From: "Matthew Wilcox (Oracle)" <[email protected]>
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) <[email protected]>
---
fs/ext4/verity.c | 35 ++---------------------
fs/f2fs/verity.c | 35 ++---------------------
include/linux/pagemap.h | 4 +++
mm/readahead.c | 61 +++++++++++++++++++++++++++++------------
4 files changed, 52 insertions(+), 83 deletions(-)
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index dc5ec724d889..f6e0bf05933e 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_limit(inode->i_mapping, NULL,
+ index, LONG_MAX, num_ra_pages, 0);
page = read_mapping_page(inode->i_mapping, index, NULL);
}
return page;
diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
index d7d430a6f130..71a3e36721fa 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_limit(inode->i_mapping, NULL,
+ index, LONG_MAX, 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 bd4291f78f41..4f36c06d064d 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -389,6 +389,10 @@ extern struct page * read_cache_page_gfp(struct address_space *mapping,
pgoff_t index, gfp_t gfp_mask);
extern int read_cache_pages(struct address_space *mapping,
struct list_head *pages, filler_t *filler, void *data);
+void page_cache_readahead_limit(struct address_space *mapping,
+ struct file *file, pgoff_t offset, pgoff_t end_index,
+ unsigned long nr_to_read, unsigned long lookahead_size);
+
static inline struct page *read_mapping_page(struct address_space *mapping,
pgoff_t index, void *data)
diff --git a/mm/readahead.c b/mm/readahead.c
index 975ff5e387be..94d499cfb657 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -142,35 +142,38 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages)
blk_finish_plug(&plug);
}
-/*
- * __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_limit - Start readahead beyond a file's i_size.
+ * @mapping: File address space.
+ * @file: This instance of the open file; used for authentication.
+ * @offset: First page index to read.
+ * @end_index: The maximum 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 potentially beyond a file's stated i_size. If you want
+ * to start readahead on a normal file, you probably want to call
+ * 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 offset, unsigned long nr_to_read,
- unsigned long lookahead_size)
+void page_cache_readahead_limit(struct address_space *mapping,
+ struct file *file, pgoff_t offset, pgoff_t end_index,
+ unsigned long nr_to_read, unsigned long lookahead_size)
{
- struct inode *inode = mapping->host;
- unsigned long end_index; /* The last page we want to read */
LIST_HEAD(page_pool);
unsigned long i;
- loff_t isize = i_size_read(inode);
gfp_t gfp_mask = readahead_gfp_mask(mapping);
bool use_list = mapping->a_ops->readpages;
struct readahead_control rac = {
.mapping = mapping,
- .file = filp,
+ .file = file,
._start = offset,
._nr_pages = 0,
};
- if (isize == 0)
- return;
-
- end_index = ((isize - 1) >> PAGE_SHIFT);
-
/*
* Preallocate as many pages as we will need.
*/
@@ -225,6 +228,30 @@ void __do_page_cache_readahead(struct address_space *mapping,
read_pages(&rac, &page_pool);
BUG_ON(!list_empty(&page_pool));
}
+EXPORT_SYMBOL_GPL(page_cache_readahead_limit);
+
+/*
+ * __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 offset, unsigned long nr_to_read,
+ unsigned long lookahead_size)
+{
+ struct inode *inode = mapping->host;
+ unsigned long end_index; /* The last page we want to read */
+ loff_t isize = i_size_read(inode);
+
+ if (isize == 0)
+ return;
+
+ end_index = ((isize - 1) >> PAGE_SHIFT);
+
+ page_cache_readahead_limit(mapping, file, offset, end_index,
+ nr_to_read, lookahead_size);
+}
/*
* Chunk the readahead into 2 megabyte units, so that we don't pin too much
--
2.25.0
On Tue, Feb 18, 2020 at 05:31:10PM +1100, Dave Chinner wrote:
> On Mon, Feb 17, 2020 at 10:45:56AM -0800, Matthew Wilcox wrote:
> > From: "Matthew Wilcox (Oracle)" <[email protected]>
> >
> > 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.
>
> Gross and nasty (hosting non-stale data beyond EOF in the page
> cache, that is).
I thought you meant sneaking changes into the VFS (that were rejected) by
copying VFS code and modifying it ...
> > +/**
> > + * page_cache_readahead_limit - Start readahead beyond a file's i_size.
> > + * @mapping: File address space.
> > + * @file: This instance of the open file; used for authentication.
> > + * @offset: First page index to read.
> > + * @end_index: The maximum 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 potentially beyond a file's stated i_size. If you want
> > + * to start readahead on a normal file, you probably want to call
> > + * 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 offset, unsigned long nr_to_read,
> > - unsigned long lookahead_size)
> > +void page_cache_readahead_limit(struct address_space *mapping,
>
> ... I don't think the function name conveys it's purpose. It's
> really a ranged readahead that ignores where i_size lies. i.e
>
> page_cache_readahead_range(mapping, start, end, nr_to_read)
>
> seems like a better API to me, and then you can drop the "start
> readahead beyond i_size" comments and replace it with "Range is not
> limited by the inode's i_size and hence can be used to read data
> stored beyond EOF into the page cache."
I'm concerned that calling it 'range' implies "I want to read between
start and end" rather than "I want to read nr_to_read at start, oh but
don't go past end".
Maybe the right way to do this is have the three callers cap nr_to_read.
Well, the one caller ... after all, f2fs and ext4 have no desire to
cap the length. Then we can call it page_cache_readahead_exceed() or
page_cache_readahead_dangerous() or something else like that to make it
clear that you shouldn't be calling it.
> Also: "This is almost certainly not the function you want to call.
> Use page_cache_async_readahead or page_cache_sync_readahead()
> instead."
+1 to that ;-)
Here's what I currently have:
From d202dda7a92566496fe9e233ee7855fb560324ce Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <[email protected]>
Date: Mon, 10 Feb 2020 18:31:15 -0500
Subject: [PATCH] mm: Add page_cache_readahead_exceed
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) <[email protected]>
---
fs/ext4/verity.c | 35 ++--------------------
fs/f2fs/verity.c | 35 ++--------------------
include/linux/pagemap.h | 3 ++
mm/readahead.c | 66 ++++++++++++++++++++++++++++-------------
4 files changed, 52 insertions(+), 87 deletions(-)
diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
index dc5ec724d889..172ebf860014 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_exceed(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/verity.c b/fs/f2fs/verity.c
index d7d430a6f130..f240ad087162 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_exceed(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 48c3bca57df6..1f7964d2b8ca 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -623,6 +623,9 @@ 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_exceed(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 9dd431fa16c9..cad26287ad8b 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -142,45 +142,43 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages)
blk_finish_plug(&plug);
}
-/*
- * __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_exceed - 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_exceed(struct address_space *mapping,
+ struct file *file, pgoff_t index, unsigned long nr_to_read,
unsigned long lookahead_size)
{
- struct inode *inode = mapping->host;
- unsigned long end_index; /* The last page we want to read */
LIST_HEAD(page_pool);
unsigned long i;
- loff_t isize = i_size_read(inode);
gfp_t gfp_mask = readahead_gfp_mask(mapping);
bool use_list = mapping->a_ops->readpages;
struct readahead_control rac = {
.mapping = mapping,
- .file = filp,
+ .file = file,
._start = index,
._nr_pages = 0,
};
- if (isize == 0)
- return;
-
- end_index = ((isize - 1) >> PAGE_SHIFT);
-
/*
* Preallocate as many pages as we will need.
*/
for (i = 0; i < nr_to_read; i++) {
- struct page *page;
-
- if (index > end_index)
- break;
+ struct page *page = xa_load(&mapping->i_pages, index);
- page = xa_load(&mapping->i_pages, index);
if (page && !xa_is_value(page)) {
/*
* Page already present? Kick off the current batch
@@ -225,6 +223,32 @@ void __do_page_cache_readahead(struct address_space *mapping,
read_pages(&rac, &page_pool);
BUG_ON(!list_empty(&page_pool));
}
+EXPORT_SYMBOL_GPL(page_cache_readahead_exceed);
+
+/*
+ * __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;
+
+ if (isize == 0)
+ return;
+
+ end_index = (isize - 1) >> PAGE_SHIFT;
+ if (end_index < index + nr_to_read)
+ nr_to_read = end_index - index;
+
+ page_cache_readahead_exceed(mapping, file, index, nr_to_read,
+ lookahead_size);
+}
/*
* Chunk the readahead into 2 megabyte units, so that we don't pin too much
--
2.25.0
On Tue, Feb 18, 2020 at 11:54:04AM -0800, Matthew Wilcox wrote:
> On Tue, Feb 18, 2020 at 05:31:10PM +1100, Dave Chinner wrote:
> > On Mon, Feb 17, 2020 at 10:45:56AM -0800, Matthew Wilcox wrote:
> > > From: "Matthew Wilcox (Oracle)" <[email protected]>
> > >
> > > 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.
> >
> > Gross and nasty (hosting non-stale data beyond EOF in the page
> > cache, that is).
>
> I thought you meant sneaking changes into the VFS (that were rejected) by
> copying VFS code and modifying it ...
Well, now that you mention it... :P
> > > +/**
> > > + * page_cache_readahead_limit - Start readahead beyond a file's i_size.
> > > + * @mapping: File address space.
> > > + * @file: This instance of the open file; used for authentication.
> > > + * @offset: First page index to read.
> > > + * @end_index: The maximum 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 potentially beyond a file's stated i_size. If you want
> > > + * to start readahead on a normal file, you probably want to call
> > > + * 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 offset, unsigned long nr_to_read,
> > > - unsigned long lookahead_size)
> > > +void page_cache_readahead_limit(struct address_space *mapping,
> >
> > ... I don't think the function name conveys it's purpose. It's
> > really a ranged readahead that ignores where i_size lies. i.e
> >
> > page_cache_readahead_range(mapping, start, end, nr_to_read)
> >
> > seems like a better API to me, and then you can drop the "start
> > readahead beyond i_size" comments and replace it with "Range is not
> > limited by the inode's i_size and hence can be used to read data
> > stored beyond EOF into the page cache."
>
> I'm concerned that calling it 'range' implies "I want to read between
> start and end" rather than "I want to read nr_to_read at start, oh but
> don't go past end".
>
> Maybe the right way to do this is have the three callers cap nr_to_read.
> Well, the one caller ... after all, f2fs and ext4 have no desire to
> cap the length. Then we can call it page_cache_readahead_exceed() or
> page_cache_readahead_dangerous() or something else like that to make it
> clear that you shouldn't be calling it.
Fair point.
And in reading this, it occurred to me that what we are enabling is
an "out of bounds" readahead function. so
page_cache_readahead_OOB() or *_unbounded() might be a better name....
> * Like add_to_page_cache_locked, but used to add newly allocated pages:
> diff --git a/mm/readahead.c b/mm/readahead.c
> index 9dd431fa16c9..cad26287ad8b 100644
> --- a/mm/readahead.c
> +++ b/mm/readahead.c
> @@ -142,45 +142,43 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages)
> blk_finish_plug(&plug);
> }
>
> -/*
> - * __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_exceed - 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.
Yup, looks much better.
Cheers,
Dave.
--
Dave Chinner
[email protected]
On 2/17/20 10:45 AM, Matthew Wilcox wrote:
> From: "Matthew Wilcox (Oracle)" <[email protected]>
>
> 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) <[email protected]>
> ---
> fs/ext4/verity.c | 35 ++---------------------
> fs/f2fs/verity.c | 35 ++---------------------
> include/linux/pagemap.h | 4 +++
> mm/readahead.c | 61 +++++++++++++++++++++++++++++------------
> 4 files changed, 52 insertions(+), 83 deletions(-)
Just some minor ideas below, mostly documentation, so:
Reviewed-by: John Hubbard <[email protected]>
>
> diff --git a/fs/ext4/verity.c b/fs/ext4/verity.c
> index dc5ec724d889..f6e0bf05933e 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_limit(inode->i_mapping, NULL,
> + index, LONG_MAX, num_ra_pages, 0);
LONG_MAX seems bold at first, but then again I can't think of anything smaller
that makes any sense, and the previous code didn't have a limit either...OK.
I also wondered about the NULL file parameter, and wonder if we're stripping out
information that is needed for authentication, given that that's what the newly
written kerneldoc says the "file" arg is for. But it seems that if we're this
deep in the fs code's read routines, file system authentication has long since
been addressed.
Any actually I don't yet (still working through the patches) see any authentication,
so maybe that parameter will turn out to be unnecessary.
Anyway, It's nice to see this factored out into a single routine.
> page = read_mapping_page(inode->i_mapping, index, NULL);
> }
> return page;
> diff --git a/fs/f2fs/verity.c b/fs/f2fs/verity.c
> index d7d430a6f130..71a3e36721fa 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_limit(inode->i_mapping, NULL,
> + index, LONG_MAX, 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 bd4291f78f41..4f36c06d064d 100644
> --- a/include/linux/pagemap.h
> +++ b/include/linux/pagemap.h
> @@ -389,6 +389,10 @@ extern struct page * read_cache_page_gfp(struct address_space *mapping,
> pgoff_t index, gfp_t gfp_mask);
> extern int read_cache_pages(struct address_space *mapping,
> struct list_head *pages, filler_t *filler, void *data);
> +void page_cache_readahead_limit(struct address_space *mapping,
> + struct file *file, pgoff_t offset, pgoff_t end_index,
> + unsigned long nr_to_read, unsigned long lookahead_size);
> +
>
> static inline struct page *read_mapping_page(struct address_space *mapping,
> pgoff_t index, void *data)
> diff --git a/mm/readahead.c b/mm/readahead.c
> index 975ff5e387be..94d499cfb657 100644
> --- a/mm/readahead.c
> +++ b/mm/readahead.c
> @@ -142,35 +142,38 @@ static void read_pages(struct readahead_control *rac, struct list_head *pages)
> blk_finish_plug(&plug);
> }
>
> -/*
> - * __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_limit - Start readahead beyond a file's i_size.
Maybe:
"Start readahead to a caller-specified end point" ?
(It's only *potentially* beyond files's i_size.)
> + * @mapping: File address space.
> + * @file: This instance of the open file; used for authentication.
> + * @offset: First page index to read.
> + * @end_index: The maximum page index to read.
> + * @nr_to_read: The number of pages to read.
How about:
"The number of pages to read, as long as end_index is not exceeded."
> + * @lookahead_size: Where to start the next readahead.
Pre-existing, but...it's hard to understand how a size is "where to start".
Should we rename this arg?
> + *
> + * This function is for filesystems to call when they want to start
> + * readahead potentially beyond a file's stated i_size. If you want
> + * to start readahead on a normal file, you probably want to call
> + * 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.
In fact, can we say "must not reenter filesystem"?
> */
> -void __do_page_cache_readahead(struct address_space *mapping,
> - struct file *filp, pgoff_t offset, unsigned long nr_to_read,
> - unsigned long lookahead_size)
> +void page_cache_readahead_limit(struct address_space *mapping,
> + struct file *file, pgoff_t offset, pgoff_t end_index,
> + unsigned long nr_to_read, unsigned long lookahead_size)
> {
> - struct inode *inode = mapping->host;
> - unsigned long end_index; /* The last page we want to read */
> LIST_HEAD(page_pool);
> unsigned long i;
> - loff_t isize = i_size_read(inode);
> gfp_t gfp_mask = readahead_gfp_mask(mapping);
> bool use_list = mapping->a_ops->readpages;
> struct readahead_control rac = {
> .mapping = mapping,
> - .file = filp,
> + .file = file,
> ._start = offset,
> ._nr_pages = 0,
> };
>
> - if (isize == 0)
> - return;
> -
> - end_index = ((isize - 1) >> PAGE_SHIFT);
> -
> /*
> * Preallocate as many pages as we will need.
> */
> @@ -225,6 +228,30 @@ void __do_page_cache_readahead(struct address_space *mapping,
> read_pages(&rac, &page_pool);
> BUG_ON(!list_empty(&page_pool));
> }
> +EXPORT_SYMBOL_GPL(page_cache_readahead_limit);
> +
> +/*
> + * __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 offset, unsigned long nr_to_read,
> + unsigned long lookahead_size)
> +{
> + struct inode *inode = mapping->host;
> + unsigned long end_index; /* The last page we want to read */
> + loff_t isize = i_size_read(inode);
> +
> + if (isize == 0)
> + return;
> +
> + end_index = ((isize - 1) >> PAGE_SHIFT);
> +
> + page_cache_readahead_limit(mapping, file, offset, end_index,
> + nr_to_read, lookahead_size);
> +}
>
> /*
> * Chunk the readahead into 2 megabyte units, so that we don't pin too much
>
thanks,
--
John Hubbard
NVIDIA