Transparent Huge Pages are currently stored in i_pages as pointers to
consecutive subpages. This patch changes that to storing consecutive
pointers to the head page in preparation for storing huge pages more
efficiently in i_pages.
Large parts of this are "inspired" by Kirill's patch
https://lore.kernel.org/lkml/[email protected]/
Signed-off-by: Matthew Wilcox <[email protected]>
Acked-by: Jan Kara <[email protected]>
Reviewed-by: Kirill Shutemov <[email protected]>
---
include/linux/pagemap.h | 9 +++
mm/filemap.c | 158 ++++++++++++++++------------------------
mm/huge_memory.c | 3 +
mm/khugepaged.c | 4 +-
mm/memfd.c | 2 +
mm/migrate.c | 2 +-
mm/shmem.c | 2 +-
mm/swap_state.c | 4 +-
8 files changed, 81 insertions(+), 103 deletions(-)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index bcf909d0de5f..7d58e4e0b68e 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -333,6 +333,15 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
mapping_gfp_mask(mapping));
}
+static inline struct page *find_subpage(struct page *page, pgoff_t offset)
+{
+ VM_BUG_ON_PAGE(PageTail(page), page);
+ VM_BUG_ON_PAGE(page->index > offset, page);
+ VM_BUG_ON_PAGE(page->index + (1 << compound_order(page)) <= offset,
+ page);
+ return page - page->index + offset;
+}
+
struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
diff --git a/mm/filemap.c b/mm/filemap.c
index 5673672fd444..d9161cae11b5 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -279,11 +279,11 @@ EXPORT_SYMBOL(delete_from_page_cache);
* @pvec: pagevec with pages to delete
*
* The function walks over mapping->i_pages and removes pages passed in @pvec
- * from the mapping. The function expects @pvec to be sorted by page index.
+ * from the mapping. The function expects @pvec to be sorted by page index
+ * and is optimised for it to be dense.
* It tolerates holes in @pvec (mapping entries at those indices are not
* modified). The function expects only THP head pages to be present in the
- * @pvec and takes care to delete all corresponding tail pages from the
- * mapping as well.
+ * @pvec.
*
* The function expects the i_pages lock to be held.
*/
@@ -292,40 +292,43 @@ static void page_cache_delete_batch(struct address_space *mapping,
{
XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index);
int total_pages = 0;
- int i = 0, tail_pages = 0;
+ int i = 0;
struct page *page;
mapping_set_update(&xas, mapping);
xas_for_each(&xas, page, ULONG_MAX) {
- if (i >= pagevec_count(pvec) && !tail_pages)
+ if (i >= pagevec_count(pvec))
break;
+
+ /* A swap/dax/shadow entry got inserted? Skip it. */
if (xa_is_value(page))
continue;
- if (!tail_pages) {
- /*
- * Some page got inserted in our range? Skip it. We
- * have our pages locked so they are protected from
- * being removed.
- */
- if (page != pvec->pages[i]) {
- VM_BUG_ON_PAGE(page->index >
- pvec->pages[i]->index, page);
- continue;
- }
- WARN_ON_ONCE(!PageLocked(page));
- if (PageTransHuge(page) && !PageHuge(page))
- tail_pages = HPAGE_PMD_NR - 1;
+ /*
+ * A page got inserted in our range? Skip it. We have our
+ * pages locked so they are protected from being removed.
+ * If we see a page whose index is higher than ours, it
+ * means our page has been removed, which shouldn't be
+ * possible because we're holding the PageLock.
+ */
+ if (page != pvec->pages[i]) {
+ VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index,
+ page);
+ continue;
+ }
+
+ WARN_ON_ONCE(!PageLocked(page));
+
+ if (page->index == xas.xa_index)
page->mapping = NULL;
- /*
- * Leave page->index set: truncation lookup relies
- * upon it
- */
+ /* Leave page->index set: truncation lookup relies on it */
+
+ /*
+ * Move to the next page in the vector if this is a small page
+ * or the index is of the last page in this compound page).
+ */
+ if (page->index + (1UL << compound_order(page)) - 1 ==
+ xas.xa_index)
i++;
- } else {
- VM_BUG_ON_PAGE(page->index + HPAGE_PMD_NR - tail_pages
- != pvec->pages[i]->index, page);
- tail_pages--;
- }
xas_store(&xas, NULL);
total_pages++;
}
@@ -1491,7 +1494,7 @@ EXPORT_SYMBOL(page_cache_prev_miss);
struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
{
XA_STATE(xas, &mapping->i_pages, offset);
- struct page *head, *page;
+ struct page *page;
rcu_read_lock();
repeat:
@@ -1506,25 +1509,19 @@ struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
if (!page || xa_is_value(page))
goto out;
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
+ if (!page_cache_get_speculative(page))
goto repeat;
- /* The page was split under us? */
- if (compound_head(page) != head) {
- put_page(head);
- goto repeat;
- }
-
/*
- * Has the page moved?
+ * Has the page moved or been split?
* This is part of the lockless pagecache protocol. See
* include/linux/pagemap.h for details.
*/
if (unlikely(page != xas_reload(&xas))) {
- put_page(head);
+ put_page(page);
goto repeat;
}
+ page = find_subpage(page, offset);
out:
rcu_read_unlock();
@@ -1706,7 +1703,6 @@ unsigned find_get_entries(struct address_space *mapping,
rcu_read_lock();
xas_for_each(&xas, page, ULONG_MAX) {
- struct page *head;
if (xas_retry(&xas, page))
continue;
/*
@@ -1717,17 +1713,13 @@ unsigned find_get_entries(struct address_space *mapping,
if (xa_is_value(page))
goto export;
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
+ if (!page_cache_get_speculative(page))
goto retry;
- /* The page was split under us? */
- if (compound_head(page) != head)
- goto put_page;
-
- /* Has the page moved? */
+ /* Has the page moved or been split? */
if (unlikely(page != xas_reload(&xas)))
goto put_page;
+ page = find_subpage(page, xas.xa_index);
export:
indices[ret] = xas.xa_index;
@@ -1736,7 +1728,7 @@ unsigned find_get_entries(struct address_space *mapping,
break;
continue;
put_page:
- put_page(head);
+ put_page(page);
retry:
xas_reset(&xas);
}
@@ -1778,33 +1770,27 @@ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
rcu_read_lock();
xas_for_each(&xas, page, end) {
- struct page *head;
if (xas_retry(&xas, page))
continue;
/* Skip over shadow, swap and DAX entries */
if (xa_is_value(page))
continue;
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
+ if (!page_cache_get_speculative(page))
goto retry;
- /* The page was split under us? */
- if (compound_head(page) != head)
- goto put_page;
-
- /* Has the page moved? */
+ /* Has the page moved or been split? */
if (unlikely(page != xas_reload(&xas)))
goto put_page;
- pages[ret] = page;
+ pages[ret] = find_subpage(page, xas.xa_index);
if (++ret == nr_pages) {
*start = page->index + 1;
goto out;
}
continue;
put_page:
- put_page(head);
+ put_page(page);
retry:
xas_reset(&xas);
}
@@ -1849,7 +1835,6 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
rcu_read_lock();
for (page = xas_load(&xas); page; page = xas_next(&xas)) {
- struct page *head;
if (xas_retry(&xas, page))
continue;
/*
@@ -1859,24 +1844,19 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
if (xa_is_value(page))
break;
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
+ if (!page_cache_get_speculative(page))
goto retry;
- /* The page was split under us? */
- if (compound_head(page) != head)
- goto put_page;
-
- /* Has the page moved? */
+ /* Has the page moved or been split? */
if (unlikely(page != xas_reload(&xas)))
goto put_page;
- pages[ret] = page;
+ pages[ret] = find_subpage(page, xas.xa_index);
if (++ret == nr_pages)
break;
continue;
put_page:
- put_page(head);
+ put_page(page);
retry:
xas_reset(&xas);
}
@@ -1912,7 +1892,6 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
rcu_read_lock();
xas_for_each_marked(&xas, page, end, tag) {
- struct page *head;
if (xas_retry(&xas, page))
continue;
/*
@@ -1923,26 +1902,21 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
if (xa_is_value(page))
continue;
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
+ if (!page_cache_get_speculative(page))
goto retry;
- /* The page was split under us? */
- if (compound_head(page) != head)
- goto put_page;
-
- /* Has the page moved? */
+ /* Has the page moved or been split? */
if (unlikely(page != xas_reload(&xas)))
goto put_page;
- pages[ret] = page;
+ pages[ret] = find_subpage(page, xas.xa_index);
if (++ret == nr_pages) {
*index = page->index + 1;
goto out;
}
continue;
put_page:
- put_page(head);
+ put_page(page);
retry:
xas_reset(&xas);
}
@@ -1991,7 +1965,6 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
rcu_read_lock();
xas_for_each_marked(&xas, page, ULONG_MAX, tag) {
- struct page *head;
if (xas_retry(&xas, page))
continue;
/*
@@ -2002,17 +1975,13 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
if (xa_is_value(page))
goto export;
- head = compound_head(page);
- if (!page_cache_get_speculative(head))
+ if (!page_cache_get_speculative(page))
goto retry;
- /* The page was split under us? */
- if (compound_head(page) != head)
- goto put_page;
-
- /* Has the page moved? */
+ /* Has the page moved or been split? */
if (unlikely(page != xas_reload(&xas)))
goto put_page;
+ page = find_subpage(page, xas.xa_index);
export:
indices[ret] = xas.xa_index;
@@ -2021,7 +1990,7 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
break;
continue;
put_page:
- put_page(head);
+ put_page(page);
retry:
xas_reset(&xas);
}
@@ -2686,7 +2655,7 @@ void filemap_map_pages(struct vm_fault *vmf,
pgoff_t last_pgoff = start_pgoff;
unsigned long max_idx;
XA_STATE(xas, &mapping->i_pages, start_pgoff);
- struct page *head, *page;
+ struct page *page;
rcu_read_lock();
xas_for_each(&xas, page, end_pgoff) {
@@ -2695,24 +2664,19 @@ void filemap_map_pages(struct vm_fault *vmf,
if (xa_is_value(page))
goto next;
- head = compound_head(page);
-
/*
* Check for a locked page first, as a speculative
* reference may adversely influence page migration.
*/
- if (PageLocked(head))
+ if (PageLocked(page))
goto next;
- if (!page_cache_get_speculative(head))
+ if (!page_cache_get_speculative(page))
goto next;
- /* The page was split under us? */
- if (compound_head(page) != head)
- goto skip;
-
- /* Has the page moved? */
+ /* Has the page moved or been split? */
if (unlikely(page != xas_reload(&xas)))
goto skip;
+ page = find_subpage(page, xas.xa_index);
if (!PageUptodate(page) ||
PageReadahead(page) ||
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d4847026d4b1..7008174c033b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2458,6 +2458,9 @@ static void __split_huge_page(struct page *page, struct list_head *list,
if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head))
shmem_uncharge(head->mapping->host, 1);
put_page(head + i);
+ } else if (!PageAnon(page)) {
+ __xa_store(&head->mapping->i_pages, head[i].index,
+ head + i, 0);
}
}
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 449044378782..7ba7a1e4fa79 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1374,7 +1374,7 @@ static void collapse_shmem(struct mm_struct *mm,
result = SCAN_FAIL;
goto xa_locked;
}
- xas_store(&xas, new_page + (index % HPAGE_PMD_NR));
+ xas_store(&xas, new_page);
nr_none++;
continue;
}
@@ -1450,7 +1450,7 @@ static void collapse_shmem(struct mm_struct *mm,
list_add_tail(&page->lru, &pagelist);
/* Finally, replace with the new page. */
- xas_store(&xas, new_page + (index % HPAGE_PMD_NR));
+ xas_store(&xas, new_page);
continue;
out_unlock:
unlock_page(page);
diff --git a/mm/memfd.c b/mm/memfd.c
index 650e65a46b9c..bccbf7dff050 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -39,6 +39,7 @@ static void memfd_tag_pins(struct xa_state *xas)
xas_for_each(xas, page, ULONG_MAX) {
if (xa_is_value(page))
continue;
+ page = find_subpage(page, xas.xa_index);
if (page_count(page) - page_mapcount(page) > 1)
xas_set_mark(xas, MEMFD_TAG_PINNED);
@@ -88,6 +89,7 @@ static int memfd_wait_for_pins(struct address_space *mapping)
bool clear = true;
if (xa_is_value(page))
continue;
+ page = find_subpage(page, xas.xa_index);
if (page_count(page) - page_mapcount(page) != 1) {
/*
* On the last scan, we clean up all those tags
diff --git a/mm/migrate.c b/mm/migrate.c
index 412d5fff78d4..8cb55dd69b9c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -465,7 +465,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
for (i = 1; i < HPAGE_PMD_NR; i++) {
xas_next(&xas);
- xas_store(&xas, newpage + i);
+ xas_store(&xas, newpage);
}
}
diff --git a/mm/shmem.c b/mm/shmem.c
index c8cdaa012f18..a78d4f05a51f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -614,7 +614,7 @@ static int shmem_add_to_page_cache(struct page *page,
if (xas_error(&xas))
goto unlock;
next:
- xas_store(&xas, page + i);
+ xas_store(&xas, page);
if (++i < nr) {
xas_next(&xas);
goto next;
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 85245fdec8d9..eb714165afd2 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -132,7 +132,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp)
for (i = 0; i < nr; i++) {
VM_BUG_ON_PAGE(xas.xa_index != idx + i, page);
set_page_private(page + i, entry.val + i);
- xas_store(&xas, page + i);
+ xas_store(&xas, page);
xas_next(&xas);
}
address_space->nrpages += nr;
@@ -167,7 +167,7 @@ void __delete_from_swap_cache(struct page *page, swp_entry_t entry)
for (i = 0; i < nr; i++) {
void *entry = xas_store(&xas, NULL);
- VM_BUG_ON_PAGE(entry != page + i, entry);
+ VM_BUG_ON_PAGE(entry != page, entry);
set_page_private(page + i, 0);
xas_next(&xas);
}
--
2.20.1
On Fri, Feb 15, 2019 at 2:25 PM Matthew Wilcox <[email protected]> wrote:
>
> Transparent Huge Pages are currently stored in i_pages as pointers to
> consecutive subpages. This patch changes that to storing consecutive
> pointers to the head page in preparation for storing huge pages more
> efficiently in i_pages.
>
> Large parts of this are "inspired" by Kirill's patch
> https://lore.kernel.org/lkml/[email protected]/
>
> Signed-off-by: Matthew Wilcox <[email protected]>
> Acked-by: Jan Kara <[email protected]>
> Reviewed-by: Kirill Shutemov <[email protected]>
> ---
> include/linux/pagemap.h | 9 +++
> mm/filemap.c | 158 ++++++++++++++++------------------------
> mm/huge_memory.c | 3 +
> mm/khugepaged.c | 4 +-
> mm/memfd.c | 2 +
> mm/migrate.c | 2 +-
> mm/shmem.c | 2 +-
> mm/swap_state.c | 4 +-
> 8 files changed, 81 insertions(+), 103 deletions(-)
>
> diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
> index bcf909d0de5f..7d58e4e0b68e 100644
> --- a/include/linux/pagemap.h
> +++ b/include/linux/pagemap.h
> @@ -333,6 +333,15 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
> mapping_gfp_mask(mapping));
> }
>
> +static inline struct page *find_subpage(struct page *page, pgoff_t offset)
> +{
> + VM_BUG_ON_PAGE(PageTail(page), page);
> + VM_BUG_ON_PAGE(page->index > offset, page);
> + VM_BUG_ON_PAGE(page->index + (1 << compound_order(page)) <= offset,
> + page);
> + return page - page->index + offset;
> +}
> +
> struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
> struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
> unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
> diff --git a/mm/filemap.c b/mm/filemap.c
> index 5673672fd444..d9161cae11b5 100644
> --- a/mm/filemap.c
> +++ b/mm/filemap.c
> @@ -279,11 +279,11 @@ EXPORT_SYMBOL(delete_from_page_cache);
> * @pvec: pagevec with pages to delete
> *
> * The function walks over mapping->i_pages and removes pages passed in @pvec
> - * from the mapping. The function expects @pvec to be sorted by page index.
> + * from the mapping. The function expects @pvec to be sorted by page index
> + * and is optimised for it to be dense.
> * It tolerates holes in @pvec (mapping entries at those indices are not
> * modified). The function expects only THP head pages to be present in the
> - * @pvec and takes care to delete all corresponding tail pages from the
> - * mapping as well.
> + * @pvec.
> *
> * The function expects the i_pages lock to be held.
> */
> @@ -292,40 +292,43 @@ static void page_cache_delete_batch(struct address_space *mapping,
> {
> XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index);
> int total_pages = 0;
> - int i = 0, tail_pages = 0;
> + int i = 0;
> struct page *page;
>
> mapping_set_update(&xas, mapping);
> xas_for_each(&xas, page, ULONG_MAX) {
> - if (i >= pagevec_count(pvec) && !tail_pages)
> + if (i >= pagevec_count(pvec))
> break;
> +
> + /* A swap/dax/shadow entry got inserted? Skip it. */
> if (xa_is_value(page))
> continue;
> - if (!tail_pages) {
> - /*
> - * Some page got inserted in our range? Skip it. We
> - * have our pages locked so they are protected from
> - * being removed.
> - */
> - if (page != pvec->pages[i]) {
> - VM_BUG_ON_PAGE(page->index >
> - pvec->pages[i]->index, page);
> - continue;
> - }
> - WARN_ON_ONCE(!PageLocked(page));
> - if (PageTransHuge(page) && !PageHuge(page))
> - tail_pages = HPAGE_PMD_NR - 1;
> + /*
> + * A page got inserted in our range? Skip it. We have our
> + * pages locked so they are protected from being removed.
> + * If we see a page whose index is higher than ours, it
> + * means our page has been removed, which shouldn't be
> + * possible because we're holding the PageLock.
> + */
> + if (page != pvec->pages[i]) {
> + VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index,
> + page);
> + continue;
> + }
> +
> + WARN_ON_ONCE(!PageLocked(page));
> +
> + if (page->index == xas.xa_index)
> page->mapping = NULL;
> - /*
> - * Leave page->index set: truncation lookup relies
> - * upon it
> - */
> + /* Leave page->index set: truncation lookup relies on it */
> +
> + /*
> + * Move to the next page in the vector if this is a small page
> + * or the index is of the last page in this compound page).
> + */
> + if (page->index + (1UL << compound_order(page)) - 1 ==
> + xas.xa_index)
> i++;
> - } else {
> - VM_BUG_ON_PAGE(page->index + HPAGE_PMD_NR - tail_pages
> - != pvec->pages[i]->index, page);
> - tail_pages--;
> - }
> xas_store(&xas, NULL);
> total_pages++;
> }
> @@ -1491,7 +1494,7 @@ EXPORT_SYMBOL(page_cache_prev_miss);
> struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
> {
> XA_STATE(xas, &mapping->i_pages, offset);
> - struct page *head, *page;
> + struct page *page;
>
> rcu_read_lock();
> repeat:
> @@ -1506,25 +1509,19 @@ struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
> if (!page || xa_is_value(page))
> goto out;
>
> - head = compound_head(page);
> - if (!page_cache_get_speculative(head))
> + if (!page_cache_get_speculative(page))
> goto repeat;
>
> - /* The page was split under us? */
> - if (compound_head(page) != head) {
> - put_page(head);
> - goto repeat;
> - }
> -
> /*
> - * Has the page moved?
> + * Has the page moved or been split?
> * This is part of the lockless pagecache protocol. See
> * include/linux/pagemap.h for details.
> */
> if (unlikely(page != xas_reload(&xas))) {
> - put_page(head);
> + put_page(page);
> goto repeat;
> }
> + page = find_subpage(page, offset);
> out:
> rcu_read_unlock();
>
> @@ -1706,7 +1703,6 @@ unsigned find_get_entries(struct address_space *mapping,
>
> rcu_read_lock();
> xas_for_each(&xas, page, ULONG_MAX) {
> - struct page *head;
> if (xas_retry(&xas, page))
> continue;
> /*
> @@ -1717,17 +1713,13 @@ unsigned find_get_entries(struct address_space *mapping,
> if (xa_is_value(page))
> goto export;
>
> - head = compound_head(page);
> - if (!page_cache_get_speculative(head))
> + if (!page_cache_get_speculative(page))
> goto retry;
>
> - /* The page was split under us? */
> - if (compound_head(page) != head)
> - goto put_page;
> -
> - /* Has the page moved? */
> + /* Has the page moved or been split? */
> if (unlikely(page != xas_reload(&xas)))
> goto put_page;
> + page = find_subpage(page, xas.xa_index);
>
> export:
> indices[ret] = xas.xa_index;
> @@ -1736,7 +1728,7 @@ unsigned find_get_entries(struct address_space *mapping,
> break;
> continue;
> put_page:
> - put_page(head);
> + put_page(page);
> retry:
> xas_reset(&xas);
> }
> @@ -1778,33 +1770,27 @@ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
>
> rcu_read_lock();
> xas_for_each(&xas, page, end) {
> - struct page *head;
> if (xas_retry(&xas, page))
> continue;
> /* Skip over shadow, swap and DAX entries */
> if (xa_is_value(page))
> continue;
>
> - head = compound_head(page);
> - if (!page_cache_get_speculative(head))
> + if (!page_cache_get_speculative(page))
> goto retry;
>
> - /* The page was split under us? */
> - if (compound_head(page) != head)
> - goto put_page;
> -
> - /* Has the page moved? */
> + /* Has the page moved or been split? */
> if (unlikely(page != xas_reload(&xas)))
> goto put_page;
>
> - pages[ret] = page;
> + pages[ret] = find_subpage(page, xas.xa_index);
> if (++ret == nr_pages) {
> *start = page->index + 1;
> goto out;
> }
> continue;
> put_page:
> - put_page(head);
> + put_page(page);
> retry:
> xas_reset(&xas);
> }
> @@ -1849,7 +1835,6 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
>
> rcu_read_lock();
> for (page = xas_load(&xas); page; page = xas_next(&xas)) {
> - struct page *head;
> if (xas_retry(&xas, page))
> continue;
> /*
> @@ -1859,24 +1844,19 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
> if (xa_is_value(page))
> break;
>
> - head = compound_head(page);
> - if (!page_cache_get_speculative(head))
> + if (!page_cache_get_speculative(page))
> goto retry;
>
> - /* The page was split under us? */
> - if (compound_head(page) != head)
> - goto put_page;
> -
> - /* Has the page moved? */
> + /* Has the page moved or been split? */
> if (unlikely(page != xas_reload(&xas)))
> goto put_page;
>
> - pages[ret] = page;
> + pages[ret] = find_subpage(page, xas.xa_index);
> if (++ret == nr_pages)
> break;
> continue;
> put_page:
> - put_page(head);
> + put_page(page);
> retry:
> xas_reset(&xas);
> }
> @@ -1912,7 +1892,6 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
>
> rcu_read_lock();
> xas_for_each_marked(&xas, page, end, tag) {
> - struct page *head;
> if (xas_retry(&xas, page))
> continue;
> /*
> @@ -1923,26 +1902,21 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
> if (xa_is_value(page))
> continue;
>
> - head = compound_head(page);
> - if (!page_cache_get_speculative(head))
> + if (!page_cache_get_speculative(page))
> goto retry;
>
> - /* The page was split under us? */
> - if (compound_head(page) != head)
> - goto put_page;
> -
> - /* Has the page moved? */
> + /* Has the page moved or been split? */
> if (unlikely(page != xas_reload(&xas)))
> goto put_page;
>
> - pages[ret] = page;
> + pages[ret] = find_subpage(page, xas.xa_index);
> if (++ret == nr_pages) {
> *index = page->index + 1;
> goto out;
> }
> continue;
> put_page:
> - put_page(head);
> + put_page(page);
> retry:
> xas_reset(&xas);
> }
> @@ -1991,7 +1965,6 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
>
> rcu_read_lock();
> xas_for_each_marked(&xas, page, ULONG_MAX, tag) {
> - struct page *head;
> if (xas_retry(&xas, page))
> continue;
> /*
> @@ -2002,17 +1975,13 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
> if (xa_is_value(page))
> goto export;
>
> - head = compound_head(page);
> - if (!page_cache_get_speculative(head))
> + if (!page_cache_get_speculative(page))
> goto retry;
>
> - /* The page was split under us? */
> - if (compound_head(page) != head)
> - goto put_page;
> -
> - /* Has the page moved? */
> + /* Has the page moved or been split? */
> if (unlikely(page != xas_reload(&xas)))
> goto put_page;
> + page = find_subpage(page, xas.xa_index);
>
> export:
> indices[ret] = xas.xa_index;
> @@ -2021,7 +1990,7 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
> break;
> continue;
> put_page:
> - put_page(head);
> + put_page(page);
> retry:
> xas_reset(&xas);
> }
> @@ -2686,7 +2655,7 @@ void filemap_map_pages(struct vm_fault *vmf,
> pgoff_t last_pgoff = start_pgoff;
> unsigned long max_idx;
> XA_STATE(xas, &mapping->i_pages, start_pgoff);
> - struct page *head, *page;
> + struct page *page;
>
> rcu_read_lock();
> xas_for_each(&xas, page, end_pgoff) {
> @@ -2695,24 +2664,19 @@ void filemap_map_pages(struct vm_fault *vmf,
> if (xa_is_value(page))
> goto next;
>
> - head = compound_head(page);
> -
> /*
> * Check for a locked page first, as a speculative
> * reference may adversely influence page migration.
> */
> - if (PageLocked(head))
> + if (PageLocked(page))
> goto next;
> - if (!page_cache_get_speculative(head))
> + if (!page_cache_get_speculative(page))
> goto next;
>
> - /* The page was split under us? */
> - if (compound_head(page) != head)
> - goto skip;
> -
> - /* Has the page moved? */
> + /* Has the page moved or been split? */
> if (unlikely(page != xas_reload(&xas)))
> goto skip;
> + page = find_subpage(page, xas.xa_index);
>
> if (!PageUptodate(page) ||
> PageReadahead(page) ||
> diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> index d4847026d4b1..7008174c033b 100644
> --- a/mm/huge_memory.c
> +++ b/mm/huge_memory.c
> @@ -2458,6 +2458,9 @@ static void __split_huge_page(struct page *page, struct list_head *list,
> if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head))
> shmem_uncharge(head->mapping->host, 1);
> put_page(head + i);
> + } else if (!PageAnon(page)) {
> + __xa_store(&head->mapping->i_pages, head[i].index,
> + head + i, 0);
> }
> }
>
> diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> index 449044378782..7ba7a1e4fa79 100644
> --- a/mm/khugepaged.c
> +++ b/mm/khugepaged.c
> @@ -1374,7 +1374,7 @@ static void collapse_shmem(struct mm_struct *mm,
> result = SCAN_FAIL;
> goto xa_locked;
> }
> - xas_store(&xas, new_page + (index % HPAGE_PMD_NR));
> + xas_store(&xas, new_page);
> nr_none++;
> continue;
> }
> @@ -1450,7 +1450,7 @@ static void collapse_shmem(struct mm_struct *mm,
> list_add_tail(&page->lru, &pagelist);
>
> /* Finally, replace with the new page. */
> - xas_store(&xas, new_page + (index % HPAGE_PMD_NR));
> + xas_store(&xas, new_page);
> continue;
> out_unlock:
> unlock_page(page);
> diff --git a/mm/memfd.c b/mm/memfd.c
> index 650e65a46b9c..bccbf7dff050 100644
> --- a/mm/memfd.c
> +++ b/mm/memfd.c
> @@ -39,6 +39,7 @@ static void memfd_tag_pins(struct xa_state *xas)
> xas_for_each(xas, page, ULONG_MAX) {
> if (xa_is_value(page))
> continue;
> + page = find_subpage(page, xas.xa_index);
This should be xas->xa_index.
I fixed this and am trying to test the patch.
Thanks,
Song
> if (page_count(page) - page_mapcount(page) > 1)
> xas_set_mark(xas, MEMFD_TAG_PINNED);
>
> @@ -88,6 +89,7 @@ static int memfd_wait_for_pins(struct address_space *mapping)
> bool clear = true;
> if (xa_is_value(page))
> continue;
> + page = find_subpage(page, xas.xa_index);
> if (page_count(page) - page_mapcount(page) != 1) {
> /*
> * On the last scan, we clean up all those tags
> diff --git a/mm/migrate.c b/mm/migrate.c
> index 412d5fff78d4..8cb55dd69b9c 100644
> --- a/mm/migrate.c
> +++ b/mm/migrate.c
> @@ -465,7 +465,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
>
> for (i = 1; i < HPAGE_PMD_NR; i++) {
> xas_next(&xas);
> - xas_store(&xas, newpage + i);
> + xas_store(&xas, newpage);
> }
> }
>
> diff --git a/mm/shmem.c b/mm/shmem.c
> index c8cdaa012f18..a78d4f05a51f 100644
> --- a/mm/shmem.c
> +++ b/mm/shmem.c
> @@ -614,7 +614,7 @@ static int shmem_add_to_page_cache(struct page *page,
> if (xas_error(&xas))
> goto unlock;
> next:
> - xas_store(&xas, page + i);
> + xas_store(&xas, page);
> if (++i < nr) {
> xas_next(&xas);
> goto next;
> diff --git a/mm/swap_state.c b/mm/swap_state.c
> index 85245fdec8d9..eb714165afd2 100644
> --- a/mm/swap_state.c
> +++ b/mm/swap_state.c
> @@ -132,7 +132,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp)
> for (i = 0; i < nr; i++) {
> VM_BUG_ON_PAGE(xas.xa_index != idx + i, page);
> set_page_private(page + i, entry.val + i);
> - xas_store(&xas, page + i);
> + xas_store(&xas, page);
> xas_next(&xas);
> }
> address_space->nrpages += nr;
> @@ -167,7 +167,7 @@ void __delete_from_swap_cache(struct page *page, swp_entry_t entry)
>
> for (i = 0; i < nr; i++) {
> void *entry = xas_store(&xas, NULL);
> - VM_BUG_ON_PAGE(entry != page + i, entry);
> + VM_BUG_ON_PAGE(entry != page, entry);
> set_page_private(page + i, 0);
> xas_next(&xas);
> }
> --
> 2.20.1
>
On Fri, Mar 1, 2019 at 11:12 AM Song Liu <[email protected]> wrote:
>
> On Fri, Feb 15, 2019 at 2:25 PM Matthew Wilcox <[email protected]> wrote:
> >
> > Transparent Huge Pages are currently stored in i_pages as pointers to
> > consecutive subpages. This patch changes that to storing consecutive
> > pointers to the head page in preparation for storing huge pages more
> > efficiently in i_pages.
> >
> > Large parts of this are "inspired" by Kirill's patch
> > https://lore.kernel.org/lkml/[email protected]/
> >
> > Signed-off-by: Matthew Wilcox <[email protected]>
> > Acked-by: Jan Kara <[email protected]>
> > Reviewed-by: Kirill Shutemov <[email protected]>
I tested with shmem with huge=always and huge=advise. Both works fine.
I also run some stress tests with CONFIG_DEBUG_VM, nothing breaks.
Other than the minor fix in memfd_tag_pins(),
Reviewed-and-tested-by: Song Liu <[email protected]>
> > ---
> > include/linux/pagemap.h | 9 +++
> > mm/filemap.c | 158 ++++++++++++++++------------------------
> > mm/huge_memory.c | 3 +
> > mm/khugepaged.c | 4 +-
> > mm/memfd.c | 2 +
> > mm/migrate.c | 2 +-
> > mm/shmem.c | 2 +-
> > mm/swap_state.c | 4 +-
> > 8 files changed, 81 insertions(+), 103 deletions(-)
> >
> > diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
> > index bcf909d0de5f..7d58e4e0b68e 100644
> > --- a/include/linux/pagemap.h
> > +++ b/include/linux/pagemap.h
> > @@ -333,6 +333,15 @@ static inline struct page *grab_cache_page_nowait(struct address_space *mapping,
> > mapping_gfp_mask(mapping));
> > }
> >
> > +static inline struct page *find_subpage(struct page *page, pgoff_t offset)
> > +{
> > + VM_BUG_ON_PAGE(PageTail(page), page);
> > + VM_BUG_ON_PAGE(page->index > offset, page);
> > + VM_BUG_ON_PAGE(page->index + (1 << compound_order(page)) <= offset,
> > + page);
> > + return page - page->index + offset;
> > +}
> > +
> > struct page *find_get_entry(struct address_space *mapping, pgoff_t offset);
> > struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset);
> > unsigned find_get_entries(struct address_space *mapping, pgoff_t start,
> > diff --git a/mm/filemap.c b/mm/filemap.c
> > index 5673672fd444..d9161cae11b5 100644
> > --- a/mm/filemap.c
> > +++ b/mm/filemap.c
> > @@ -279,11 +279,11 @@ EXPORT_SYMBOL(delete_from_page_cache);
> > * @pvec: pagevec with pages to delete
> > *
> > * The function walks over mapping->i_pages and removes pages passed in @pvec
> > - * from the mapping. The function expects @pvec to be sorted by page index.
> > + * from the mapping. The function expects @pvec to be sorted by page index
> > + * and is optimised for it to be dense.
> > * It tolerates holes in @pvec (mapping entries at those indices are not
> > * modified). The function expects only THP head pages to be present in the
> > - * @pvec and takes care to delete all corresponding tail pages from the
> > - * mapping as well.
> > + * @pvec.
> > *
> > * The function expects the i_pages lock to be held.
> > */
> > @@ -292,40 +292,43 @@ static void page_cache_delete_batch(struct address_space *mapping,
> > {
> > XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index);
> > int total_pages = 0;
> > - int i = 0, tail_pages = 0;
> > + int i = 0;
> > struct page *page;
> >
> > mapping_set_update(&xas, mapping);
> > xas_for_each(&xas, page, ULONG_MAX) {
> > - if (i >= pagevec_count(pvec) && !tail_pages)
> > + if (i >= pagevec_count(pvec))
> > break;
> > +
> > + /* A swap/dax/shadow entry got inserted? Skip it. */
> > if (xa_is_value(page))
> > continue;
> > - if (!tail_pages) {
> > - /*
> > - * Some page got inserted in our range? Skip it. We
> > - * have our pages locked so they are protected from
> > - * being removed.
> > - */
> > - if (page != pvec->pages[i]) {
> > - VM_BUG_ON_PAGE(page->index >
> > - pvec->pages[i]->index, page);
> > - continue;
> > - }
> > - WARN_ON_ONCE(!PageLocked(page));
> > - if (PageTransHuge(page) && !PageHuge(page))
> > - tail_pages = HPAGE_PMD_NR - 1;
> > + /*
> > + * A page got inserted in our range? Skip it. We have our
> > + * pages locked so they are protected from being removed.
> > + * If we see a page whose index is higher than ours, it
> > + * means our page has been removed, which shouldn't be
> > + * possible because we're holding the PageLock.
> > + */
> > + if (page != pvec->pages[i]) {
> > + VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index,
> > + page);
> > + continue;
> > + }
> > +
> > + WARN_ON_ONCE(!PageLocked(page));
> > +
> > + if (page->index == xas.xa_index)
> > page->mapping = NULL;
> > - /*
> > - * Leave page->index set: truncation lookup relies
> > - * upon it
> > - */
> > + /* Leave page->index set: truncation lookup relies on it */
> > +
> > + /*
> > + * Move to the next page in the vector if this is a small page
> > + * or the index is of the last page in this compound page).
> > + */
> > + if (page->index + (1UL << compound_order(page)) - 1 ==
> > + xas.xa_index)
> > i++;
> > - } else {
> > - VM_BUG_ON_PAGE(page->index + HPAGE_PMD_NR - tail_pages
> > - != pvec->pages[i]->index, page);
> > - tail_pages--;
> > - }
> > xas_store(&xas, NULL);
> > total_pages++;
> > }
> > @@ -1491,7 +1494,7 @@ EXPORT_SYMBOL(page_cache_prev_miss);
> > struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
> > {
> > XA_STATE(xas, &mapping->i_pages, offset);
> > - struct page *head, *page;
> > + struct page *page;
> >
> > rcu_read_lock();
> > repeat:
> > @@ -1506,25 +1509,19 @@ struct page *find_get_entry(struct address_space *mapping, pgoff_t offset)
> > if (!page || xa_is_value(page))
> > goto out;
> >
> > - head = compound_head(page);
> > - if (!page_cache_get_speculative(head))
> > + if (!page_cache_get_speculative(page))
> > goto repeat;
> >
> > - /* The page was split under us? */
> > - if (compound_head(page) != head) {
> > - put_page(head);
> > - goto repeat;
> > - }
> > -
> > /*
> > - * Has the page moved?
> > + * Has the page moved or been split?
> > * This is part of the lockless pagecache protocol. See
> > * include/linux/pagemap.h for details.
> > */
> > if (unlikely(page != xas_reload(&xas))) {
> > - put_page(head);
> > + put_page(page);
> > goto repeat;
> > }
> > + page = find_subpage(page, offset);
> > out:
> > rcu_read_unlock();
> >
> > @@ -1706,7 +1703,6 @@ unsigned find_get_entries(struct address_space *mapping,
> >
> > rcu_read_lock();
> > xas_for_each(&xas, page, ULONG_MAX) {
> > - struct page *head;
> > if (xas_retry(&xas, page))
> > continue;
> > /*
> > @@ -1717,17 +1713,13 @@ unsigned find_get_entries(struct address_space *mapping,
> > if (xa_is_value(page))
> > goto export;
> >
> > - head = compound_head(page);
> > - if (!page_cache_get_speculative(head))
> > + if (!page_cache_get_speculative(page))
> > goto retry;
> >
> > - /* The page was split under us? */
> > - if (compound_head(page) != head)
> > - goto put_page;
> > -
> > - /* Has the page moved? */
> > + /* Has the page moved or been split? */
> > if (unlikely(page != xas_reload(&xas)))
> > goto put_page;
> > + page = find_subpage(page, xas.xa_index);
> >
> > export:
> > indices[ret] = xas.xa_index;
> > @@ -1736,7 +1728,7 @@ unsigned find_get_entries(struct address_space *mapping,
> > break;
> > continue;
> > put_page:
> > - put_page(head);
> > + put_page(page);
> > retry:
> > xas_reset(&xas);
> > }
> > @@ -1778,33 +1770,27 @@ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
> >
> > rcu_read_lock();
> > xas_for_each(&xas, page, end) {
> > - struct page *head;
> > if (xas_retry(&xas, page))
> > continue;
> > /* Skip over shadow, swap and DAX entries */
> > if (xa_is_value(page))
> > continue;
> >
> > - head = compound_head(page);
> > - if (!page_cache_get_speculative(head))
> > + if (!page_cache_get_speculative(page))
> > goto retry;
> >
> > - /* The page was split under us? */
> > - if (compound_head(page) != head)
> > - goto put_page;
> > -
> > - /* Has the page moved? */
> > + /* Has the page moved or been split? */
> > if (unlikely(page != xas_reload(&xas)))
> > goto put_page;
> >
> > - pages[ret] = page;
> > + pages[ret] = find_subpage(page, xas.xa_index);
> > if (++ret == nr_pages) {
> > *start = page->index + 1;
> > goto out;
> > }
> > continue;
> > put_page:
> > - put_page(head);
> > + put_page(page);
> > retry:
> > xas_reset(&xas);
> > }
> > @@ -1849,7 +1835,6 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
> >
> > rcu_read_lock();
> > for (page = xas_load(&xas); page; page = xas_next(&xas)) {
> > - struct page *head;
> > if (xas_retry(&xas, page))
> > continue;
> > /*
> > @@ -1859,24 +1844,19 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index,
> > if (xa_is_value(page))
> > break;
> >
> > - head = compound_head(page);
> > - if (!page_cache_get_speculative(head))
> > + if (!page_cache_get_speculative(page))
> > goto retry;
> >
> > - /* The page was split under us? */
> > - if (compound_head(page) != head)
> > - goto put_page;
> > -
> > - /* Has the page moved? */
> > + /* Has the page moved or been split? */
> > if (unlikely(page != xas_reload(&xas)))
> > goto put_page;
> >
> > - pages[ret] = page;
> > + pages[ret] = find_subpage(page, xas.xa_index);
> > if (++ret == nr_pages)
> > break;
> > continue;
> > put_page:
> > - put_page(head);
> > + put_page(page);
> > retry:
> > xas_reset(&xas);
> > }
> > @@ -1912,7 +1892,6 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
> >
> > rcu_read_lock();
> > xas_for_each_marked(&xas, page, end, tag) {
> > - struct page *head;
> > if (xas_retry(&xas, page))
> > continue;
> > /*
> > @@ -1923,26 +1902,21 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index,
> > if (xa_is_value(page))
> > continue;
> >
> > - head = compound_head(page);
> > - if (!page_cache_get_speculative(head))
> > + if (!page_cache_get_speculative(page))
> > goto retry;
> >
> > - /* The page was split under us? */
> > - if (compound_head(page) != head)
> > - goto put_page;
> > -
> > - /* Has the page moved? */
> > + /* Has the page moved or been split? */
> > if (unlikely(page != xas_reload(&xas)))
> > goto put_page;
> >
> > - pages[ret] = page;
> > + pages[ret] = find_subpage(page, xas.xa_index);
> > if (++ret == nr_pages) {
> > *index = page->index + 1;
> > goto out;
> > }
> > continue;
> > put_page:
> > - put_page(head);
> > + put_page(page);
> > retry:
> > xas_reset(&xas);
> > }
> > @@ -1991,7 +1965,6 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
> >
> > rcu_read_lock();
> > xas_for_each_marked(&xas, page, ULONG_MAX, tag) {
> > - struct page *head;
> > if (xas_retry(&xas, page))
> > continue;
> > /*
> > @@ -2002,17 +1975,13 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
> > if (xa_is_value(page))
> > goto export;
> >
> > - head = compound_head(page);
> > - if (!page_cache_get_speculative(head))
> > + if (!page_cache_get_speculative(page))
> > goto retry;
> >
> > - /* The page was split under us? */
> > - if (compound_head(page) != head)
> > - goto put_page;
> > -
> > - /* Has the page moved? */
> > + /* Has the page moved or been split? */
> > if (unlikely(page != xas_reload(&xas)))
> > goto put_page;
> > + page = find_subpage(page, xas.xa_index);
> >
> > export:
> > indices[ret] = xas.xa_index;
> > @@ -2021,7 +1990,7 @@ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start,
> > break;
> > continue;
> > put_page:
> > - put_page(head);
> > + put_page(page);
> > retry:
> > xas_reset(&xas);
> > }
> > @@ -2686,7 +2655,7 @@ void filemap_map_pages(struct vm_fault *vmf,
> > pgoff_t last_pgoff = start_pgoff;
> > unsigned long max_idx;
> > XA_STATE(xas, &mapping->i_pages, start_pgoff);
> > - struct page *head, *page;
> > + struct page *page;
> >
> > rcu_read_lock();
> > xas_for_each(&xas, page, end_pgoff) {
> > @@ -2695,24 +2664,19 @@ void filemap_map_pages(struct vm_fault *vmf,
> > if (xa_is_value(page))
> > goto next;
> >
> > - head = compound_head(page);
> > -
> > /*
> > * Check for a locked page first, as a speculative
> > * reference may adversely influence page migration.
> > */
> > - if (PageLocked(head))
> > + if (PageLocked(page))
> > goto next;
> > - if (!page_cache_get_speculative(head))
> > + if (!page_cache_get_speculative(page))
> > goto next;
> >
> > - /* The page was split under us? */
> > - if (compound_head(page) != head)
> > - goto skip;
> > -
> > - /* Has the page moved? */
> > + /* Has the page moved or been split? */
> > if (unlikely(page != xas_reload(&xas)))
> > goto skip;
> > + page = find_subpage(page, xas.xa_index);
> >
> > if (!PageUptodate(page) ||
> > PageReadahead(page) ||
> > diff --git a/mm/huge_memory.c b/mm/huge_memory.c
> > index d4847026d4b1..7008174c033b 100644
> > --- a/mm/huge_memory.c
> > +++ b/mm/huge_memory.c
> > @@ -2458,6 +2458,9 @@ static void __split_huge_page(struct page *page, struct list_head *list,
> > if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head))
> > shmem_uncharge(head->mapping->host, 1);
> > put_page(head + i);
> > + } else if (!PageAnon(page)) {
> > + __xa_store(&head->mapping->i_pages, head[i].index,
> > + head + i, 0);
> > }
> > }
> >
> > diff --git a/mm/khugepaged.c b/mm/khugepaged.c
> > index 449044378782..7ba7a1e4fa79 100644
> > --- a/mm/khugepaged.c
> > +++ b/mm/khugepaged.c
> > @@ -1374,7 +1374,7 @@ static void collapse_shmem(struct mm_struct *mm,
> > result = SCAN_FAIL;
> > goto xa_locked;
> > }
> > - xas_store(&xas, new_page + (index % HPAGE_PMD_NR));
> > + xas_store(&xas, new_page);
> > nr_none++;
> > continue;
> > }
> > @@ -1450,7 +1450,7 @@ static void collapse_shmem(struct mm_struct *mm,
> > list_add_tail(&page->lru, &pagelist);
> >
> > /* Finally, replace with the new page. */
> > - xas_store(&xas, new_page + (index % HPAGE_PMD_NR));
> > + xas_store(&xas, new_page);
> > continue;
> > out_unlock:
> > unlock_page(page);
> > diff --git a/mm/memfd.c b/mm/memfd.c
> > index 650e65a46b9c..bccbf7dff050 100644
> > --- a/mm/memfd.c
> > +++ b/mm/memfd.c
> > @@ -39,6 +39,7 @@ static void memfd_tag_pins(struct xa_state *xas)
> > xas_for_each(xas, page, ULONG_MAX) {
> > if (xa_is_value(page))
> > continue;
> > + page = find_subpage(page, xas.xa_index);
>
> This should be xas->xa_index.
>
> I fixed this and am trying to test the patch.
>
> Thanks,
> Song
>
> > if (page_count(page) - page_mapcount(page) > 1)
> > xas_set_mark(xas, MEMFD_TAG_PINNED);
> >
> > @@ -88,6 +89,7 @@ static int memfd_wait_for_pins(struct address_space *mapping)
> > bool clear = true;
> > if (xa_is_value(page))
> > continue;
> > + page = find_subpage(page, xas.xa_index);
> > if (page_count(page) - page_mapcount(page) != 1) {
> > /*
> > * On the last scan, we clean up all those tags
> > diff --git a/mm/migrate.c b/mm/migrate.c
> > index 412d5fff78d4..8cb55dd69b9c 100644
> > --- a/mm/migrate.c
> > +++ b/mm/migrate.c
> > @@ -465,7 +465,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
> >
> > for (i = 1; i < HPAGE_PMD_NR; i++) {
> > xas_next(&xas);
> > - xas_store(&xas, newpage + i);
> > + xas_store(&xas, newpage);
> > }
> > }
> >
> > diff --git a/mm/shmem.c b/mm/shmem.c
> > index c8cdaa012f18..a78d4f05a51f 100644
> > --- a/mm/shmem.c
> > +++ b/mm/shmem.c
> > @@ -614,7 +614,7 @@ static int shmem_add_to_page_cache(struct page *page,
> > if (xas_error(&xas))
> > goto unlock;
> > next:
> > - xas_store(&xas, page + i);
> > + xas_store(&xas, page);
> > if (++i < nr) {
> > xas_next(&xas);
> > goto next;
> > diff --git a/mm/swap_state.c b/mm/swap_state.c
> > index 85245fdec8d9..eb714165afd2 100644
> > --- a/mm/swap_state.c
> > +++ b/mm/swap_state.c
> > @@ -132,7 +132,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp)
> > for (i = 0; i < nr; i++) {
> > VM_BUG_ON_PAGE(xas.xa_index != idx + i, page);
> > set_page_private(page + i, entry.val + i);
> > - xas_store(&xas, page + i);
> > + xas_store(&xas, page);
> > xas_next(&xas);
> > }
> > address_space->nrpages += nr;
> > @@ -167,7 +167,7 @@ void __delete_from_swap_cache(struct page *page, swp_entry_t entry)
> >
> > for (i = 0; i < nr; i++) {
> > void *entry = xas_store(&xas, NULL);
> > - VM_BUG_ON_PAGE(entry != page + i, entry);
> > + VM_BUG_ON_PAGE(entry != page, entry);
> > set_page_private(page + i, 0);
> > xas_next(&xas);
> > }
> > --
> > 2.20.1
> >
Other than the bug Song found in memfd_tag_pins(), I'd like to suggest two quick
but pedantic changes to mm/filemap.c:
Though not modified in this patch, in line 284, the parenthesis should be moved
to after the period:
* modified.) The function expects only THP head pages to be present in the
> + * Move to the next page in the vector if this is a small page
> + * or the index is of the last page in this compound page).
A few lines later, there is an extraneous parenthesis, and the comment could be a bit
clearer.
Might I suggest:
* Move to the next page in the vector if this is a PAGESIZE
* page or if the index is of the last PAGESIZE page within
* this compound page.
You can say "base" instead of "PAGESIZE," but "small" seems open to interpretation.
I haven't run across any problems and have been hammering the code for over five days
without issue; all my testing was with transparent_hugepage/enabled set to
"always."
Tested-by: William Kucharski <[email protected]>
Reviewed-by: William Kucharski <[email protected]>
On Wed, Mar 06, 2019 at 02:36:35AM -0700, William Kucharski wrote:
>
> Other than the bug Song found in memfd_tag_pins(), I'd like to suggest two quick
> but pedantic changes to mm/filemap.c:
>
> Though not modified in this patch, in line 284, the parenthesis should be moved
> to after the period:
>
> * modified.) The function expects only THP head pages to be present in the
https://english.stackexchange.com/questions/6632/where-does-the-period-go-when-using-parentheses disagrees with you
> > + * Move to the next page in the vector if this is a small page
> > + * or the index is of the last page in this compound page).
>
> A few lines later, there is an extraneous parenthesis, and the comment could be a bit
> clearer.
>
> Might I suggest:
>
> * Move to the next page in the vector if this is a PAGESIZE
> * page or if the index is of the last PAGESIZE page within
> * this compound page.
>
> You can say "base" instead of "PAGESIZE," but "small" seems open to interpretation.
Agreed on the spurios close paren. The THP documentation prefers the
term 'regular page', so I went with:
* Move to the next page in the vector if this is a regular
* page or the index is of the last sub-page of this compound
* page.
> I haven't run across any problems and have been hammering the code for over five days
> without issue; all my testing was with transparent_hugepage/enabled set to
> "always."
>
> Tested-by: William Kucharski <[email protected]>
> Reviewed-by: William Kucharski <[email protected]>
Thanks!