I'm a little disappointed to have received no feedback on these patches
from those who were involved with creating the ugly situation in the
first place.
There are other ext4/f2fs patches in this patch series for which it
would also be nice to get reviewed-by tags.
----- Forwarded message from Matthew Wilcox <willy@xxxxxxxxxxxxx> -----
Date: Fri, 20 Mar 2020 07:22:19 -0700
From: Matthew Wilcox <willy@xxxxxxxxxxxxx>
To: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>,
linux-fsdevel@xxxxxxxxxxxxxxx, linux-mm@xxxxxxxxx,
linux-kernel@xxxxxxxxxxxxxxx, linux-btrfs@xxxxxxxxxxxxxxx,
linux-erofs@xxxxxxxxxxxxxxxx, linux-ext4@xxxxxxxxxxxxxxx,
linux-f2fs-devel@xxxxxxxxxxxxxxxxxxxxx, cluster-devel@xxxxxxxxxx,
ocfs2-devel@xxxxxxxxxxxxxx, linux-xfs@xxxxxxxxxxxxxxx, Christoph
Hellwig <hch@xxxxxx>, William Kucharski <william.kucharski@xxxxxxxxxx>
Subject: [PATCH v9 13/25] mm: Add page_cache_readahead_unbounded
X-Mailer: git-send-email 2.21.1
From: "Matthew Wilcox (Oracle)" <willy@xxxxxxxxxxxxx>
ext4 and f2fs have duplicated the guts of the readahead code so
they can read past i_size. Instead, separate out the guts of the
readahead code so they can call it directly.
Signed-off-by: Matthew Wilcox (Oracle) <willy@xxxxxxxxxxxxx>
Reviewed-by: Christoph Hellwig <hch@xxxxxx>
Reviewed-by: William Kucharski <william.kucharski@xxxxxxxxxx>
---
fs/ext4/verity.c | 35 ++-----------------
fs/f2fs/data.c | 2 +-
fs/f2fs/f2fs.h | 3 --
fs/f2fs/verity.c | 35 ++-----------------
include/linux/pagemap.h | 3 ++
mm/readahead.c | 74 ++++++++++++++++++++++++++++-------------
6 files changed, 58 insertions(+), 94 deletions(-)
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index dc5ec724d889..dec1244dd062 100644
--- a/fs/ext4/verity.c
+++ b/fs/ext4/verity.c
@@ -342,37 +342,6 @@ static int ext4_get_verity_descriptor(struct inode *inode, void *buf,
return desc_size;
}
-/*
- * Prefetch some pages from the file's Merkle tree.
- *
- * This is basically a stripped-down version of __do_page_cache_readahead()
- * which works on pages past i_size.
- */
-static void ext4_merkle_tree_readahead(struct address_space *mapping,
- pgoff_t start_index, unsigned long count)
-{
- LIST_HEAD(pages);
- unsigned int nr_pages = 0;
- struct page *page;
- pgoff_t index;
- struct blk_plug plug;
-
- for (index = start_index; index < start_index + count; index++) {
- page = xa_load(&mapping->i_pages, index);
- if (!page || xa_is_value(page)) {
- page = __page_cache_alloc(readahead_gfp_mask(mapping));
- if (!page)
- break;
- page->index = index;
- list_add(&page->lru, &pages);
- nr_pages++;
- }
- }
- blk_start_plug(&plug);
- ext4_mpage_readpages(mapping, &pages, NULL, nr_pages, true);
- blk_finish_plug(&plug);
-}
-
static struct page *ext4_read_merkle_tree_page(struct inode *inode,
pgoff_t index,
unsigned long num_ra_pages)
@@ -386,8 +355,8 @@ static struct page *ext4_read_merkle_tree_page(struct inode *inode,
if (page)
put_page(page);
else if (num_ra_pages > 1)
- ext4_merkle_tree_readahead(inode->i_mapping, index,
- num_ra_pages);
+ page_cache_readahead_unbounded(inode->i_mapping, NULL,
+ index, num_ra_pages, 0);
page = read_mapping_page(inode->i_mapping, index, NULL);
}
return page;
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index b27b72107911..8e9aa2254490 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -2159,7 +2159,7 @@ int f2fs_read_multi_pages(struct compress_ctx *cc, struct bio **bio_ret,
* use ->readpage() or do the necessary surgery to decouple ->readpages()
* from read-ahead.
*/
-int f2fs_mpage_readpages(struct address_space *mapping,
+static int f2fs_mpage_readpages(struct address_space *mapping,
struct list_head *pages, struct page *page,
unsigned nr_pages, bool is_readahead)
{
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 5355be6b6755..4a414e06a8af 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3344,9 +3344,6 @@ int f2fs_reserve_new_block(struct dnode_of_data *dn);
int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
-int f2fs_mpage_readpages(struct address_space *mapping,
- struct list_head *pages, struct page *page,
- unsigned nr_pages, bool is_readahead);
struct page *f2fs_get_read_data_page(struct inode *inode, pgoff_t index,
int op_flags, bool for_write);
struct page *f2fs_find_data_page(struct inode *inode, pgoff_t index);
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index d7d430a6f130..865c9fb774fb 100644
--- a/fs/f2fs/verity.c
+++ b/fs/f2fs/verity.c
@@ -222,37 +222,6 @@ static int f2fs_get_verity_descriptor(struct inode *inode, void *buf,
return size;
}
-/*
- * Prefetch some pages from the file's Merkle tree.
- *
- * This is basically a stripped-down version of __do_page_cache_readahead()
- * which works on pages past i_size.
- */
-static void f2fs_merkle_tree_readahead(struct address_space *mapping,
- pgoff_t start_index, unsigned long count)
-{
- LIST_HEAD(pages);
- unsigned int nr_pages = 0;
- struct page *page;
- pgoff_t index;
- struct blk_plug plug;
-
- for (index = start_index; index < start_index + count; index++) {
- page = xa_load(&mapping->i_pages, index);
- if (!page || xa_is_value(page)) {
- page = __page_cache_alloc(readahead_gfp_mask(mapping));
- if (!page)
- break;
- page->index = index;
- list_add(&page->lru, &pages);
- nr_pages++;
- }
- }
- blk_start_plug(&plug);
- f2fs_mpage_readpages(mapping, &pages, NULL, nr_pages, true);
- blk_finish_plug(&plug);
-}
-
static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
pgoff_t index,
unsigned long num_ra_pages)
@@ -266,8 +235,8 @@ static struct page *f2fs_read_merkle_tree_page(struct inode *inode,
if (page)
put_page(page);
else if (num_ra_pages > 1)
- f2fs_merkle_tree_readahead(inode->i_mapping, index,
- num_ra_pages);
+ page_cache_readahead_unbounded(inode->i_mapping, NULL,
+ index, num_ra_pages, 0);
page = read_mapping_page(inode->i_mapping, index, NULL);
}
return page;
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 232892d37071..0c25625ed27d 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -621,6 +621,9 @@ void page_cache_sync_readahead(struct address_space *, struct file_ra_state *,
void page_cache_async_readahead(struct address_space *, struct file_ra_state *,
struct file *, struct page *, pgoff_t index,
unsigned long req_count);
+void page_cache_readahead_unbounded(struct address_space *, struct file *,
+ pgoff_t index, unsigned long nr_to_read,
+ unsigned long lookahead_count);
/*
* Like add_to_page_cache_locked, but used to add newly allocated pages:
diff --git a/mm/readahead.c b/mm/readahead.c
index a37b68f66233..8ee9036fd681 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -156,40 +156,34 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages,
rac->_index++;
}
-/*
- * __do_page_cache_readahead() actually reads a chunk of disk. It allocates
- * the pages first, then submits them for I/O. This avoids the very bad
- * behaviour which would occur if page allocations are causing VM writeback.
- * We really don't want to intermingle reads and writes like that.
+/**
+ * page_cache_readahead_unbounded - Start unchecked readahead.
+ * @mapping: File address space.
+ * @file: This instance of the open file; used for authentication.
+ * @index: First page index to read.
+ * @nr_to_read: The number of pages to read.
+ * @lookahead_size: Where to start the next readahead.
+ *
+ * This function is for filesystems to call when they want to start
+ * readahead beyond a file's stated i_size. This is almost certainly
+ * not the function you want to call. Use page_cache_async_readahead()
+ * or page_cache_sync_readahead() instead.
+ *
+ * Context: File is referenced by caller. Mutexes may be held by caller.
+ * May sleep, but will not reenter filesystem to reclaim memory.
*/
-void __do_page_cache_readahead(struct address_space *mapping,
- struct file *filp, pgoff_t index, unsigned long nr_to_read,
+void page_cache_readahead_unbounded(struct address_space *mapping,
+ struct file *file, pgoff_t index, unsigned long nr_to_read,
unsigned long lookahead_size)
{
- struct inode *inode = mapping->host;
LIST_HEAD(page_pool);
- loff_t isize = i_size_read(inode);
gfp_t gfp_mask = readahead_gfp_mask(mapping);
struct readahead_control rac = {
.mapping = mapping,
- .file = filp,
+ .file = file,
._index = index,
};
unsigned long i;
- pgoff_t end_index; /* The last page we want to read */
-
- if (isize == 0)
- return;
-
- end_index = (isize - 1) >> PAGE_SHIFT;
- if (index > end_index)
- return;
- /* Avoid wrapping to the beginning of the file */
- if (index + nr_to_read < index)
- nr_to_read = ULONG_MAX - index + 1;
- /* Don't read past the page containing the last byte of the file */
- if (index + nr_to_read >= end_index)
- nr_to_read = end_index - index + 1;
/*
* Preallocate as many pages as we will need.
@@ -233,6 +227,38 @@ void __do_page_cache_readahead(struct address_space *mapping,
*/
read_pages(&rac, &page_pool, false);
}
+EXPORT_SYMBOL_GPL(page_cache_readahead_unbounded);
+
+/*
+ * __do_page_cache_readahead() actually reads a chunk of disk. It allocates
+ * the pages first, then submits them for I/O. This avoids the very bad
+ * behaviour which would occur if page allocations are causing VM writeback.
+ * We really don't want to intermingle reads and writes like that.
+ */
+void __do_page_cache_readahead(struct address_space *mapping,
+ struct file *file, pgoff_t index, unsigned long nr_to_read,
+ unsigned long lookahead_size)
+{
+ struct inode *inode = mapping->host;
+ loff_t isize = i_size_read(inode);
+ pgoff_t end_index; /* The last page we want to read */
+
+ if (isize == 0)
+ return;
+
+ end_index = (isize - 1) >> PAGE_SHIFT;
+ if (index > end_index)
+ return;
+ /* Avoid wrapping to the beginning of the file */
+ if (index + nr_to_read < index)
+ nr_to_read = ULONG_MAX - index + 1;
+ /* Don't read past the page containing the last byte of the file */
+ if (index + nr_to_read >= end_index)
+ nr_to_read = end_index - index + 1;
+
+ page_cache_readahead_unbounded(mapping, file, index, nr_to_read,
+ lookahead_size);
+}
/*
* Chunk the readahead into 2 megabyte units, so that we don't pin too much
--
2.25.1
----- End forwarded message -----
