlock a page
- * @page: the page to be munlocked
+ * page_mlock - try to mlock a page
+ * @page: the page to be mlocked
*
- * Called from munlock code. Checks all of the VMAs mapping the page
- * to make sure nobody else has this page mlocked. The page will be
- * returned with PG_mlocked cleared if no other vmas have it mlocked.
+ * Called from munlock code. Checks all of the VMAs mapping the page and mlocks
+ * the page if any are found. The page will be returned with PG_mlocked cleared
+ * if it is not mapped by any locked vmas.
*/
-
-void try_to_munlock(struct page *page)
+void page_mlock(struct page *page)
{
struct rmap_walk_control rwc = {
- .rmap_one = try_to_unmap_one,
- .arg = (void *)TTU_MUNLOCK,
+ .rmap_one = page_mlock_one,
.done = page_not_mapped,
.anon_lock = page_lock_anon_vma_read,
@@ -1855,7 +1887,7 @@ static struct anon_vma *rmap_walk_anon_l
* Find all the mappings of a page using the mapping pointer and the vma chains
* contained in the anon_vma struct it points to.
*
- * When called from try_to_munlock(), the mmap_lock of the mm containing the vma
+ * When called from page_mlock(), the mmap_lock of the mm containing the vma
* where the page was found will be held for write. So, we won't recheck
* vm_flags for that VMA. That should be OK, because that vma shouldn't be
* LOCKED.
@@ -1908,7 +1940,7 @@ static void rmap_walk_anon(struct page *
* Find all the mappings of a page using the mapping pointer and the vma chains
* contained in the address_space struct it points to.
*
- * When called from try_to_munlock(), the mmap_lock of the mm containing the vma
+ * When called from page_mlock(), the mmap_lock of the mm containing the vma
* where the page was found will be held for write. So, we won't recheck
* vm_flags for that VMA. That should be OK, because that vma shouldn't be
* LOCKED.