summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-08-03 10:35:43 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2022-08-03 10:35:43 -0700
commitf00654007fe1c154dafbdc1f5953c132e8c27c38 (patch)
tree69dd4b82b1a1be18b789ef3010b13e4834c8e353 /mm
parente087437a6fef3acc11aaa1ade84731fe1571b808 (diff)
parentcf5e7a652168fba45410ac6f5b363fcf8677dea5 (diff)
Merge tag 'folio-6.0' of git://git.infradead.org/users/willy/pagecache
Pull folio updates from Matthew Wilcox: - Fix an accounting bug that made NR_FILE_DIRTY grow without limit when running xfstests - Convert more of mpage to use folios - Remove add_to_page_cache() and add_to_page_cache_locked() - Convert find_get_pages_range() to filemap_get_folios() - Improvements to the read_cache_page() family of functions - Remove a few unnecessary checks of PageError - Some straightforward filesystem conversions to use folios - Split PageMovable users out from address_space_operations into their own movable_operations - Convert aops->migratepage to aops->migrate_folio - Remove nobh support (Christoph Hellwig) * tag 'folio-6.0' of git://git.infradead.org/users/willy/pagecache: (78 commits) fs: remove the NULL get_block case in mpage_writepages fs: don't call ->writepage from __mpage_writepage fs: remove the nobh helpers jfs: stop using the nobh helper ext2: remove nobh support ntfs3: refactor ntfs_writepages mm/folio-compat: Remove migration compatibility functions fs: Remove aops->migratepage() secretmem: Convert to migrate_folio hugetlb: Convert to migrate_folio aio: Convert to migrate_folio f2fs: Convert to filemap_migrate_folio() ubifs: Convert to filemap_migrate_folio() btrfs: Convert btrfs_migratepage to migrate_folio mm/migrate: Add filemap_migrate_folio() mm/migrate: Convert migrate_page() to migrate_folio() nfs: Convert to migrate_folio btrfs: Convert btree_migratepage to migrate_folio mm/migrate: Convert expected_page_refs() to folio_expected_refs() mm/migrate: Convert buffer_migrate_page() to buffer_migrate_folio() ...
Diffstat (limited to 'mm')
-rw-r--r--mm/balloon_compaction.c10
-rw-r--r--mm/compaction.c34
-rw-r--r--mm/filemap.c139
-rw-r--r--mm/folio-compat.c22
-rw-r--r--mm/huge_memory.c11
-rw-r--r--mm/hugetlb.c14
-rw-r--r--mm/ksm.c2
-rw-r--r--mm/memory-failure.c2
-rw-r--r--mm/migrate.c238
-rw-r--r--mm/migrate_device.c3
-rw-r--r--mm/secretmem.c13
-rw-r--r--mm/shmem.c19
-rw-r--r--mm/swap.c29
-rw-r--r--mm/swap_state.c4
-rw-r--r--mm/truncate.c2
-rw-r--r--mm/util.c4
-rw-r--r--mm/vmscan.c56
-rw-r--r--mm/z3fold.c84
-rw-r--r--mm/zsmalloc.c102
19 files changed, 314 insertions, 474 deletions
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index 4b8eab4b3f45..22c96fed70b5 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -228,10 +228,8 @@ static void balloon_page_putback(struct page *page)
spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
}
-
/* move_to_new_page() counterpart for a ballooned page */
-static int balloon_page_migrate(struct address_space *mapping,
- struct page *newpage, struct page *page,
+static int balloon_page_migrate(struct page *newpage, struct page *page,
enum migrate_mode mode)
{
struct balloon_dev_info *balloon = balloon_page_device(page);
@@ -250,11 +248,11 @@ static int balloon_page_migrate(struct address_space *mapping,
return balloon->migratepage(balloon, newpage, page, mode);
}
-const struct address_space_operations balloon_aops = {
- .migratepage = balloon_page_migrate,
+const struct movable_operations balloon_mops = {
+ .migrate_page = balloon_page_migrate,
.isolate_page = balloon_page_isolate,
.putback_page = balloon_page_putback,
};
-EXPORT_SYMBOL_GPL(balloon_aops);
+EXPORT_SYMBOL_GPL(balloon_mops);
#endif /* CONFIG_BALLOON_COMPACTION */
diff --git a/mm/compaction.c b/mm/compaction.c
index 1f89b969c12b..a2c53fcf933e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -110,28 +110,27 @@ static void split_map_pages(struct list_head *list)
}
#ifdef CONFIG_COMPACTION
-
-int PageMovable(struct page *page)
+bool PageMovable(struct page *page)
{
- struct address_space *mapping;
+ const struct movable_operations *mops;
VM_BUG_ON_PAGE(!PageLocked(page), page);
if (!__PageMovable(page))
- return 0;
+ return false;
- mapping = page_mapping(page);
- if (mapping && mapping->a_ops && mapping->a_ops->isolate_page)
- return 1;
+ mops = page_movable_ops(page);
+ if (mops)
+ return true;
- return 0;
+ return false;
}
EXPORT_SYMBOL(PageMovable);
-void __SetPageMovable(struct page *page, struct address_space *mapping)
+void __SetPageMovable(struct page *page, const struct movable_operations *mops)
{
VM_BUG_ON_PAGE(!PageLocked(page), page);
- VM_BUG_ON_PAGE((unsigned long)mapping & PAGE_MAPPING_MOVABLE, page);
- page->mapping = (void *)((unsigned long)mapping | PAGE_MAPPING_MOVABLE);
+ VM_BUG_ON_PAGE((unsigned long)mops & PAGE_MAPPING_MOVABLE, page);
+ page->mapping = (void *)((unsigned long)mops | PAGE_MAPPING_MOVABLE);
}
EXPORT_SYMBOL(__SetPageMovable);
@@ -139,12 +138,10 @@ void __ClearPageMovable(struct page *page)
{
VM_BUG_ON_PAGE(!PageMovable(page), page);
/*
- * Clear registered address_space val with keeping PAGE_MAPPING_MOVABLE
- * flag so that VM can catch up released page by driver after isolation.
- * With it, VM migration doesn't try to put it back.
+ * This page still has the type of a movable page, but it's
+ * actually not movable any more.
*/
- page->mapping = (void *)((unsigned long)page->mapping &
- PAGE_MAPPING_MOVABLE);
+ page->mapping = (void *)PAGE_MAPPING_MOVABLE;
}
EXPORT_SYMBOL(__ClearPageMovable);
@@ -1034,7 +1031,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
/*
* Only pages without mappings or that have a
- * ->migratepage callback are possible to migrate
+ * ->migrate_folio callback are possible to migrate
* without blocking. However, we can be racing with
* truncation so it's necessary to lock the page
* to stabilise the mapping as truncation holds
@@ -1045,7 +1042,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
goto isolate_fail_put;
mapping = page_mapping(page);
- migrate_dirty = !mapping || mapping->a_ops->migratepage;
+ migrate_dirty = !mapping ||
+ mapping->a_ops->migrate_folio;
unlock_page(page);
if (!migrate_dirty)
goto isolate_fail_put;
diff --git a/mm/filemap.c b/mm/filemap.c
index 254931a6e3ed..0dec96ea6688 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -929,26 +929,6 @@ error:
}
ALLOW_ERROR_INJECTION(__filemap_add_folio, ERRNO);
-/**
- * add_to_page_cache_locked - add a locked page to the pagecache
- * @page: page to add
- * @mapping: the page's address_space
- * @offset: page index
- * @gfp_mask: page allocation mode
- *
- * This function is used to add a page to the pagecache. It must be locked.
- * This function does not add the page to the LRU. The caller must do that.
- *
- * Return: %0 on success, negative error code otherwise.
- */
-int add_to_page_cache_locked(struct page *page, struct address_space *mapping,
- pgoff_t offset, gfp_t gfp_mask)
-{
- return __filemap_add_folio(mapping, page_folio(page), offset,
- gfp_mask, NULL);
-}
-EXPORT_SYMBOL(add_to_page_cache_locked);
-
int filemap_add_folio(struct address_space *mapping, struct folio *folio,
pgoff_t index, gfp_t gfp)
{
@@ -2151,65 +2131,46 @@ put:
return folio_batch_count(fbatch);
}
-static inline
-bool folio_more_pages(struct folio *folio, pgoff_t index, pgoff_t max)
-{
- if (!folio_test_large(folio) || folio_test_hugetlb(folio))
- return false;
- if (index >= max)
- return false;
- return index < folio->index + folio_nr_pages(folio) - 1;
-}
-
/**
- * find_get_pages_range - gang pagecache lookup
+ * filemap_get_folios - Get a batch of folios
* @mapping: The address_space to search
* @start: The starting page index
* @end: The final page index (inclusive)
- * @nr_pages: The maximum number of pages
- * @pages: Where the resulting pages are placed
+ * @fbatch: The batch to fill.
*
- * find_get_pages_range() will search for and return a group of up to @nr_pages
- * pages in the mapping starting at index @start and up to index @end
- * (inclusive). The pages are placed at @pages. find_get_pages_range() takes
- * a reference against the returned pages.
+ * Search for and return a batch of folios in the mapping starting at
+ * index @start and up to index @end (inclusive). The folios are returned
+ * in @fbatch with an elevated reference count.
*
- * The search returns a group of mapping-contiguous pages with ascending
- * indexes. There may be holes in the indices due to not-present pages.
- * We also update @start to index the next page for the traversal.
+ * The first folio may start before @start; if it does, it will contain
+ * @start. The final folio may extend beyond @end; if it does, it will
+ * contain @end. The folios have ascending indices. There may be gaps
+ * between the folios if there are indices which have no folio in the
+ * page cache. If folios are added to or removed from the page cache
+ * while this is running, they may or may not be found by this call.
*
- * Return: the number of pages which were found. If this number is
- * smaller than @nr_pages, the end of specified range has been
- * reached.
+ * Return: The number of folios which were found.
+ * We also update @start to index the next folio for the traversal.
*/
-unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start,
- pgoff_t end, unsigned int nr_pages,
- struct page **pages)
+unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start,
+ pgoff_t end, struct folio_batch *fbatch)
{
XA_STATE(xas, &mapping->i_pages, *start);
struct folio *folio;
- unsigned ret = 0;
-
- if (unlikely(!nr_pages))
- return 0;
rcu_read_lock();
- while ((folio = find_get_entry(&xas, end, XA_PRESENT))) {
+ while ((folio = find_get_entry(&xas, end, XA_PRESENT)) != NULL) {
/* Skip over shadow, swap and DAX entries */
if (xa_is_value(folio))
continue;
+ if (!folio_batch_add(fbatch, folio)) {
+ unsigned long nr = folio_nr_pages(folio);
-again:
- pages[ret] = folio_file_page(folio, xas.xa_index);
- if (++ret == nr_pages) {
- *start = xas.xa_index + 1;
+ if (folio_test_hugetlb(folio))
+ nr = 1;
+ *start = folio->index + nr;
goto out;
}
- if (folio_more_pages(folio, xas.xa_index, end)) {
- xas.xa_index++;
- folio_ref_inc(folio);
- goto again;
- }
}
/*
@@ -2225,7 +2186,18 @@ again:
out:
rcu_read_unlock();
- return ret;
+ return folio_batch_count(fbatch);
+}
+EXPORT_SYMBOL(filemap_get_folios);
+
+static inline
+bool folio_more_pages(struct folio *folio, pgoff_t index, pgoff_t max)
+{
+ if (!folio_test_large(folio) || folio_test_hugetlb(folio))
+ return false;
+ if (index >= max)
+ return false;
+ return index < folio->index + folio_nr_pages(folio) - 1;
}
/**
@@ -2413,7 +2385,7 @@ retry:
rcu_read_unlock();
}
-static int filemap_read_folio(struct file *file, struct address_space *mapping,
+static int filemap_read_folio(struct file *file, filler_t filler,
struct folio *folio)
{
int error;
@@ -2425,7 +2397,7 @@ static int filemap_read_folio(struct file *file, struct address_space *mapping,
*/
folio_clear_error(folio);
/* Start the actual read. The read will unlock the page. */
- error = mapping->a_ops->read_folio(file, folio);
+ error = filler(file, folio);
if (error)
return error;
@@ -2434,7 +2406,8 @@ static int filemap_read_folio(struct file *file, struct address_space *mapping,
return error;
if (folio_test_uptodate(folio))
return 0;
- shrink_readahead_size_eio(&file->f_ra);
+ if (file)
+ shrink_readahead_size_eio(&file->f_ra);
return -EIO;
}
@@ -2507,7 +2480,8 @@ static int filemap_update_page(struct kiocb *iocb,
if (iocb->ki_flags & (IOCB_NOIO | IOCB_NOWAIT | IOCB_WAITQ))
goto unlock;
- error = filemap_read_folio(iocb->ki_filp, mapping, folio);
+ error = filemap_read_folio(iocb->ki_filp, mapping->a_ops->read_folio,
+ folio);
goto unlock_mapping;
unlock:
folio_unlock(folio);
@@ -2550,7 +2524,7 @@ static int filemap_create_folio(struct file *file,
if (error)
goto error;
- error = filemap_read_folio(file, mapping, folio);
+ error = filemap_read_folio(file, mapping->a_ops->read_folio, folio);
if (error)
goto error;
@@ -3234,7 +3208,7 @@ page_not_uptodate:
* and we need to check for errors.
*/
fpin = maybe_unlock_mmap_for_io(vmf, fpin);
- error = filemap_read_folio(file, mapping, folio);
+ error = filemap_read_folio(file, mapping->a_ops->read_folio, folio);
if (fpin)
goto out_retry;
folio_put(folio);
@@ -3524,20 +3498,7 @@ repeat:
return ERR_PTR(err);
}
-filler:
- err = filler(file, folio);
- if (err < 0) {
- folio_put(folio);
- return ERR_PTR(err);
- }
-
- folio_wait_locked(folio);
- if (!folio_test_uptodate(folio)) {
- folio_put(folio);
- return ERR_PTR(-EIO);
- }
-
- goto out;
+ goto filler;
}
if (folio_test_uptodate(folio))
goto out;
@@ -3560,14 +3521,14 @@ filler:
goto out;
}
- /*
- * A previous I/O error may have been due to temporary
- * failures.
- * Clear page error before actual read, PG_error will be
- * set again if read page fails.
- */
- folio_clear_error(folio);
- goto filler;
+filler:
+ err = filemap_read_folio(file, filler, folio);
+ if (err) {
+ folio_put(folio);
+ if (err == AOP_TRUNCATED_PAGE)
+ goto repeat;
+ return ERR_PTR(err);
+ }
out:
folio_mark_accessed(folio);
diff --git a/mm/folio-compat.c b/mm/folio-compat.c
index 20bc15b57d93..458618c7302c 100644
--- a/mm/folio-compat.c
+++ b/mm/folio-compat.c
@@ -51,28 +51,6 @@ void mark_page_accessed(struct page *page)
}
EXPORT_SYMBOL(mark_page_accessed);
-#ifdef CONFIG_MIGRATION
-int migrate_page_move_mapping(struct address_space *mapping,
- struct page *newpage, struct page *page, int extra_count)
-{
- return folio_migrate_mapping(mapping, page_folio(newpage),
- page_folio(page), extra_count);
-}
-EXPORT_SYMBOL(migrate_page_move_mapping);
-
-void migrate_page_states(struct page *newpage, struct page *page)
-{
- folio_migrate_flags(page_folio(newpage), page_folio(page));
-}
-EXPORT_SYMBOL(migrate_page_states);
-
-void migrate_page_copy(struct page *newpage, struct page *page)
-{
- folio_migrate_copy(page_folio(newpage), page_folio(page));
-}
-EXPORT_SYMBOL(migrate_page_copy);
-#endif
-
bool set_page_writeback(struct page *page)
{
return folio_start_writeback(page_folio(page));
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 834f288b3769..15965084816d 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -18,6 +18,7 @@
#include <linux/shrinker.h>
#include <linux/mm_inline.h>
#include <linux/swapops.h>
+#include <linux/backing-dev.h>
#include <linux/dax.h>
#include <linux/khugepaged.h>
#include <linux/freezer.h>
@@ -2440,11 +2441,15 @@ static void __split_huge_page(struct page *page, struct list_head *list,
__split_huge_page_tail(head, i, lruvec, list);
/* Some pages can be beyond EOF: drop them from page cache */
if (head[i].index >= end) {
- ClearPageDirty(head + i);
- __delete_from_page_cache(head + i, NULL);
+ struct folio *tail = page_folio(head + i);
+
if (shmem_mapping(head->mapping))
shmem_uncharge(head->mapping->host, 1);
- put_page(head + i);
+ else if (folio_test_clear_dirty(tail))
+ folio_account_cleaned(tail,
+ inode_to_wb(folio->mapping->host));
+ __filemap_remove_folio(tail, NULL);
+ folio_put(tail);
} else if (!PageAnon(page)) {
__xa_store(&head->mapping->i_pages, head[i].index,
head + i, 0);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index a18c071c294e..aa39534898e0 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -5419,19 +5419,25 @@ static bool hugetlbfs_pagecache_present(struct hstate *h,
int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
pgoff_t idx)
{
+ struct folio *folio = page_folio(page);
struct inode *inode = mapping->host;
struct hstate *h = hstate_inode(inode);
- int err = add_to_page_cache(page, mapping, idx, GFP_KERNEL);
+ int err;
- if (err)
+ __folio_set_locked(folio);
+ err = __filemap_add_folio(mapping, folio, idx, GFP_KERNEL, NULL);
+
+ if (unlikely(err)) {
+ __folio_clear_locked(folio);
return err;
+ }
ClearHPageRestoreReserve(page);
/*
- * set page dirty so that it will not be removed from cache/file
+ * mark folio dirty so that it will not be removed from cache/file
* by non-hugetlbfs specific code paths.
*/
- set_page_dirty(page);
+ folio_mark_dirty(folio);
spin_lock(&inode->i_lock);
inode->i_blocks += blocks_per_huge_page(h);
diff --git a/mm/ksm.c b/mm/ksm.c
index 54f78c9eecae..e8f8c1a2bb39 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -712,7 +712,7 @@ again:
* however, it might mean that the page is under page_ref_freeze().
* The __remove_mapping() case is easy, again the node is now stale;
* the same is in reuse_ksm_page() case; but if page is swapcache
- * in migrate_page_move_mapping(), it might still be our page,
+ * in folio_migrate_mapping(), it might still be our page,
* in which case it's essential to keep the node.
*/
while (!get_page_unless_zero(page)) {
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index da39ec8afca8..b864c2eff641 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1940,7 +1940,7 @@ try_again:
/*
* Now take care of user space mappings.
- * Abort on fail: __delete_from_page_cache() assumes unmapped page.
+ * Abort on fail: __filemap_remove_folio() assumes unmapped page.
*/
if (!hwpoison_user_mappings(p, pfn, flags, p)) {
action_result(pfn, MF_MSG_UNMAP_FAILED, MF_IGNORED);
diff --git a/mm/migrate.c b/mm/migrate.c
index 6c1ea61f39d8..1b4b977809a1 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -59,7 +59,7 @@
int isolate_movable_page(struct page *page, isolate_mode_t mode)
{
- struct address_space *mapping;
+ const struct movable_operations *mops;
/*
* Avoid burning cycles with pages that are yet under __free_pages(),
@@ -97,10 +97,10 @@ int isolate_movable_page(struct page *page, isolate_mode_t mode)
if (!PageMovable(page) || PageIsolated(page))
goto out_no_isolated;
- mapping = page_mapping(page);
- VM_BUG_ON_PAGE(!mapping, page);
+ mops = page_movable_ops(page);
+ VM_BUG_ON_PAGE(!mops, page);
- if (!mapping->a_ops->isolate_page(page, mode))
+ if (!mops->isolate_page(page, mode))
goto out_no_isolated;
/* Driver shouldn't use PG_isolated bit of page->flags */
@@ -120,10 +120,9 @@ out:
static void putback_movable_page(struct page *page)
{
- struct address_space *mapping;
+ const struct movable_operations *mops = page_movable_ops(page);
- mapping = page_mapping(page);
- mapping->a_ops->putback_page(page);
+ mops->putback_page(page);
ClearPageIsolated(page);
}
@@ -337,13 +336,18 @@ unlock:
}
#endif
-static int expected_page_refs(struct address_space *mapping, struct page *page)
+static int folio_expected_refs(struct address_space *mapping,
+ struct folio *folio)
{
- int expected_count = 1;
+ int refs = 1;
+ if (!mapping)
+ return refs;
- if (mapping)
- expected_count += compound_nr(page) + page_has_private(page);
- return expected_count;
+ refs += folio_nr_pages(folio);
+ if (folio_test_private(folio))
+ refs++;
+
+ return refs;
}
/*
@@ -360,7 +364,7 @@ int folio_migrate_mapping(struct address_space *mapping,
XA_STATE(xas, &mapping->i_pages, folio_index(folio));
struct zone *oldzone, *newzone;
int dirty;
- int expected_count = expected_page_refs(mapping, &folio->page) + extra_count;
+ int expected_count = folio_expected_refs(mapping, folio) + extra_count;
long nr = folio_nr_pages(folio);
if (!mapping) {
@@ -470,26 +474,26 @@ EXPORT_SYMBOL(folio_migrate_mapping);
* of folio_migrate_mapping().
*/
int migrate_huge_page_move_mapping(struct address_space *mapping,
- struct page *newpage, struct page *page)
+ struct folio *dst, struct folio *src)
{
- XA_STATE(xas, &mapping->i_pages, page_index(page));
+ XA_STATE(xas, &mapping->i_pages, folio_index(src));
int expected_count;
xas_lock_irq(&xas);
- expected_count = 2 + page_has_private(page);
- if (!page_ref_freeze(page, expected_count)) {
+ expected_count = 2 + folio_has_private(src);
+ if (!folio_ref_freeze(src, expected_count)) {
xas_unlock_irq(&xas);
return -EAGAIN;
}
- newpage->index = page->index;
- newpage->mapping = page->mapping;
+ dst->index = src->index;
+ dst->mapping = src->mapping;
- get_page(newpage);
+ folio_get(dst);
- xas_store(&xas, newpage);
+ xas_store(&xas, dst);
- page_ref_unfreeze(page, expected_count - 1);
+ folio_ref_unfreeze(src, expected_count - 1);
xas_unlock_irq(&xas);
@@ -589,34 +593,37 @@ EXPORT_SYMBOL(folio_migrate_copy);
* Migration functions
***********************************************************/
-/*
- * Common logic to directly migrate a single LRU page suitable for
- * pages that do not use PagePrivate/PagePrivate2.
+/**
+ * migrate_folio() - Simple folio migration.
+ * @mapping: The address_space containing the folio.
+ * @dst: The folio to migrate the data to.
+ * @src: The folio containing the current data.
+ * @mode: How to migrate the page.
+ *
+ * Common logic to directly migrate a single LRU folio suitable for
+ * folios that do not use PagePrivate/PagePrivate2.
*
- * Pages are locked upon entry and exit.
+ * Folios are locked upon entry and exit.
*/
-int migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page,
- enum migrate_mode mode)
+int migrate_folio(struct address_space *mapping, struct folio *dst,
+ struct folio *src, enum migrate_mode mode)
{
- struct folio *newfolio = page_folio(newpage);
- struct folio *folio = page_folio(page);
int rc;
- BUG_ON(folio_test_writeback(folio)); /* Writeback must be complete */
+ BUG_ON(folio_test_writeback(src)); /* Writeback must be complete */
- rc = folio_migrate_mapping(mapping, newfolio, folio, 0);
+ rc = folio_migrate_mapping(mapping, dst, src, 0);
if (rc != MIGRATEPAGE_SUCCESS)
return rc;
if (mode != MIGRATE_SYNC_NO_COPY)
- folio_migrate_copy(newfolio, folio);
+ folio_migrate_copy(dst, src);
else
- folio_migrate_flags(newfolio, folio);
+ folio_migrate_flags(dst, src);
return MIGRATEPAGE_SUCCESS;
}
-EXPORT_SYMBOL(migrate_page);
+EXPORT_SYMBOL(migrate_folio);
#ifdef CONFIG_BLOCK
/* Returns true if all buffers are successfully locked */
@@ -657,23 +664,23 @@ static bool buffer_migrate_lock_buffers(struct buffer_head *head,
return true;
}
-static int __buffer_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page, enum migrate_mode mode,
+static int __buffer_migrate_folio(struct address_space *mapping,
+ struct folio *dst, struct folio *src, enum migrate_mode mode,
bool check_refs)
{
struct buffer_head *bh, *head;
int rc;
int expected_count;
- if (!page_has_buffers(page))
- return migrate_page(mapping, newpage, page, mode);
+ head = folio_buffers(src);
+ if (!head)
+ return migrate_folio(mapping, dst, src, mode);
/* Check whether page does not have extra refs before we do more work */
- expected_count = expected_page_refs(mapping, page);
- if (page_count(page) != expected_count)
+ expected_count = folio_expected_refs(mapping, src);
+ if (folio_ref_count(src) != expected_count)
return -EAGAIN;
- head = page_buffers(page);
if (!buffer_migrate_lock_buffers(head, mode))
return -EAGAIN;
@@ -704,23 +711,22 @@ recheck_buffers:
}
}
- rc = migrate_page_move_mapping(mapping, newpage, page, 0);
+ rc = folio_migrate_mapping(mapping, dst, src, 0);
if (rc != MIGRATEPAGE_SUCCESS)
goto unlock_buffers;
- attach_page_private(newpage, detach_page_private(page));
+ folio_attach_private(dst, folio_detach_private(src));
bh = head;
do {
- set_bh_page(bh, newpage, bh_offset(bh));
+ set_bh_page(bh, &dst->page, bh_offset(bh));
bh = bh->b_this_page;
-
} while (bh != head);
if (mode != MIGRATE_SYNC_NO_COPY)
- migrate_page_copy(newpage, page);
+ folio_migrate_copy(dst, src);
else
- migrate_page_states(newpage, page);
+ folio_migrate_flags(dst, src);
rc = MIGRATEPAGE_SUCCESS;
unlock_buffers:
@@ -730,43 +736,79 @@ unlock_buffers:
do {
unlock_buffer(bh);
bh = bh->b_this_page;
-
} while (bh != head);
return rc;
}
-/*
- * Migration function for pages with buffers. This function can only be used
- * if the underlying filesystem guarantees that no other references to "page"
- * exist. For example attached buffer heads are accessed only under page lock.
+/**
+ * buffer_migrate_folio() - Migration function for folios with buffers.
+ * @mapping: The address space containing @src.
+ * @dst: The folio to migrate to.
+ * @src: The folio to migrate from.
+ * @mode: How to migrate the folio.
+ *
+ * This function can only be used if the underlying filesystem guarantees
+ * that no other references to @src exist. For example attached buffer
+ * heads are accessed only under the folio lock. If your filesystem cannot
+ * provide this guarantee, buffer_migrate_folio_norefs() may be more
+ * appropriate.
+ *
+ * Return: 0 on success or a negative errno on failure.
*/
-int buffer_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page, enum migrate_mode mode)
+int buffer_migrate_folio(struct address_space *mapping,
+ struct folio *dst, struct folio *src, enum migrate_mode mode)
{
- return __buffer_migrate_page(mapping, newpage, page, mode, false);
+ return __buffer_migrate_folio(mapping, dst, src, mode, false);
}
-EXPORT_SYMBOL(buffer_migrate_page);
+EXPORT_SYMBOL(buffer_migrate_folio);
-/*
- * Same as above except that this variant is more careful and checks that there
- * are also no buffer head references. This function is the right one for
- * mappings where buffer heads are directly looked up and referenced (such as
- * block device mappings).
+/**
+ * buffer_migrate_folio_norefs() - Migration function for folios with buffers.
+ * @mapping: The address space containing @src.
+ * @dst: The folio to migrate to.
+ * @src: The folio to migrate from.
+ * @mode: How to migrate the folio.
+ *
+ * Like buffer_migrate_folio() except that this variant is more careful
+ * and checks that there are also no buffer head references. This function
+ * is the right one for mappings where buffer heads are directly looked
+ * up and referenced (such as block device mappings).
+ *
+ * Return: 0 on success or a negative errno on failure.
*/
-int buffer_migrate_page_norefs(struct address_space *mapping,
- struct page *newpage, struct page *page, enum migrate_mode mode)
+int buffer_migrate_folio_norefs(struct address_space *mapping,
+ struct folio *dst, struct folio *src, enum migrate_mode mode)
{
- return __buffer_migrate_page(mapping, newpage, page, mode, true);
+ return __buffer_migrate_folio(mapping, dst, src, mode, true);
}
#endif
+int filemap_migrate_folio(struct address_space *mapping,
+ struct folio *dst, struct folio *src, enum migrate_mode mode)
+{
+ int ret;
+
+ ret = folio_migrate_mapping(mapping, dst, src, 0);
+ if (ret != MIGRATEPAGE_SUCCESS)
+ return ret;
+
+ if (folio_get_private(src))
+ folio_attach_private(dst, folio_detach_private(src));
+
+ if (mode != MIGRATE_SYNC_NO_COPY)
+ folio_migrate_copy(dst, src);
+ else
+ folio_migrate_flags(dst, src);
+ return MIGRATEPAGE_SUCCESS;
+}
+EXPORT_SYMBOL_GPL(filemap_migrate_folio);
+
/*
- * Writeback a page to clean the dirty state
+ * Writeback a folio to clean the dirty state
*/
-static int writeout(struct address_space *mapping, struct page *page)
+static int writeout(struct address_space *mapping, struct folio *folio)
{
- struct folio *folio = page_folio(page);
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
.nr_to_write = 1,
@@ -780,25 +822,25 @@ static int writeout(struct address_space *mapping, struct page *page)
/* No write method for the address space */
return -EINVAL;
- if (!clear_page_dirty_for_io(page))
+ if (!folio_clear_dirty_for_io(folio))
/* Someone else already triggered a write */
return -EAGAIN;
/*
- * A dirty page may imply that the underlying filesystem has
- * the page on some queue. So the page must be clean for
- * migration. Writeout may mean we loose the lock and the
- * page state is no longer what we checked for earlier.
+ * A dirty folio may imply that the underlying filesystem has
+ * the folio on some queue. So the folio must be clean for
+ * migration. Writeout may mean we lose the lock and the
+ * folio state is no longer what we checked for earlier.
* At this point we know that the migration attempt cannot
* be successful.
*/
remove_migration_ptes(folio, folio, false);
- rc = mapping->a_ops->writepage(page, &wbc);
+ rc = mapping->a_ops->writepage(&folio->page, &wbc);
if (rc != AOP_WRITEPAGE_ACTIVATE)
/* unlocked. Relock */
- lock_page(page);
+ folio_lock(folio);
return (rc < 0) ? -EIO : -EAGAIN;
}
@@ -806,11 +848,11 @@ static int writeout(struct address_space *mapping, struct page *page)
/*
* Default handling if a filesystem does not provide a migration function.
*/
-static int fallback_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page, enum migrate_mode mode)
+static int fallback_migrate_folio(struct address_space *mapping,
+ struct folio *dst, struct folio *src, enum migrate_mode mode)
{
- if (PageDirty(page)) {
- /* Only writeback pages in full synchronous migration */
+ if (folio_test_dirty(src)) {
+ /* Only writeback folios in full synchronous migration */
switch (mode) {
case MIGRATE_SYNC:
case MIGRATE_SYNC_NO_COPY:
@@ -818,18 +860,18 @@ static int fallback_migrate_page(struct address_space *mapping,
default:
return -EBUSY;
}
- return writeout(mapping, page);
+ return writeout(mapping, src);
}
/*
* Buffers may be managed in a filesystem specific way.
* We must have no buffers or drop them.
*/
- if (page_has_private(page) &&
- !try_to_release_page(page, GFP_KERNEL))
+ if (folio_test_private(src) &&
+ !filemap_release_folio(src, GFP_KERNEL))
return mode == MIGRATE_SYNC ? -EAGAIN : -EBUSY;
- return migrate_page(mapping, newpage, page, mode);
+ return migrate_folio(mapping, dst, src, mode);
}
/*
@@ -846,32 +888,32 @@ static int fallback_migrate_page(struct address_space *mapping,
static int move_to_new_folio(struct folio *dst, struct folio *src,
enum migrate_mode mode)
{
- struct address_space *mapping;
int rc = -EAGAIN;
bool is_lru = !__PageMovable(&src->page);
VM_BUG_ON_FOLIO(!folio_test_locked(src), src);
VM_BUG_ON_FOLIO(!folio_test_locked(dst), dst);
- mapping = folio_mapping(src);
-
if (likely(is_lru)) {
+ struct address_space *mapping = folio_mapping(src);
+
if (!mapping)
- rc = migrate_page(mapping, &dst->page, &src->page, mode);
- else if (mapping->a_ops->migratepage)
+ rc = migrate_folio(mapping, dst, src, mode);
+ else if (mapping->a_ops->migrate_folio)
/*
- * Most pages have a mapping and most filesystems
- * provide a migratepage callback. Anonymous pages
+ * Most folios have a mapping and most filesystems
+ * provide a migrate_folio callback. Anonymous folios
* are part of swap space which also has its own
- * migratepage callback. This is the most common path
+ * migrate_folio callback. This is the most common path
* for page migration.
*/
- rc = mapping->a_ops->migratepage(mapping, &dst->page,
- &src->page, mode);
+ rc = mapping->a_ops->migrate_folio(mapping, dst, src,
+ mode);
else
- rc = fallback_migrate_page(mapping, &dst->page,
- &src->page, mode);
+ rc = fallback_migrate_folio(mapping, dst, src, mode);
} else {
+ const struct movable_operations *mops;
+
/*
* In case of non-lru page, it could be released after
* isolation step. In that case, we shouldn't try migration.
@@ -883,8 +925,8 @@ static int move_to_new_folio(struct folio *dst, struct folio *src,
goto out;
}
- rc = mapping->a_ops->migratepage(mapping, &dst->page,
- &src->page, mode);
+ mops = page_movable_ops(&src->page);
+ rc = mops->migrate_page(&dst->page, &src->page, mode);
WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS &&
!folio_test_isolated(src));
}
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 5052093d0262..5dd97c39ca6a 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -718,7 +718,8 @@ void migrate_vma_pages(struct migrate_vma *migrate)
continue;
}
- r = migrate_page(mapping, newpage, page, MIGRATE_SYNC_NO_COPY);
+ r = migrate_folio(mapping, page_folio(newpage),
+ page_folio(page), MIGRATE_SYNC_NO_COPY);
if (r != MIGRATEPAGE_SUCCESS)
migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
}
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 71fb78f59d72..e3e9590c6fb3 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -144,14 +144,8 @@ static const struct file_operations secretmem_fops = {
.mmap = secretmem_mmap,
};
-static bool secretmem_isolate_page(struct page *page, isolate_mode_t mode)
-{
- return false;
-}
-
-static int secretmem_migratepage(struct address_space *mapping,
- struct page *newpage, struct page *page,
- enum migrate_mode mode)
+static int secretmem_migrate_folio(struct address_space *mapping,
+ struct folio *dst, struct folio *src, enum migrate_mode mode)
{
return -EBUSY;
}
@@ -165,8 +159,7 @@ static void secretmem_free_folio(struct folio *folio)
const struct address_space_operations secretmem_aops = {
.dirty_folio = noop_dirty_folio,
.free_folio = secretmem_free_folio,
- .migratepage = secretmem_migratepage,
- .isolate_page = secretmem_isolate_page,
+ .migrate_folio = secretmem_migrate_folio,
};
static int secretmem_setattr(struct user_namespace *mnt_userns,
diff --git a/mm/shmem.c b/mm/shmem.c
index b7f2d4a56867..e5e43b990fdc 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -392,7 +392,7 @@ void shmem_uncharge(struct inode *inode, long pages)
struct shmem_inode_info *info = SHMEM_I(inode);
unsigned long flags;
- /* nrpages adjustment done by __delete_from_page_cache() or caller */
+ /* nrpages adjustment done by __filemap_remove_folio() or caller */
spin_lock_irqsave(&info->lock, flags);
info->alloced -= pages;
@@ -693,7 +693,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
/*
- * Like add_to_page_cache_locked, but error if expected item has gone.
+ * Like filemap_add_folio, but error if expected item has gone.
*/
static int shmem_add_to_page_cache(struct folio *folio,
struct address_space *mapping,
@@ -867,18 +867,17 @@ unsigned long shmem_swap_usage(struct vm_area_struct *vma)
*/
void shmem_unlock_mapping(struct address_space *mapping)
{
- struct pagevec pvec;
+ struct folio_batch fbatch;
pgoff_t index = 0;
- pagevec_init(&pvec);
+ folio_batch_init(&fbatch);
/*
* Minor point, but we might as well stop if someone else SHM_LOCKs it.
*/
- while (!mapping_unevictable(mapping)) {
- if (!pagevec_lookup(&pvec, mapping, &index))
- break;
- check_move_unevictable_pages(&pvec);
- pagevec_release(&pvec);
+ while (!mapping_unevictable(mapping) &&
+ filemap_get_folios(mapping, &index, ~0UL, &fbatch)) {
+ check_move_unevictable_folios(&fbatch);
+ folio_batch_release(&fbatch);
cond_resched();
}
}
@@ -3799,7 +3798,7 @@ const struct address_space_operations shmem_aops = {
.write_end = shmem_write_end,
#endif
#ifdef CONFIG_MIGRATION
- .migratepage = migrate_page,
+ .migrate_folio = migrate_folio,
#endif
.error_remove_page = shmem_error_remove_page,
};
diff --git a/mm/swap.c b/mm/swap.c
index 034bb24879a3..275a4ea1bc66 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -1086,35 +1086,6 @@ void folio_batch_remove_exceptionals(struct folio_batch *fbatch)
fbatch->nr = j;
}
-/**
- * pagevec_lookup_range - gang pagecache lookup
- * @pvec: Where the resulting pages are placed
- * @mapping: The address_space to search
- * @start: The starting page index
- * @end: The final page index
- *
- * pagevec_lookup_range() will search for & return a group of up to PAGEVEC_SIZE
- * pages in the mapping starting from index @start and upto index @end
- * (inclusive). The pages are placed in @pvec. pagevec_lookup() takes a
- * reference against the pages in @pvec.
- *
- * The search returns a group of mapping-contiguous pages with ascending
- * indexes. There may be holes in the indices due to not-present pages. We
- * also update @start to index the next page for the traversal.
- *
- * pagevec_lookup_range() returns the number of pages which were found. If this
- * number is smaller than PAGEVEC_SIZE, the end of specified range has been
- * reached.
- */
-unsigned pagevec_lookup_range(struct pagevec *pvec,
- struct address_space *mapping, pgoff_t *start, pgoff_t end)
-{
- pvec->nr = find_get_pages_range(mapping, start, end, PAGEVEC_SIZE,
- pvec->pages);
- return pagevec_count(pvec);
-}
-EXPORT_SYMBOL(pagevec_lookup_range);
-
unsigned pagevec_lookup_range_tag(struct pagevec *pvec,
struct address_space *mapping, pgoff_t *index, pgoff_t end,
xa_mark_t tag)
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 778d57d2d92d..0a2021fc55ad 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -33,7 +33,7 @@ static const struct address_space_operations swap_aops = {
.writepage = swap_writepage,
.dirty_folio = noop_dirty_folio,
#ifdef CONFIG_MIGRATION
- .migratepage = migrate_page,
+ .migrate_folio = migrate_folio,
#endif
};
@@ -95,7 +95,7 @@ void *get_shadow_from_swap_cache(swp_entry_t entry)
}
/*
- * add_to_swap_cache resembles add_to_page_cache_locked on swapper_space,
+ * add_to_swap_cache resembles filemap_add_folio on swapper_space,
* but sets SwapCache flag and private instead of mapping and index.
*/
int add_to_swap_cache(struct page *page, swp_entry_t entry,
diff --git a/mm/truncate.c b/mm/truncate.c
index ab50d0d59a2a..0b0708bf935f 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -443,7 +443,7 @@ EXPORT_SYMBOL(truncate_inode_pages_range);
* mapping->invalidate_lock.
*
* Note: When this function returns, there can be a page in the process of
- * deletion (inside __delete_from_page_cache()) in the specified range. Thus
+ * deletion (inside __filemap_remove_folio()) in the specified range. Thus
* mapping->nrpages can be non-zero when this function returns even after
* truncation of the whole mapping.
*/
diff --git a/mm/util.c b/mm/util.c
index 0837570c9225..53af0e79d3e4 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -804,10 +804,10 @@ struct address_space *folio_mapping(struct folio *folio)
return swap_address_space(folio_swap_entry(folio));
mapping = folio->mapping;
- if ((unsigned long)mapping & PAGE_MAPPING_ANON)
+ if ((unsigned long)mapping & PAGE_MAPPING_FLAGS)
return NULL;
- return (void *)((unsigned long)mapping & ~PAGE_MAPPING_FLAGS);
+ return mapping;
}
EXPORT_SYMBOL(folio_mapping);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f7d9a683e3a7..04f8671caad9 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4790,45 +4790,57 @@ int node_reclaim(struct pglist_data *pgdat, gfp_t gfp_mask, unsigned int order)
}
#endif
+void check_move_unevictable_pages(struct pagevec *pvec)
+{
+ struct folio_batch fbatch;
+ unsigned i;
+
+ folio_batch_init(&fbatch);
+ for (i = 0; i < pvec->nr; i++) {
+ struct page *page = pvec->pages[i];
+
+ if (PageTransTail(page))
+ continue;
+ folio_batch_add(&fbatch, page_folio(page));
+ }
+ check_move_unevictable_folios(&fbatch);
+}
+EXPORT_SYMBOL_GPL(check_move_unevictable_pages);
+
/**
- * check_move_unevictable_pages - check pages for evictability and move to
- * appropriate zone lru list
- * @pvec: pagevec with lru pages to check
+ * check_move_unevictable_folios - Move evictable folios to appropriate zone
+ * lru list
+ * @fbatch: Batch of lru folios to check.
*
- * Checks pages for evictability, if an evictable page is in the unevictable
+ * Checks folios for evictability, if an evictable folio is in the unevictable
* lru list, moves it to the appropriate evictable lru list. This function
- * should be only used for lru pages.
+ * should be only used for lru folios.
*/
-void check_move_unevictable_pages(struct pagevec *pvec)
+void check_move_unevictable_folios(struct folio_batch *fbatch)
{
struct lruvec *lruvec = NULL;
int pgscanned = 0;
int pgrescued = 0;
int i;
- for (i = 0; i < pvec->nr; i++) {
- struct page *page = pvec->pages[i];
- struct folio *folio = page_folio(page);
- int nr_pages;
-
- if (PageTransTail(page))
- continue;
+ for (i = 0; i < fbatch->nr; i++) {
+ struct folio *folio = fbatch->folios[i];
+ int nr_pages = folio_nr_pages(folio);
- nr_pages = thp_nr_pages(page);
pgscanned += nr_pages;
- /* block memcg migration during page moving between lru */
- if (!TestClearPageLRU(page))
+ /* block memcg migration while the folio moves between lrus */
+ if (!folio_test_clear_lru(folio))
continue;
lruvec = folio_lruvec_relock_irq(folio, lruvec);
- if (page_evictable(page) && PageUnevictable(page)) {
- del_page_from_lru_list(page, lruvec);
- ClearPageUnevictable(page);
- add_page_to_lru_list(page, lruvec);
+ if (folio_evictable(folio) && folio_test_unevictable(folio)) {
+ lruvec_del_folio(lruvec, folio);
+ folio_clear_unevictable(folio);
+ lruvec_add_folio(lruvec, folio);
pgrescued += nr_pages;
}
- SetPageLRU(page);
+ folio_set_lru(folio);
}
if (lruvec) {
@@ -4839,4 +4851,4 @@ void check_move_unevictable_pages(struct pagevec *pvec)
count_vm_events(UNEVICTABLE_PGSCANNED, pgscanned);
}
}
-EXPORT_SYMBOL_GPL(check_move_unevictable_pages);
+EXPORT_SYMBOL_GPL(check_move_unevictable_folios);
diff --git a/mm/z3fold.c b/mm/z3fold.c
index f41f8b0d9e9a..cf71da10d04e 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -34,15 +34,11 @@
#include <linux/node.h>
#include <linux/compaction.h>
#include <linux/percpu.h>
-#include <linux/mount.h>
-#include <linux/pseudo_fs.h>
-#include <linux/fs.h>
#include <linux/preempt.h>
#include <linux/workqueue.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/zpool.h>
-#include <linux/magic.h>
#include <linux/kmemleak.h>
/*
@@ -149,7 +145,6 @@ struct z3fold_header {
* @compact_wq: workqueue for page layout background optimization
* @release_wq: workqueue for safe page release
* @work: work_struct for safe page release
- * @inode: inode for z3fold pseudo filesystem
*
* This structure is allocated at pool creation time and maintains metadata
* pertaining to a particular z3fold pool.
@@ -169,7 +164,6 @@ struct z3fold_pool {
struct workqueue_struct *compact_wq;
struct workqueue_struct *release_wq;
struct work_struct work;
- struct inode *inode;
};
/*
@@ -334,54 +328,6 @@ static inline void free_handle(unsigned long handle, struct z3fold_header *zhdr)
}
}
-static int z3fold_init_fs_context(struct fs_context *fc)
-{
- return init_pseudo(fc, Z3FOLD_MAGIC) ? 0 : -ENOMEM;
-}
-
-static struct file_system_type z3fold_fs = {
- .name = "z3fold",
- .init_fs_context = z3fold_init_fs_context,
- .kill_sb = kill_anon_super,
-};
-
-static struct vfsmount *z3fold_mnt;
-static int __init z3fold_mount(void)
-{
- int ret = 0;
-
- z3fold_mnt = kern_mount(&z3fold_fs);
- if (IS_ERR(z3fold_mnt))
- ret = PTR_ERR(z3fold_mnt);
-
- return ret;
-}
-
-static void z3fold_unmount(void)
-{
- kern_unmount(z3fold_mnt);
-}
-
-static const struct address_space_operations z3fold_aops;
-static int z3fold_register_migration(struct z3fold_pool *pool)
-{
- pool->inode = alloc_anon_inode(z3fold_mnt->mnt_sb);
- if (IS_ERR(pool->inode)) {
- pool->inode = NULL;
- return 1;
- }
-
- pool->inode->i_mapping->private_data = pool;
- pool->inode->i_mapping->a_ops = &z3fold_aops;
- return 0;
-}
-
-static void z3fold_unregister_migration(struct z3fold_pool *pool)
-{
- if (pool->inode)
- iput(pool->inode);
-}
-
/* Initializes the z3fold header of a newly allocated z3fold page */
static struct z3fold_header *init_z3fold_page(struct page *page, bool headless,
struct z3fold_pool *pool, gfp_t gfp)
@@ -1002,14 +948,10 @@ static struct z3fold_pool *z3fold_create_pool(const char *name, gfp_t gfp,
pool->release_wq = create_singlethread_workqueue(pool->name);
if (!pool->release_wq)
goto out_wq;
- if (z3fold_register_migration(pool))
- goto out_rwq;
INIT_WORK(&pool->work, free_pages_work);
pool->ops = ops;
return pool;
-out_rwq:
- destroy_workqueue(pool->release_wq);
out_wq:
destroy_workqueue(pool->compact_wq);
out_unbuddied:
@@ -1043,11 +985,12 @@ static void z3fold_destroy_pool(struct z3fold_pool *pool)
destroy_workqueue(pool->compact_wq);
destroy_workqueue(pool->release_wq);
- z3fold_unregister_migration(pool);
free_percpu(pool->unbuddied);
kfree(pool);
}
+static const struct movable_operations z3fold_mops;
+
/**
* z3fold_alloc() - allocates a region of a given size
* @pool: z3fold pool from which to allocate
@@ -1117,11 +1060,11 @@ retry:
}
if (can_sleep) {
lock_page(page);
- __SetPageMovable(page, pool->inode->i_mapping);
+ __SetPageMovable(page, &z3fold_mops);
unlock_page(page);
} else {
WARN_ON(!trylock_page(page));
- __SetPageMovable(page, pool->inode->i_mapping);
+ __SetPageMovable(page, &z3fold_mops);
unlock_page(page);
}
z3fold_page_lock(zhdr);
@@ -1554,12 +1497,11 @@ out:
return false;
}
-static int z3fold_page_migrate(struct address_space *mapping, struct page *newpage,
- struct page *page, enum migrate_mode mode)
+static int z3fold_page_migrate(struct page *newpage, struct page *page,
+ enum migrate_mode mode)
{
struct z3fold_header *zhdr, *new_zhdr;
struct z3fold_pool *pool;
- struct address_space *new_mapping;
VM_BUG_ON_PAGE(!PageMovable(page), page);
VM_BUG_ON_PAGE(!PageIsolated(page), page);
@@ -1592,7 +1534,6 @@ static int z3fold_page_migrate(struct address_space *mapping, struct page *newpa
* so we only have to reinitialize it.
*/
INIT_LIST_HEAD(&new_zhdr->buddy);
- new_mapping = page_mapping(page);
__ClearPageMovable(page);
get_page(newpage);
@@ -1608,7 +1549,7 @@ static int z3fold_page_migrate(struct address_space *mapping, struct page *newpa
spin_lock(&pool->lock);
list_add(&newpage->lru, &pool->lru);
spin_unlock(&pool->lock);
- __SetPageMovable(newpage, new_mapping);
+ __SetPageMovable(newpage, &z3fold_mops);
z3fold_page_unlock(new_zhdr);
queue_work_on(new_zhdr->cpu, pool->compact_wq, &new_zhdr->work);
@@ -1642,9 +1583,9 @@ static void z3fold_page_putback(struct page *page)
z3fold_page_unlock(zhdr);
}
-static const struct address_space_operations z3fold_aops = {
+static const struct movable_operations z3fold_mops = {
.isolate_page = z3fold_page_isolate,
- .migratepage = z3fold_page_migrate,
+ .migrate_page = z3fold_page_migrate,
.putback_page = z3fold_page_putback,
};
@@ -1746,17 +1687,11 @@ MODULE_ALIAS("zpool-z3fold");
static int __init init_z3fold(void)
{
- int ret;
-
/*
* Make sure the z3fold header is not larger than the page size and
* there has remaining spaces for its buddy.
*/
BUILD_BUG_ON(ZHDR_SIZE_ALIGNED > PAGE_SIZE - CHUNK_SIZE);
- ret = z3fold_mount();
- if (ret)
- return ret;
-
zpool_register_driver(&z3fold_zpool_driver);
return 0;
@@ -1764,7 +1699,6 @@ static int __init init_z3fold(void)
static void __exit exit_z3fold(void)
{
- z3fold_unmount();
zpool_unregister_driver(&z3fold_zpool_driver);
}
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index 5d5fc04385b8..71d6edcbea48 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -41,7 +41,6 @@
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
-#include <linux/magic.h>
#include <linux/bitops.h>
#include <linux/errno.h>
#include <linux/highmem.h>
@@ -59,8 +58,6 @@
#include <linux/debugfs.h>
#include <linux/zsmalloc.h>
#include <linux/zpool.h>
-#include <linux/mount.h>
-#include <linux/pseudo_fs.h>
#include <linux/migrate.h>
#include <linux/wait.h>
#include <linux/pagemap.h>
@@ -177,10 +174,6 @@ struct zs_size_stat {
static struct dentry *zs_stat_root;
#endif
-#ifdef CONFIG_COMPACTION
-static struct vfsmount *zsmalloc_mnt;
-#endif
-
/*
* We assign a page to ZS_ALMOST_EMPTY fullness group when:
* n <= N / f, where
@@ -252,7 +245,6 @@ struct zs_pool {
struct dentry *stat_dentry;
#endif
#ifdef CONFIG_COMPACTION
- struct inode *inode;
struct work_struct free_work;
#endif
/* protect page/zspage migration */
@@ -271,6 +263,7 @@ struct zspage {
unsigned int freeobj;
struct page *first_page;
struct list_head list; /* fullness list */
+ struct zs_pool *pool;
#ifdef CONFIG_COMPACTION
rwlock_t lock;
#endif
@@ -295,8 +288,6 @@ static bool ZsHugePage(struct zspage *zspage)
}
#ifdef CONFIG_COMPACTION
-static int zs_register_migration(struct zs_pool *pool);
-static void zs_unregister_migration(struct zs_pool *pool);
static void migrate_lock_init(struct zspage *zspage);
static void migrate_read_lock(struct zspage *zspage);
static void migrate_read_unlock(struct zspage *zspage);
@@ -307,10 +298,6 @@ static void kick_deferred_free(struct zs_pool *pool);
static void init_deferred_free(struct zs_pool *pool);
static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage);
#else
-static int zsmalloc_mount(void) { return 0; }
-static void zsmalloc_unmount(void) {}
-static int zs_register_migration(struct zs_pool *pool) { return 0; }
-static void zs_unregister_migration(struct zs_pool *pool) {}
static void migrate_lock_init(struct zspage *zspage) {}
static void migrate_read_lock(struct zspage *zspage) {}
static void migrate_read_unlock(struct zspage *zspage) {}
@@ -1083,6 +1070,7 @@ static struct zspage *alloc_zspage(struct zs_pool *pool,
create_page_chain(class, zspage, pages);
init_zspage(class, zspage);
+ zspage->pool = pool;
return zspage;
}
@@ -1754,33 +1742,6 @@ static void lock_zspage(struct zspage *zspage)
migrate_read_unlock(zspage);
}
-static int zs_init_fs_context(struct fs_context *fc)
-{
- return init_pseudo(fc, ZSMALLOC_MAGIC) ? 0 : -ENOMEM;
-}
-
-static struct file_system_type zsmalloc_fs = {
- .name = "zsmalloc",
- .init_fs_context = zs_init_fs_context,
- .kill_sb = kill_anon_super,
-};
-
-static int zsmalloc_mount(void)
-{
- int ret = 0;
-
- zsmalloc_mnt = kern_mount(&zsmalloc_fs);
- if (IS_ERR(zsmalloc_mnt))
- ret = PTR_ERR(zsmalloc_mnt);
-
- return ret;
-}
-
-static void zsmalloc_unmount(void)
-{
- kern_unmount(zsmalloc_mnt);
-}
-
static void migrate_lock_init(struct zspage *zspage)
{
rwlock_init(&zspage->lock);
@@ -1823,6 +1784,8 @@ static void dec_zspage_isolation(struct zspage *zspage)
zspage->isolated--;
}
+static const struct movable_operations zsmalloc_mops;
+
static void replace_sub_page(struct size_class *class, struct zspage *zspage,
struct page *newpage, struct page *oldpage)
{
@@ -1843,7 +1806,7 @@ static void replace_sub_page(struct size_class *class, struct zspage *zspage,
set_first_obj_offset(newpage, get_first_obj_offset(oldpage));
if (unlikely(ZsHugePage(zspage)))
newpage->index = oldpage->index;
- __SetPageMovable(newpage, page_mapping(oldpage));
+ __SetPageMovable(newpage, &zsmalloc_mops);
}
static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
@@ -1865,8 +1828,8 @@ static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
return true;
}
-static int zs_page_migrate(struct address_space *mapping, struct page *newpage,
- struct page *page, enum migrate_mode mode)
+static int zs_page_migrate(struct page *newpage, struct page *page,
+ enum migrate_mode mode)
{
struct zs_pool *pool;
struct size_class *class;
@@ -1889,14 +1852,15 @@ static int zs_page_migrate(struct address_space *mapping, struct page *newpage,
VM_BUG_ON_PAGE(!PageMovable(page), page);
VM_BUG_ON_PAGE(!PageIsolated(page), page);
- pool = mapping->private_data;
+ /* The page is locked, so this pointer must remain valid */
+ zspage = get_zspage(page);
+ pool = zspage->pool;
/*
* The pool migrate_lock protects the race between zpage migration
* and zs_free.
*/
write_lock(&pool->migrate_lock);
- zspage = get_zspage(page);
class = zspage_class(pool, zspage);
/*
@@ -1964,31 +1928,12 @@ static void zs_page_putback(struct page *page)
migrate_write_unlock(zspage);
}
-static const struct address_space_operations zsmalloc_aops = {
+static const struct movable_operations zsmalloc_mops = {
.isolate_page = zs_page_isolate,
- .migratepage = zs_page_migrate,
+ .migrate_page = zs_page_migrate,
.putback_page = zs_page_putback,
};
-static int zs_register_migration(struct zs_pool *pool)
-{
- pool->inode = alloc_anon_inode(zsmalloc_mnt->mnt_sb);
- if (IS_ERR(pool->inode)) {
- pool->inode = NULL;
- return 1;
- }
-
- pool->inode->i_mapping->private_data = pool;
- pool->inode->i_mapping->a_ops = &zsmalloc_aops;
- return 0;
-}
-
-static void zs_unregister_migration(struct zs_pool *pool)
-{
- flush_work(&pool->free_work);
- iput(pool->inode);
-}
-
/*
* Caller should hold page_lock of all pages in the zspage
* In here, we cannot use zspage meta data.
@@ -2032,6 +1977,11 @@ static void kick_deferred_free(struct zs_pool *pool)
schedule_work(&pool->free_work);
}
+static void zs_flush_migration(struct zs_pool *pool)
+{
+ flush_work(&pool->free_work);
+}
+
static void init_deferred_free(struct zs_pool *pool)
{
INIT_WORK(&pool->free_work, async_free_zspage);
@@ -2043,10 +1993,12 @@ static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage)
do {
WARN_ON(!trylock_page(page));
- __SetPageMovable(page, pool->inode->i_mapping);
+ __SetPageMovable(page, &zsmalloc_mops);
unlock_page(page);
} while ((page = get_next_page(page)) != NULL);
}
+#else
+static inline void zs_flush_migration(struct zs_pool *pool) { }
#endif
/*
@@ -2324,9 +2276,6 @@ struct zs_pool *zs_create_pool(const char *name)
/* debug only, don't abort if it fails */
zs_pool_stat_create(pool, name);
- if (zs_register_migration(pool))
- goto err;
-
/*
* Not critical since shrinker is only used to trigger internal
* defragmentation of the pool which is pretty optional thing. If
@@ -2348,7 +2297,7 @@ void zs_destroy_pool(struct zs_pool *pool)
int i;
zs_unregister_shrinker(pool);
- zs_unregister_migration(pool);
+ zs_flush_migration(pool);
zs_pool_stat_destroy(pool);
for (i = 0; i < ZS_SIZE_CLASSES; i++) {
@@ -2380,14 +2329,10 @@ static int __init zs_init(void)
{
int ret;
- ret = zsmalloc_mount();
- if (ret)
- goto out;
-
ret = cpuhp_setup_state(CPUHP_MM_ZS_PREPARE, "mm/zsmalloc:prepare",
zs_cpu_prepare, zs_cpu_dead);
if (ret)
- goto hp_setup_fail;
+ goto out;
#ifdef CONFIG_ZPOOL
zpool_register_driver(&zs_zpool_driver);
@@ -2397,8 +2342,6 @@ static int __init zs_init(void)
return 0;
-hp_setup_fail:
- zsmalloc_unmount();
out:
return ret;
}
@@ -2408,7 +2351,6 @@ static void __exit zs_exit(void)
#ifdef CONFIG_ZPOOL
zpool_unregister_driver(&zs_zpool_driver);
#endif
- zsmalloc_unmount();
cpuhp_remove_state(CPUHP_MM_ZS_PREPARE);
zs_stat_exit();