From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
To: linux-mm@kvack.org
Cc: "Matthew Wilcox (Oracle)" <willy@infradead.org>,
Andrew Morton <akpm@linux-foundation.org>,
Hugh Dickins <hughd@google.com>,
William Kucharski <william.kucharski@oracle.com>,
Johannes Weiner <hannes@cmpxchg.org>, Jan Kara <jack@suse.cz>,
Yang Shi <yang.shi@linux.alibaba.com>,
Dave Chinner <dchinner@redhat.com>,
linux-kernel@vger.kernel.org
Subject: [PATCH v2 05/12] mm: Add and use find_lock_entries
Date: Mon, 14 Sep 2020 14:00:35 +0100 [thread overview]
Message-ID: <20200914130042.11442-6-willy@infradead.org> (raw)
In-Reply-To: <20200914130042.11442-1-willy@infradead.org>
We have three functions (shmem_undo_range(), truncate_inode_pages_range()
and invalidate_mapping_pages()) which want exactly this function, so
add it to filemap.c.
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
---
mm/filemap.c | 57 ++++++++++++++++++++++++++++++++
mm/internal.h | 2 ++
mm/shmem.c | 22 +++----------
mm/truncate.c | 90 +++++++--------------------------------------------
4 files changed, 75 insertions(+), 96 deletions(-)
diff --git a/mm/filemap.c b/mm/filemap.c
index 5662f932b85b..9f7f6b46aee4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -1854,6 +1854,63 @@ unsigned find_get_entries(struct address_space *mapping,
return ret;
}
+/**
+ * find_lock_entries - Find a batch of pagecache entries.
+ * @mapping: The address_space to search.
+ * @start: The starting page cache index.
+ * @end: The final page index (inclusive).
+ * @pvec: Where the resulting entries are placed.
+ * @indices: The cache indices of the entries in @pvec.
+ *
+ * find_lock_entries() will return a batch of entries from @mapping.
+ * Swap, shadow and DAX entries are included. Pages are returned
+ * locked and with an incremented refcount. Pages which are locked by
+ * somebody else or under writeback are skipped. Only the head page of
+ * a THP is returned. Pages which are partially outside the range are
+ * not returned.
+ *
+ * The entries have ascending indexes. The indices may not be consecutive
+ * due to not-present entries, THP pages, pages which could not be locked
+ * or pages under writeback.
+ *
+ * Return: The number of entries which were found.
+ */
+unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
+ pgoff_t end, struct pagevec *pvec, pgoff_t *indices)
+{
+ XA_STATE(xas, &mapping->i_pages, start);
+ struct page *page;
+
+ rcu_read_lock();
+ while ((page = xas_find_get_entry(&xas, end, XA_PRESENT))) {
+ if (!xa_is_value(page)) {
+ if (page->index < start)
+ goto put;
+ VM_BUG_ON_PAGE(page->index != xas.xa_index, page);
+ if (page->index + thp_nr_pages(page) - 1 > end)
+ goto put;
+ if (!trylock_page(page))
+ goto put;
+ if (page->mapping != mapping || PageWriteback(page))
+ goto unlock;
+ }
+ indices[pvec->nr] = xas.xa_index;
+ if (!pagevec_add(pvec, page))
+ break;
+ goto next;
+unlock:
+ unlock_page(page);
+put:
+ put_page(page);
+next:
+ if (!xa_is_value(page) && PageTransHuge(page))
+ xas_set(&xas, page->index + thp_nr_pages(page));
+ }
+ rcu_read_unlock();
+
+ return pagevec_count(pvec);
+}
+
/**
* find_get_pages_range - gang pagecache lookup
* @mapping: The address_space to search
diff --git a/mm/internal.h b/mm/internal.h
index 6345b08ce86c..1c5f4425ed74 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -62,6 +62,8 @@ static inline void force_page_cache_readahead(struct address_space *mapping,
struct page *find_get_entry(struct address_space *mapping, pgoff_t index);
struct page *find_lock_entry(struct address_space *mapping, pgoff_t index);
+unsigned find_lock_entries(struct address_space *mapping, pgoff_t start,
+ pgoff_t end, struct pagevec *pvec, pgoff_t *indices);
/**
* page_evictable - test whether a page is evictable
diff --git a/mm/shmem.c b/mm/shmem.c
index b65263d9bb67..a73ce8ce28e3 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -905,12 +905,8 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
pagevec_init(&pvec);
index = start;
- while (index < end) {
- pvec.nr = find_get_entries(mapping, index,
- min(end - index, (pgoff_t)PAGEVEC_SIZE),
- pvec.pages, indices);
- if (!pvec.nr)
- break;
+ while (index < end && find_lock_entries(mapping, index, end - 1,
+ &pvec, indices)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
@@ -925,18 +921,10 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
index, page);
continue;
}
+ index += thp_nr_pages(page) - 1;
- VM_BUG_ON_PAGE(page_to_pgoff(page) != index, page);
-
- if (!trylock_page(page))
- continue;
-
- if ((!unfalloc || !PageUptodate(page)) &&
- page_mapping(page) == mapping) {
- VM_BUG_ON_PAGE(PageWriteback(page), page);
- if (shmem_punch_compound(page, start, end))
- truncate_inode_page(mapping, page);
- }
+ if (!unfalloc || !PageUptodate(page))
+ truncate_inode_page(mapping, page);
unlock_page(page);
}
pagevec_remove_exceptionals(&pvec);
diff --git a/mm/truncate.c b/mm/truncate.c
index 1cc93b57fb41..5dbe0c77b5ac 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -326,51 +326,19 @@ void truncate_inode_pages_range(struct address_space *mapping,
pagevec_init(&pvec);
index = start;
- while (index < end && pagevec_lookup_entries(&pvec, mapping, index,
- min(end - index, (pgoff_t)PAGEVEC_SIZE),
- indices)) {
- /*
- * Pagevec array has exceptional entries and we may also fail
- * to lock some pages. So we store pages that can be deleted
- * in a new pagevec.
- */
- struct pagevec locked_pvec;
-
- pagevec_init(&locked_pvec);
- for (i = 0; i < pagevec_count(&pvec); i++) {
- struct page *page = pvec.pages[i];
-
- /* We rely upon deletion not changing page->index */
- index = indices[i];
- if (index >= end)
- break;
-
- if (xa_is_value(page))
- continue;
-
- if (!trylock_page(page))
- continue;
- WARN_ON(page_to_index(page) != index);
- if (PageWriteback(page)) {
- unlock_page(page);
- continue;
- }
- if (page->mapping != mapping) {
- unlock_page(page);
- continue;
- }
- pagevec_add(&locked_pvec, page);
- }
- for (i = 0; i < pagevec_count(&locked_pvec); i++)
- truncate_cleanup_page(mapping, locked_pvec.pages[i]);
- delete_from_page_cache_batch(mapping, &locked_pvec);
- for (i = 0; i < pagevec_count(&locked_pvec); i++)
- unlock_page(locked_pvec.pages[i]);
+ while (index < end && find_lock_entries(mapping, index, end - 1,
+ &pvec, indices)) {
+ index = indices[pagevec_count(&pvec) - 1] + 1;
truncate_exceptional_pvec_entries(mapping, &pvec, indices, end);
+ for (i = 0; i < pagevec_count(&pvec); i++)
+ truncate_cleanup_page(mapping, pvec.pages[i]);
+ delete_from_page_cache_batch(mapping, &pvec);
+ for (i = 0; i < pagevec_count(&pvec); i++)
+ unlock_page(pvec.pages[i]);
pagevec_release(&pvec);
cond_resched();
- index++;
}
+
if (partial_start) {
struct page *page = find_lock_page(mapping, start - 1);
if (page) {
@@ -554,9 +522,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
int i;
pagevec_init(&pvec);
- while (index <= end && pagevec_lookup_entries(&pvec, mapping, index,
- min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
- indices)) {
+ while (find_lock_entries(mapping, index, end, &pvec, indices)) {
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
@@ -570,39 +536,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
page);
continue;
}
-
- if (!trylock_page(page))
- continue;
-
- WARN_ON(page_to_index(page) != index);
-
- /* Middle of THP: skip */
- if (PageTransTail(page)) {
- unlock_page(page);
- continue;
- } else if (PageTransHuge(page)) {
- index += HPAGE_PMD_NR - 1;
- i += HPAGE_PMD_NR - 1;
- /*
- * 'end' is in the middle of THP. Don't
- * invalidate the page as the part outside of
- * 'end' could be still useful.
- */
- if (index > end) {
- unlock_page(page);
- continue;
- }
-
- /* Take a pin outside pagevec */
- get_page(page);
-
- /*
- * Drop extra pins before trying to invalidate
- * the huge page.
- */
- pagevec_remove_exceptionals(&pvec);
- pagevec_release(&pvec);
- }
+ index += thp_nr_pages(page) - 1;
ret = invalidate_inode_page(page);
unlock_page(page);
@@ -612,8 +546,6 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
*/
if (!ret)
deactivate_file_page(page);
- if (PageTransHuge(page))
- put_page(page);
count += ret;
}
pagevec_remove_exceptionals(&pvec);
--
2.28.0
next prev parent reply other threads:[~2020-09-14 13:01 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-14 13:00 [PATCH v2 00/12] Overhaul multi-page lookups for THP Matthew Wilcox (Oracle)
2020-09-14 13:00 ` [PATCH v2 01/12] mm: Make pagecache tagged lookups return only head pages Matthew Wilcox (Oracle)
2020-09-29 9:13 ` Jan Kara
2020-09-14 13:00 ` [PATCH v2 02/12] mm/shmem: Use pagevec_lookup in shmem_unlock_mapping Matthew Wilcox (Oracle)
2020-09-29 8:28 ` Jan Kara
2020-09-29 18:36 ` Matthew Wilcox
2020-09-14 13:00 ` [PATCH v2 03/12] mm/filemap: Add helper for finding pages Matthew Wilcox (Oracle)
2020-09-29 8:27 ` Jan Kara
2020-09-14 13:00 ` [PATCH v2 04/12] mm/filemap: Add mapping_seek_hole_data Matthew Wilcox (Oracle)
2020-09-29 8:46 ` Jan Kara
2020-09-29 12:42 ` Matthew Wilcox
2020-09-29 13:39 ` Matthew Wilcox
2020-09-14 13:00 ` Matthew Wilcox (Oracle) [this message]
2020-09-29 8:58 ` [PATCH v2 05/12] mm: Add and use find_lock_entries Jan Kara
2020-09-29 12:48 ` Matthew Wilcox
2020-09-30 10:40 ` Jan Kara
2020-09-14 13:00 ` [PATCH v2 06/12] mm: Add an 'end' parameter to find_get_entries Matthew Wilcox (Oracle)
2020-09-14 13:00 ` [PATCH v2 07/12] mm: Add an 'end' parameter to pagevec_lookup_entries Matthew Wilcox (Oracle)
2020-09-29 9:02 ` Jan Kara
2020-09-14 13:00 ` [PATCH v2 08/12] mm: Remove nr_entries parameter from pagevec_lookup_entries Matthew Wilcox (Oracle)
2020-09-29 9:03 ` Jan Kara
2020-09-14 13:00 ` [PATCH v2 09/12] mm: Pass pvec directly to find_get_entries Matthew Wilcox (Oracle)
2020-09-29 9:07 ` Jan Kara
2020-09-14 13:00 ` [PATCH v2 10/12] mm: Remove pagevec_lookup_entries Matthew Wilcox (Oracle)
2020-09-29 9:08 ` Jan Kara
2020-09-14 13:00 ` [PATCH v2 11/12] mm/truncate,shmem: Handle truncates that split THPs Matthew Wilcox (Oracle)
2020-09-30 11:59 ` Jan Kara
2020-09-30 14:51 ` Matthew Wilcox
2020-09-14 13:00 ` [PATCH v2 12/12] mm/filemap: Return only head pages from find_get_entries Matthew Wilcox (Oracle)
2020-09-30 12:15 ` Jan Kara
2020-09-30 12:36 ` Matthew Wilcox
2020-09-30 17:08 ` Jan Kara
2020-09-30 17:23 ` Matthew Wilcox
2020-10-01 7:17 ` Jan Kara
2020-10-25 23:19 ` Matthew Wilcox
2020-10-26 9:11 ` Jan Kara
2020-09-28 20:13 ` [PATCH v2 00/12] Overhaul multi-page lookups for THP Matthew Wilcox
2020-09-29 8:50 ` William Kucharski
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20200914130042.11442-6-willy@infradead.org \
--to=willy@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=dchinner@redhat.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=jack@suse.cz \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=william.kucharski@oracle.com \
--cc=yang.shi@linux.alibaba.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).