[PATCH v2 0/3] Implement readahead for squashfs

[PATCH v2 0/3] Implement readahead for squashfs

[Hsin-Yi Wang]

Commit c1f6925e1091("mm: put readahead pages in cache earlier") requires
fs to implement readahead callback. Otherwise there will be a
performance regression.

Commit 9eec1d897139("squashfs: provide backing_dev_info in order to
disable read-ahead") mitigates the performance drop issue for squashfs
by closing readahead for it.

This series implements readahead callback for squashfs. The previous
discussion are in [1] and [2].

[1] https://lore.kernel.org/all/CAJMQK-g9G6KQmH-V=BRGX0swZji9Wxe_2c7ht-MMAapdFy2pXw@mail.gmail.com/T/
[2] https://lore.kernel.org/linux-mm/Yn5Yij9pRPCzDozt@casper.infradead.org/t/#m4af4473b94f98a4996cb11756b633a07e5e059d1

Hsin-Yi Wang (2):
  Revert "squashfs: provide backing_dev_info in order to disable
    read-ahead"
  squashfs: implement readahead

Phillip Lougher (1):
  squashfs: always build "file direct" version of page actor

 fs/squashfs/Makefile     |  4 +--
 fs/squashfs/file.c       | 77 +++++++++++++++++++++++++++++++++++++++-
 fs/squashfs/page_actor.h | 41 ---------------------
 fs/squashfs/super.c      | 33 -----------------
 4 files changed, 78 insertions(+), 77 deletions(-)

-- 
2.36.0.550.gb090851708-goog

[PATCH v2 1/3] Revert "squashfs: provide backing_dev_info in order to disable read-ahead"

[Hsin-Yi Wang]

This reverts commit 9eec1d897139e5de287af5d559a02b811b844d82.

Revert closing the readahead to squashfs since the readahead callback
for squashfs is implemented.

Suggested-by: Xiongwei Song <sxwjean@gmail.com>
Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
---
 fs/squashfs/super.c | 33 ---------------------------------
 1 file changed, 33 deletions(-)

diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 6d594ba2ed28..32565dafa7f3 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -29,7 +29,6 @@
 #include <linux/module.h>
 #include <linux/magic.h>
 #include <linux/xattr.h>
-#include <linux/backing-dev.h>
 
 #include "squashfs_fs.h"
 #include "squashfs_fs_sb.h"
@@ -113,24 +112,6 @@ static const struct squashfs_decompressor *supported_squashfs_filesystem(
 	return decompressor;
 }
 
-static int squashfs_bdi_init(struct super_block *sb)
-{
-	int err;
-	unsigned int major = MAJOR(sb->s_dev);
-	unsigned int minor = MINOR(sb->s_dev);
-
-	bdi_put(sb->s_bdi);
-	sb->s_bdi = &noop_backing_dev_info;
-
-	err = super_setup_bdi_name(sb, "squashfs_%u_%u", major, minor);
-	if (err)
-		return err;
-
-	sb->s_bdi->ra_pages = 0;
-	sb->s_bdi->io_pages = 0;
-
-	return 0;
-}
 
 static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc)
 {
@@ -146,20 +127,6 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	TRACE("Entered squashfs_fill_superblock\n");
 
-	/*
-	 * squashfs provides 'backing_dev_info' in order to disable read-ahead. For
-	 * squashfs, I/O is not deferred, it is done immediately in read_folio,
-	 * which means the user would always have to wait their own I/O. So the effect
-	 * of readahead is very weak for squashfs. squashfs_bdi_init will set
-	 * sb->s_bdi->ra_pages and sb->s_bdi->io_pages to 0 and close readahead for
-	 * squashfs.
-	 */
-	err = squashfs_bdi_init(sb);
-	if (err) {
-		errorf(fc, "squashfs init bdi failed");
-		return err;
-	}
-
 	sb->s_fs_info = kzalloc(sizeof(*msblk), GFP_KERNEL);
 	if (sb->s_fs_info == NULL) {
 		ERROR("Failed to allocate squashfs_sb_info\n");
-- 
2.36.0.550.gb090851708-goog

Re: [PATCH v2 1/3] Revert "squashfs: provide backing_dev_info in order to disable read-ahead"

[Xiongwei Song]

On Tue, May 17, 2022 at 4:27 PM Hsin-Yi Wang <hsinyi@chromium.org> wrote:
>
> This reverts commit 9eec1d897139e5de287af5d559a02b811b844d82.
>
> Revert closing the readahead to squashfs since the readahead callback
> for squashfs is implemented.
>
> Suggested-by: Xiongwei Song <sxwjean@gmail.com>

I'd like to use "xiongwei.song@windriver.com" in my tag.

> Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
> ---
>  fs/squashfs/super.c | 33 ---------------------------------
>  1 file changed, 33 deletions(-)
>
> diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
> index 6d594ba2ed28..32565dafa7f3 100644
> --- a/fs/squashfs/super.c
> +++ b/fs/squashfs/super.c
> @@ -29,7 +29,6 @@
>  #include <linux/module.h>
>  #include <linux/magic.h>
>  #include <linux/xattr.h>
> -#include <linux/backing-dev.h>
>
>  #include "squashfs_fs.h"
>  #include "squashfs_fs_sb.h"
> @@ -113,24 +112,6 @@ static const struct squashfs_decompressor *supported_squashfs_filesystem(
>         return decompressor;
>  }
>
> -static int squashfs_bdi_init(struct super_block *sb)
> -{
> -       int err;
> -       unsigned int major = MAJOR(sb->s_dev);
> -       unsigned int minor = MINOR(sb->s_dev);
> -
> -       bdi_put(sb->s_bdi);
> -       sb->s_bdi = &noop_backing_dev_info;
> -
> -       err = super_setup_bdi_name(sb, "squashfs_%u_%u", major, minor);
> -       if (err)
> -               return err;
> -
> -       sb->s_bdi->ra_pages = 0;
> -       sb->s_bdi->io_pages = 0;
> -
> -       return 0;
> -}
>
>  static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc)
>  {
> @@ -146,20 +127,6 @@ static int squashfs_fill_super(struct super_block *sb, struct fs_context *fc)
>
>         TRACE("Entered squashfs_fill_superblock\n");
>
> -       /*
> -        * squashfs provides 'backing_dev_info' in order to disable read-ahead. For
> -        * squashfs, I/O is not deferred, it is done immediately in read_folio,
> -        * which means the user would always have to wait their own I/O. So the effect
> -        * of readahead is very weak for squashfs. squashfs_bdi_init will set
> -        * sb->s_bdi->ra_pages and sb->s_bdi->io_pages to 0 and close readahead for
> -        * squashfs.
> -        */
> -       err = squashfs_bdi_init(sb);
> -       if (err) {
> -               errorf(fc, "squashfs init bdi failed");
> -               return err;
> -       }
> -
>         sb->s_fs_info = kzalloc(sizeof(*msblk), GFP_KERNEL);
>         if (sb->s_fs_info == NULL) {
>                 ERROR("Failed to allocate squashfs_sb_info\n");
> --
> 2.36.0.550.gb090851708-goog
>
>

[PATCH v2 2/3] squashfs: always build "file direct" version of page actor

[Hsin-Yi Wang]

From: Phillip Lougher <phillip@squashfs.org.uk>

Squashfs_readahead uses the "file direct" version of the page
actor, and so build it unconditionally.

Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Phillip Lougher <phillip@squashfs.org.uk>
Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
---
 fs/squashfs/Makefile     |  4 ++--
 fs/squashfs/page_actor.h | 41 ----------------------------------------
 2 files changed, 2 insertions(+), 43 deletions(-)

diff --git a/fs/squashfs/Makefile b/fs/squashfs/Makefile
index 7bd9b8b856d0..477c89a519ee 100644
--- a/fs/squashfs/Makefile
+++ b/fs/squashfs/Makefile
@@ -5,9 +5,9 @@
 
 obj-$(CONFIG_SQUASHFS) += squashfs.o
 squashfs-y += block.o cache.o dir.o export.o file.o fragment.o id.o inode.o
-squashfs-y += namei.o super.o symlink.o decompressor.o
+squashfs-y += namei.o super.o symlink.o decompressor.o page_actor.o
 squashfs-$(CONFIG_SQUASHFS_FILE_CACHE) += file_cache.o
-squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o page_actor.o
+squashfs-$(CONFIG_SQUASHFS_FILE_DIRECT) += file_direct.o
 squashfs-$(CONFIG_SQUASHFS_DECOMP_SINGLE) += decompressor_single.o
 squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI) += decompressor_multi.o
 squashfs-$(CONFIG_SQUASHFS_DECOMP_MULTI_PERCPU) += decompressor_multi_percpu.o
diff --git a/fs/squashfs/page_actor.h b/fs/squashfs/page_actor.h
index 2e3073ace009..26e07373af8a 100644
--- a/fs/squashfs/page_actor.h
+++ b/fs/squashfs/page_actor.h
@@ -6,46 +6,6 @@
  * Phillip Lougher <phillip@squashfs.org.uk>
  */
 
-#ifndef CONFIG_SQUASHFS_FILE_DIRECT
-struct squashfs_page_actor {
-	void	**page;
-	int	pages;
-	int	length;
-	int	next_page;
-};
-
-static inline struct squashfs_page_actor *squashfs_page_actor_init(void **page,
-	int pages, int length)
-{
-	struct squashfs_page_actor *actor = kmalloc(sizeof(*actor), GFP_KERNEL);
-
-	if (actor == NULL)
-		return NULL;
-
-	actor->length = length ? : pages * PAGE_SIZE;
-	actor->page = page;
-	actor->pages = pages;
-	actor->next_page = 0;
-	return actor;
-}
-
-static inline void *squashfs_first_page(struct squashfs_page_actor *actor)
-{
-	actor->next_page = 1;
-	return actor->page[0];
-}
-
-static inline void *squashfs_next_page(struct squashfs_page_actor *actor)
-{
-	return actor->next_page == actor->pages ? NULL :
-		actor->page[actor->next_page++];
-}
-
-static inline void squashfs_finish_page(struct squashfs_page_actor *actor)
-{
-	/* empty */
-}
-#else
 struct squashfs_page_actor {
 	union {
 		void		**buffer;
@@ -76,4 +36,3 @@ static inline void squashfs_finish_page(struct squashfs_page_actor *actor)
 	actor->squashfs_finish_page(actor);
 }
 #endif
-#endif
-- 
2.36.0.550.gb090851708-goog

[PATCH v2 3/3] squashfs: implement readahead

[Hsin-Yi Wang]

Implement readahead callback for squashfs. It will read datablocks
which cover pages in readahead request. For a few cases it will
not mark page as uptodate, including:
- file end is 0.
- zero filled blocks.
- current batch of pages isn't in the same datablock or not enough in a
  datablock.
Otherwise pages will be marked as uptodate. The unhandled pages will be
updated by readpage later.

Suggested-by: Matthew Wilcox <willy@infradead.org>
Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
Reported-by: Matthew Wilcox <willy@infradead.org>
Reported-by: Phillip Lougher <phillip@squashfs.org.uk>
Reported-by: Xiongwei Song <sxwjean@gmail.com>
---
v1->v2: remove unused check on readahead_expand().
v1: https://lore.kernel.org/lkml/20220516105100.1412740-3-hsinyi@chromium.org/
---
 fs/squashfs/file.c | 77 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 76 insertions(+), 1 deletion(-)

diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index a8e495d8eb86..e10a55c5b1eb 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -39,6 +39,7 @@
 #include "squashfs_fs_sb.h"
 #include "squashfs_fs_i.h"
 #include "squashfs.h"
+#include "page_actor.h"
 
 /*
  * Locate cache slot in range [offset, index] for specified inode.  If
@@ -495,7 +496,81 @@ static int squashfs_read_folio(struct file *file, struct folio *folio)
 	return 0;
 }
 
+static void squashfs_readahead(struct readahead_control *ractl)
+{
+	struct inode *inode = ractl->mapping->host;
+	struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
+	size_t mask = (1UL << msblk->block_log) - 1;
+	size_t shift = msblk->block_log - PAGE_SHIFT;
+	loff_t start = readahead_pos(ractl) &~ mask;
+	size_t len = readahead_length(ractl) + readahead_pos(ractl) - start;
+	struct squashfs_page_actor *actor;
+	unsigned int nr_pages = 0;
+	struct page **pages;
+	u64 block = 0;
+	int bsize, res, i, index;
+	int file_end = i_size_read(inode) >> msblk->block_log;
+	unsigned int max_pages = 1UL << shift;
+
+	readahead_expand(ractl, start, (len | mask) + 1);
+
+	if (file_end == 0)
+		return;
+
+	pages = kmalloc_array(max_pages, sizeof(void *), GFP_KERNEL);
+	if (!pages)
+		return;
+
+	actor = squashfs_page_actor_init_special(pages, max_pages, 0);
+	if (!actor)
+		goto out;
+
+	for (;;) {
+		nr_pages = __readahead_batch(ractl, pages, max_pages);
+		if (!nr_pages)
+			break;
+
+		if (readahead_pos(ractl) >= i_size_read(inode) ||
+		    nr_pages < max_pages)
+			goto skip_pages;
+
+		index = pages[0]->index >> shift;
+		if ((pages[nr_pages - 1]->index >> shift) != index)
+			goto skip_pages;
+
+		bsize = read_blocklist(inode, index, &block);
+		if (bsize == 0)
+			goto skip_pages;
+
+		res = squashfs_read_data(inode->i_sb, block, bsize, NULL,
+					 actor);
+
+		if (res >= 0)
+			for (i = 0; i < nr_pages; i++)
+				SetPageUptodate(pages[i]);
+
+		for (i = 0; i < nr_pages; i++) {
+			unlock_page(pages[i]);
+			put_page(pages[i]);
+		}
+	}
+
+	kfree(actor);
+	kfree(pages);
+	return;
+
+skip_pages:
+	for (i = 0; i < nr_pages; i++) {
+		unlock_page(pages[i]);
+		put_page(pages[i]);
+	}
+
+	kfree(actor);
+out:
+	kfree(pages);
+}
 
 const struct address_space_operations squashfs_aops = {
-	.read_folio = squashfs_read_folio
+	.read_folio = squashfs_read_folio,
+	.readahead = squashfs_readahead
 };
-- 
2.36.0.550.gb090851708-goog

Re: [PATCH v2 3/3] squashfs: implement readahead

[Xiongwei Song]

On Tue, May 17, 2022 at 4:28 PM Hsin-Yi Wang <hsinyi@chromium.org> wrote:
>
> Implement readahead callback for squashfs. It will read datablocks
> which cover pages in readahead request. For a few cases it will
> not mark page as uptodate, including:
> - file end is 0.
> - zero filled blocks.
> - current batch of pages isn't in the same datablock or not enough in a
>   datablock.
> Otherwise pages will be marked as uptodate. The unhandled pages will be
> updated by readpage later.
>
> Suggested-by: Matthew Wilcox <willy@infradead.org>
> Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
> Reported-by: Matthew Wilcox <willy@infradead.org>
> Reported-by: Phillip Lougher <phillip@squashfs.org.uk>
> Reported-by: Xiongwei Song <sxwjean@gmail.com>

"xiongwei.song@windriver.com" too.

> ---
> v1->v2: remove unused check on readahead_expand().
> v1: https://lore.kernel.org/lkml/20220516105100.1412740-3-hsinyi@chromium.org/
> ---
>  fs/squashfs/file.c | 77 +++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 76 insertions(+), 1 deletion(-)
>
> diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
> index a8e495d8eb86..e10a55c5b1eb 100644
> --- a/fs/squashfs/file.c
> +++ b/fs/squashfs/file.c
> @@ -39,6 +39,7 @@
>  #include "squashfs_fs_sb.h"
>  #include "squashfs_fs_i.h"
>  #include "squashfs.h"
> +#include "page_actor.h"
>
>  /*
>   * Locate cache slot in range [offset, index] for specified inode.  If
> @@ -495,7 +496,81 @@ static int squashfs_read_folio(struct file *file, struct folio *folio)
>         return 0;
>  }
>
> +static void squashfs_readahead(struct readahead_control *ractl)
> +{
> +       struct inode *inode = ractl->mapping->host;
> +       struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
> +       size_t mask = (1UL << msblk->block_log) - 1;
> +       size_t shift = msblk->block_log - PAGE_SHIFT;
> +       loff_t start = readahead_pos(ractl) &~ mask;
> +       size_t len = readahead_length(ractl) + readahead_pos(ractl) - start;
> +       struct squashfs_page_actor *actor;
> +       unsigned int nr_pages = 0;
> +       struct page **pages;
> +       u64 block = 0;
> +       int bsize, res, i, index;
> +       int file_end = i_size_read(inode) >> msblk->block_log;
> +       unsigned int max_pages = 1UL << shift;
> +
> +       readahead_expand(ractl, start, (len | mask) + 1);
> +
> +       if (file_end == 0)
> +               return;
> +
> +       pages = kmalloc_array(max_pages, sizeof(void *), GFP_KERNEL);
> +       if (!pages)
> +               return;
> +
> +       actor = squashfs_page_actor_init_special(pages, max_pages, 0);
> +       if (!actor)
> +               goto out;
> +
> +       for (;;) {
> +               nr_pages = __readahead_batch(ractl, pages, max_pages);
> +               if (!nr_pages)
> +                       break;
> +
> +               if (readahead_pos(ractl) >= i_size_read(inode) ||
> +                   nr_pages < max_pages)
> +                       goto skip_pages;
> +
> +               index = pages[0]->index >> shift;
> +               if ((pages[nr_pages - 1]->index >> shift) != index)
> +                       goto skip_pages;
> +
> +               bsize = read_blocklist(inode, index, &block);
> +               if (bsize == 0)
> +                       goto skip_pages;
> +
> +               res = squashfs_read_data(inode->i_sb, block, bsize, NULL,
> +                                        actor);
> +
> +               if (res >= 0)
> +                       for (i = 0; i < nr_pages; i++)
> +                               SetPageUptodate(pages[i]);
> +
> +               for (i = 0; i < nr_pages; i++) {
> +                       unlock_page(pages[i]);
> +                       put_page(pages[i]);
> +               }
> +       }
> +
> +       kfree(actor);
> +       kfree(pages);
> +       return;
> +
> +skip_pages:
> +       for (i = 0; i < nr_pages; i++) {
> +               unlock_page(pages[i]);
> +               put_page(pages[i]);
> +       }
> +
> +       kfree(actor);
> +out:
> +       kfree(pages);
> +}
>
>  const struct address_space_operations squashfs_aops = {
> -       .read_folio = squashfs_read_folio
> +       .read_folio = squashfs_read_folio,
> +       .readahead = squashfs_readahead
>  };
> --
> 2.36.0.550.gb090851708-goog
>
>

Re: [PATCH v2 3/3] squashfs: implement readahead

[Hsin-Yi Wang]

On Tue, May 17, 2022 at 5:17 PM Xiongwei Song <sxwjean@gmail.com> wrote:
>
> On Tue, May 17, 2022 at 4:28 PM Hsin-Yi Wang <hsinyi@chromium.org> wrote:
> >
> > Implement readahead callback for squashfs. It will read datablocks
> > which cover pages in readahead request. For a few cases it will
> > not mark page as uptodate, including:
> > - file end is 0.
> > - zero filled blocks.
> > - current batch of pages isn't in the same datablock or not enough in a
> >   datablock.
> > Otherwise pages will be marked as uptodate. The unhandled pages will be
> > updated by readpage later.
> >
> > Suggested-by: Matthew Wilcox <willy@infradead.org>
> > Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
> > Reported-by: Matthew Wilcox <willy@infradead.org>
> > Reported-by: Phillip Lougher <phillip@squashfs.org.uk>
> > Reported-by: Xiongwei Song <sxwjean@gmail.com>
>
> "xiongwei.song@windriver.com" too.
>
ack.
<snip>

Re: [PATCH v2 3/3] squashfs: implement readahead

[Hsin-Yi Wang]

On Tue, May 17, 2022 at 4:28 PM Hsin-Yi Wang <hsinyi@chromium.org> wrote:
>
> Implement readahead callback for squashfs. It will read datablocks
> which cover pages in readahead request. For a few cases it will
> not mark page as uptodate, including:
> - file end is 0.
> - zero filled blocks.
> - current batch of pages isn't in the same datablock or not enough in a
>   datablock.
> Otherwise pages will be marked as uptodate. The unhandled pages will be
> updated by readpage later.
>
> Suggested-by: Matthew Wilcox <willy@infradead.org>
> Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
> Reported-by: Matthew Wilcox <willy@infradead.org>
> Reported-by: Phillip Lougher <phillip@squashfs.org.uk>
> Reported-by: Xiongwei Song <sxwjean@gmail.com>
> ---
> v1->v2: remove unused check on readahead_expand().
> v1: https://lore.kernel.org/lkml/20220516105100.1412740-3-hsinyi@chromium.org/
> ---

Hi Phillip and Matthew,

Regarding the performance issue of this patch, I saw a possible
performance gain if we only read the first block instead of reading
until nr_pages == 0.

To be more clear, apply the following diff (Please ignore the skipping
of nr_pages check first. This is a demonstration of "only read and
update the first block per readahead call"):

diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
index aad6823f0615..c52f7c4a7cfe 100644
--- a/fs/squashfs/file.c
+++ b/fs/squashfs/file.c
@@ -524,10 +524,8 @@ static void squashfs_readahead(struct
readahead_control *ractl)
        if (!actor)
                goto out;

-       for (;;) {
+       {
                nr_pages = __readahead_batch(ractl, pages, max_pages);
-               if (!nr_pages)
-                       break;

                if (readahead_pos(ractl) >= i_size_read(inode) ||
                    nr_pages < max_pages)


All the performance numbers:
1. original: 39s
2. revert "mm: put readahead pages in cache earlier": 2.8s
3. v2 of this patch: 2.7s
4. v2 of this patch and apply the diff: 1.8s

In my testing data, normally it reads and updates 1~2 blocks per
readahead call. The change might not make sense since the performance
improvement may only happen in certain cases.

What do you think? Or is the performance of the current patch
considered reasonable?

Thanks.

testing env:
- arm64 on kernel 5.10
- data: ~ 300K pack file contains some android files

>  fs/squashfs/file.c | 77 +++++++++++++++++++++++++++++++++++++++++++++-
>  1 file changed, 76 insertions(+), 1 deletion(-)
>
> diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
> index a8e495d8eb86..e10a55c5b1eb 100644
> --- a/fs/squashfs/file.c
> +++ b/fs/squashfs/file.c
> @@ -39,6 +39,7 @@
>  #include "squashfs_fs_sb.h"
>  #include "squashfs_fs_i.h"
>  #include "squashfs.h"
> +#include "page_actor.h"
>
>  /*
>   * Locate cache slot in range [offset, index] for specified inode.  If
> @@ -495,7 +496,81 @@ static int squashfs_read_folio(struct file *file, struct folio *folio)
>         return 0;
>  }
>
> +static void squashfs_readahead(struct readahead_control *ractl)
> +{
> +       struct inode *inode = ractl->mapping->host;
> +       struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
> +       size_t mask = (1UL << msblk->block_log) - 1;
> +       size_t shift = msblk->block_log - PAGE_SHIFT;
> +       loff_t start = readahead_pos(ractl) &~ mask;
> +       size_t len = readahead_length(ractl) + readahead_pos(ractl) - start;
> +       struct squashfs_page_actor *actor;
> +       unsigned int nr_pages = 0;
> +       struct page **pages;
> +       u64 block = 0;
> +       int bsize, res, i, index;
> +       int file_end = i_size_read(inode) >> msblk->block_log;
> +       unsigned int max_pages = 1UL << shift;
> +
> +       readahead_expand(ractl, start, (len | mask) + 1);
> +
> +       if (file_end == 0)
> +               return;
> +
> +       pages = kmalloc_array(max_pages, sizeof(void *), GFP_KERNEL);
> +       if (!pages)
> +               return;
> +
> +       actor = squashfs_page_actor_init_special(pages, max_pages, 0);
> +       if (!actor)
> +               goto out;
> +
> +       for (;;) {
> +               nr_pages = __readahead_batch(ractl, pages, max_pages);
> +               if (!nr_pages)
> +                       break;
> +
> +               if (readahead_pos(ractl) >= i_size_read(inode) ||
> +                   nr_pages < max_pages)
> +                       goto skip_pages;
> +
> +               index = pages[0]->index >> shift;
> +               if ((pages[nr_pages - 1]->index >> shift) != index)
> +                       goto skip_pages;
> +
> +               bsize = read_blocklist(inode, index, &block);
> +               if (bsize == 0)
> +                       goto skip_pages;
> +
> +               res = squashfs_read_data(inode->i_sb, block, bsize, NULL,
> +                                        actor);
> +
> +               if (res >= 0)
> +                       for (i = 0; i < nr_pages; i++)
> +                               SetPageUptodate(pages[i]);
> +
> +               for (i = 0; i < nr_pages; i++) {
> +                       unlock_page(pages[i]);
> +                       put_page(pages[i]);
> +               }
> +       }
> +
> +       kfree(actor);
> +       kfree(pages);
> +       return;
> +
> +skip_pages:
> +       for (i = 0; i < nr_pages; i++) {
> +               unlock_page(pages[i]);
> +               put_page(pages[i]);
> +       }
> +
> +       kfree(actor);
> +out:
> +       kfree(pages);
> +}
>
>  const struct address_space_operations squashfs_aops = {
> -       .read_folio = squashfs_read_folio
> +       .read_folio = squashfs_read_folio,
> +       .readahead = squashfs_readahead
>  };
> --
> 2.36.0.550.gb090851708-goog
>

Re: [PATCH v2 3/3] squashfs: implement readahead

[Phillip Lougher]

On 19/05/2022 09:09, Hsin-Yi Wang wrote:
> On Tue, May 17, 2022 at 4:28 PM Hsin-Yi Wang <hsinyi@chromium.org> wrote:
>>
>> Implement readahead callback for squashfs. It will read datablocks
>> which cover pages in readahead request. For a few cases it will
>> not mark page as uptodate, including:
>> - file end is 0.
>> - zero filled blocks.
>> - current batch of pages isn't in the same datablock or not enough in a
>>    datablock.
>> Otherwise pages will be marked as uptodate. The unhandled pages will be
>> updated by readpage later.
>>
>> Suggested-by: Matthew Wilcox <willy@infradead.org>
>> Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
>> Reported-by: Matthew Wilcox <willy@infradead.org>
>> Reported-by: Phillip Lougher <phillip@squashfs.org.uk>
>> Reported-by: Xiongwei Song <sxwjean@gmail.com>
>> ---
>> v1->v2: remove unused check on readahead_expand().
>> v1: https://lore.kernel.org/lkml/20220516105100.1412740-3-hsinyi@chromium.org/
>> ---
> 
> Hi Phillip and Matthew,
> 
> Regarding the performance issue of this patch, I saw a possible
> performance gain if we only read the first block instead of reading
> until nr_pages == 0.
> 
> To be more clear, apply the following diff (Please ignore the skipping
> of nr_pages check first. This is a demonstration of "only read and
> update the first block per readahead call"):
> 
> diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
> index aad6823f0615..c52f7c4a7cfe 100644
> --- a/fs/squashfs/file.c
> +++ b/fs/squashfs/file.c
> @@ -524,10 +524,8 @@ static void squashfs_readahead(struct
> readahead_control *ractl)
>          if (!actor)
>                  goto out;
> 
> -       for (;;) {
> +       {
>                  nr_pages = __readahead_batch(ractl, pages, max_pages);
> -               if (!nr_pages)
> -                       break;
> 
>                  if (readahead_pos(ractl) >= i_size_read(inode) ||
>                      nr_pages < max_pages)
> 
> 
> All the performance numbers:
> 1. original: 39s
> 2. revert "mm: put readahead pages in cache earlier": 2.8s
> 3. v2 of this patch: 2.7s
> 4. v2 of this patch and apply the diff: 1.8s
> 
> In my testing data, normally it reads and updates 1~2 blocks per
> readahead call. The change might not make sense since the performance
> improvement may only happen in certain cases.
> What do you think? Or is the performance of the current patch
> considered reasonable?

It entirely depends on where the speed improvement comes from.

 From experience, the speed improvement is probably worthwhile,
and probably isn't gained at the expense of worse performance
on other work-loads.

But this is a guestimate, based on the fact timings 2 and 3
(2.8s v 2.7s) are almost identical.  Which implies the v2
patch isn't now doing any more work than the previous
baseline before the "mm: put readahead pages in cache earlier"
patch (*).

As such the speed improvement must be coming from increased
parallelism.  Such as moving from serially reading the
readahead blocks to parallel reading.

But, without looking at any trace output, that is just a
guestimate.

Phillip

(*) multiply decompressing the same blocks, which
     is the cause of the performance regression.
> 
> Thanks.
> 
> testing env:
> - arm64 on kernel 5.10
> - data: ~ 300K pack file contains some android files
> 
>>   fs/squashfs/file.c | 77 +++++++++++++++++++++++++++++++++++++++++++++-
>>   1 file changed, 76 insertions(+), 1 deletion(-)
>>
>> diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
>> index a8e495d8eb86..e10a55c5b1eb 100644
>> --- a/fs/squashfs/file.c
>> +++ b/fs/squashfs/file.c
>> @@ -39,6 +39,7 @@
>>   #include "squashfs_fs_sb.h"
>>   #include "squashfs_fs_i.h"
>>   #include "squashfs.h"
>> +#include "page_actor.h"
>>
>>   /*
>>    * Locate cache slot in range [offset, index] for specified inode.  If
>> @@ -495,7 +496,81 @@ static int squashfs_read_folio(struct file *file, struct folio *folio)
>>          return 0;
>>   }
>>
>> +static void squashfs_readahead(struct readahead_control *ractl)
>> +{
>> +       struct inode *inode = ractl->mapping->host;
>> +       struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
>> +       size_t mask = (1UL << msblk->block_log) - 1;
>> +       size_t shift = msblk->block_log - PAGE_SHIFT;
>> +       loff_t start = readahead_pos(ractl) &~ mask;
>> +       size_t len = readahead_length(ractl) + readahead_pos(ractl) - start;
>> +       struct squashfs_page_actor *actor;
>> +       unsigned int nr_pages = 0;
>> +       struct page **pages;
>> +       u64 block = 0;
>> +       int bsize, res, i, index;
>> +       int file_end = i_size_read(inode) >> msblk->block_log;
>> +       unsigned int max_pages = 1UL << shift;
>> +
>> +       readahead_expand(ractl, start, (len | mask) + 1);
>> +
>> +       if (file_end == 0)
>> +               return;
>> +
>> +       pages = kmalloc_array(max_pages, sizeof(void *), GFP_KERNEL);
>> +       if (!pages)
>> +               return;
>> +
>> +       actor = squashfs_page_actor_init_special(pages, max_pages, 0);
>> +       if (!actor)
>> +               goto out;
>> +
>> +       for (;;) {
>> +               nr_pages = __readahead_batch(ractl, pages, max_pages);
>> +               if (!nr_pages)
>> +                       break;
>> +
>> +               if (readahead_pos(ractl) >= i_size_read(inode) ||
>> +                   nr_pages < max_pages)
>> +                       goto skip_pages;
>> +
>> +               index = pages[0]->index >> shift;
>> +               if ((pages[nr_pages - 1]->index >> shift) != index)
>> +                       goto skip_pages;
>> +
>> +               bsize = read_blocklist(inode, index, &block);
>> +               if (bsize == 0)
>> +                       goto skip_pages;
>> +
>> +               res = squashfs_read_data(inode->i_sb, block, bsize, NULL,
>> +                                        actor);
>> +
>> +               if (res >= 0)
>> +                       for (i = 0; i < nr_pages; i++)
>> +                               SetPageUptodate(pages[i]);
>> +
>> +               for (i = 0; i < nr_pages; i++) {
>> +                       unlock_page(pages[i]);
>> +                       put_page(pages[i]);
>> +               }
>> +       }
>> +
>> +       kfree(actor);
>> +       kfree(pages);
>> +       return;
>> +
>> +skip_pages:
>> +       for (i = 0; i < nr_pages; i++) {
>> +               unlock_page(pages[i]);
>> +               put_page(pages[i]);
>> +       }
>> +
>> +       kfree(actor);
>> +out:
>> +       kfree(pages);
>> +}
>>
>>   const struct address_space_operations squashfs_aops = {
>> -       .read_folio = squashfs_read_folio
>> +       .read_folio = squashfs_read_folio,
>> +       .readahead = squashfs_readahead
>>   };
>> --
>> 2.36.0.550.gb090851708-goog
>>

Re: [PATCH v2 3/3] squashfs: implement readahead

[Hsin-Yi Wang]

On Fri, May 20, 2022 at 11:02 AM Phillip Lougher
<phillip@squashfs.org.uk> wrote:
>
> On 19/05/2022 09:09, Hsin-Yi Wang wrote:
> > On Tue, May 17, 2022 at 4:28 PM Hsin-Yi Wang <hsinyi@chromium.org> wrote:
> >>
> >> Implement readahead callback for squashfs. It will read datablocks
> >> which cover pages in readahead request. For a few cases it will
> >> not mark page as uptodate, including:
> >> - file end is 0.
> >> - zero filled blocks.
> >> - current batch of pages isn't in the same datablock or not enough in a
> >>    datablock.
> >> Otherwise pages will be marked as uptodate. The unhandled pages will be
> >> updated by readpage later.
> >>
> >> Suggested-by: Matthew Wilcox <willy@infradead.org>
> >> Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
> >> Reported-by: Matthew Wilcox <willy@infradead.org>
> >> Reported-by: Phillip Lougher <phillip@squashfs.org.uk>
> >> Reported-by: Xiongwei Song <sxwjean@gmail.com>
> >> ---
> >> v1->v2: remove unused check on readahead_expand().
> >> v1: https://lore.kernel.org/lkml/20220516105100.1412740-3-hsinyi@chromium.org/
> >> ---
> >
> > Hi Phillip and Matthew,
> >
> > Regarding the performance issue of this patch, I saw a possible
> > performance gain if we only read the first block instead of reading
> > until nr_pages == 0.
> >
> > To be more clear, apply the following diff (Please ignore the skipping
> > of nr_pages check first. This is a demonstration of "only read and
> > update the first block per readahead call"):
> >
> > diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
> > index aad6823f0615..c52f7c4a7cfe 100644
> > --- a/fs/squashfs/file.c
> > +++ b/fs/squashfs/file.c
> > @@ -524,10 +524,8 @@ static void squashfs_readahead(struct
> > readahead_control *ractl)
> >          if (!actor)
> >                  goto out;
> >
> > -       for (;;) {
> > +       {
> >                  nr_pages = __readahead_batch(ractl, pages, max_pages);
> > -               if (!nr_pages)
> > -                       break;
> >
> >                  if (readahead_pos(ractl) >= i_size_read(inode) ||
> >                      nr_pages < max_pages)
> >
> >
> > All the performance numbers:
> > 1. original: 39s
> > 2. revert "mm: put readahead pages in cache earlier": 2.8s
> > 3. v2 of this patch: 2.7s
> > 4. v2 of this patch and apply the diff: 1.8s
> >
> > In my testing data, normally it reads and updates 1~2 blocks per
> > readahead call. The change might not make sense since the performance
> > improvement may only happen in certain cases.
> > What do you think? Or is the performance of the current patch
> > considered reasonable?
>
> It entirely depends on where the speed improvement comes from.
>
>  From experience, the speed improvement is probably worthwhile,
> and probably isn't gained at the expense of worse performance
> on other work-loads.
>
> But this is a guestimate, based on the fact timings 2 and 3
> (2.8s v 2.7s) are almost identical.  Which implies the v2
> patch isn't now doing any more work than the previous
> baseline before the "mm: put readahead pages in cache earlier"
> patch (*).
>
> As such the speed improvement must be coming from increased
> parallelism.  Such as moving from serially reading the
> readahead blocks to parallel reading.
>
Thanks for the idea. I checked this by offlining other cores until
only one core exists. Removing loops still results in less time.

But after counting the #traces lines in squashfs_read_data():
If we remove the for loop (timings 4), the logs are less: 2.3K lines,
while v2 (timings 3) has 3.7K (other timings are also around 3.7K), so
removing loop doesn't look right.

I think v2 should be fine considering the slightly to none regression
compared to before.

Hi Matthew, what do you think? Do you have other comments? If not,
should I send a v3 to change Xiongwei Song's email address or can you
help modify it?

Thanks

> But, without looking at any trace output, that is just a
> guestimate.
>
> Phillip
>
> (*) multiply decompressing the same blocks, which
>      is the cause of the performance regression.
> >
> > Thanks.
> >
> > testing env:
> > - arm64 on kernel 5.10
> > - data: ~ 300K pack file contains some android files
> >
> >>   fs/squashfs/file.c | 77 +++++++++++++++++++++++++++++++++++++++++++++-
> >>   1 file changed, 76 insertions(+), 1 deletion(-)
> >>
> >> diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
> >> index a8e495d8eb86..e10a55c5b1eb 100644
> >> --- a/fs/squashfs/file.c
> >> +++ b/fs/squashfs/file.c
> >> @@ -39,6 +39,7 @@
> >>   #include "squashfs_fs_sb.h"
> >>   #include "squashfs_fs_i.h"
> >>   #include "squashfs.h"
> >> +#include "page_actor.h"
> >>
> >>   /*
> >>    * Locate cache slot in range [offset, index] for specified inode.  If
> >> @@ -495,7 +496,81 @@ static int squashfs_read_folio(struct file *file, struct folio *folio)
> >>          return 0;
> >>   }
> >>
> >> +static void squashfs_readahead(struct readahead_control *ractl)
> >> +{
> >> +       struct inode *inode = ractl->mapping->host;
> >> +       struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
> >> +       size_t mask = (1UL << msblk->block_log) - 1;
> >> +       size_t shift = msblk->block_log - PAGE_SHIFT;
> >> +       loff_t start = readahead_pos(ractl) &~ mask;
> >> +       size_t len = readahead_length(ractl) + readahead_pos(ractl) - start;
> >> +       struct squashfs_page_actor *actor;
> >> +       unsigned int nr_pages = 0;
> >> +       struct page **pages;
> >> +       u64 block = 0;
> >> +       int bsize, res, i, index;
> >> +       int file_end = i_size_read(inode) >> msblk->block_log;
> >> +       unsigned int max_pages = 1UL << shift;
> >> +
> >> +       readahead_expand(ractl, start, (len | mask) + 1);
> >> +
> >> +       if (file_end == 0)
> >> +               return;
> >> +
> >> +       pages = kmalloc_array(max_pages, sizeof(void *), GFP_KERNEL);
> >> +       if (!pages)
> >> +               return;
> >> +
> >> +       actor = squashfs_page_actor_init_special(pages, max_pages, 0);
> >> +       if (!actor)
> >> +               goto out;
> >> +
> >> +       for (;;) {
> >> +               nr_pages = __readahead_batch(ractl, pages, max_pages);
> >> +               if (!nr_pages)
> >> +                       break;
> >> +
> >> +               if (readahead_pos(ractl) >= i_size_read(inode) ||
> >> +                   nr_pages < max_pages)
> >> +                       goto skip_pages;
> >> +
> >> +               index = pages[0]->index >> shift;
> >> +               if ((pages[nr_pages - 1]->index >> shift) != index)
> >> +                       goto skip_pages;
> >> +
> >> +               bsize = read_blocklist(inode, index, &block);
> >> +               if (bsize == 0)
> >> +                       goto skip_pages;
> >> +
> >> +               res = squashfs_read_data(inode->i_sb, block, bsize, NULL,
> >> +                                        actor);
> >> +
> >> +               if (res >= 0)
> >> +                       for (i = 0; i < nr_pages; i++)
> >> +                               SetPageUptodate(pages[i]);
> >> +
> >> +               for (i = 0; i < nr_pages; i++) {
> >> +                       unlock_page(pages[i]);
> >> +                       put_page(pages[i]);
> >> +               }
> >> +       }
> >> +
> >> +       kfree(actor);
> >> +       kfree(pages);
> >> +       return;
> >> +
> >> +skip_pages:
> >> +       for (i = 0; i < nr_pages; i++) {
> >> +               unlock_page(pages[i]);
> >> +               put_page(pages[i]);
> >> +       }
> >> +
> >> +       kfree(actor);
> >> +out:
> >> +       kfree(pages);
> >> +}
> >>
> >>   const struct address_space_operations squashfs_aops = {
> >> -       .read_folio = squashfs_read_folio
> >> +       .read_folio = squashfs_read_folio,
> >> +       .readahead = squashfs_readahead
> >>   };
> >> --
> >> 2.36.0.550.gb090851708-goog
> >>
>

Re: [PATCH v2 3/3] squashfs: implement readahead

[Phillip Lougher]

On 20/05/2022 08:38, Hsin-Yi Wang wrote:
> On Fri, May 20, 2022 at 11:02 AM Phillip Lougher
> <phillip@squashfs.org.uk> wrote:
>>
>> On 19/05/2022 09:09, Hsin-Yi Wang wrote:
>>> On Tue, May 17, 2022 at 4:28 PM Hsin-Yi Wang <hsinyi@chromium.org> wrote:
>>>>
>>>> Implement readahead callback for squashfs. It will read datablocks
>>>> which cover pages in readahead request. For a few cases it will
>>>> not mark page as uptodate, including:
>>>> - file end is 0.
>>>> - zero filled blocks.
>>>> - current batch of pages isn't in the same datablock or not enough in a
>>>>     datablock.
>>>> Otherwise pages will be marked as uptodate. The unhandled pages will be
>>>> updated by readpage later.
>>>>
>>>> Suggested-by: Matthew Wilcox <willy@infradead.org>
>>>> Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
>>>> Reported-by: Matthew Wilcox <willy@infradead.org>
>>>> Reported-by: Phillip Lougher <phillip@squashfs.org.uk>
>>>> Reported-by: Xiongwei Song <sxwjean@gmail.com>
>>>> ---
>>>> v1->v2: remove unused check on readahead_expand().
>>>> v1: https://lore.kernel.org/lkml/20220516105100.1412740-3-hsinyi@chromium.org/
>>>> ---
>>>
>>> Hi Phillip and Matthew,
>>>
>>> Regarding the performance issue of this patch, I saw a possible
>>> performance gain if we only read the first block instead of reading
>>> until nr_pages == 0.
>>>
>>> To be more clear, apply the following diff (Please ignore the skipping
>>> of nr_pages check first. This is a demonstration of "only read and
>>> update the first block per readahead call"):
>>>
>>> diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
>>> index aad6823f0615..c52f7c4a7cfe 100644
>>> --- a/fs/squashfs/file.c
>>> +++ b/fs/squashfs/file.c
>>> @@ -524,10 +524,8 @@ static void squashfs_readahead(struct
>>> readahead_control *ractl)
>>>           if (!actor)
>>>                   goto out;
>>>
>>> -       for (;;) {
>>> +       {
>>>                   nr_pages = __readahead_batch(ractl, pages, max_pages);
>>> -               if (!nr_pages)
>>> -                       break;
>>>
>>>                   if (readahead_pos(ractl) >= i_size_read(inode) ||
>>>                       nr_pages < max_pages)
>>>
>>>
>>> All the performance numbers:
>>> 1. original: 39s
>>> 2. revert "mm: put readahead pages in cache earlier": 2.8s
>>> 3. v2 of this patch: 2.7s
>>> 4. v2 of this patch and apply the diff: 1.8s
>>>
>>> In my testing data, normally it reads and updates 1~2 blocks per
>>> readahead call. The change might not make sense since the performance
>>> improvement may only happen in certain cases.
>>> What do you think? Or is the performance of the current patch
>>> considered reasonable?
>>
>> It entirely depends on where the speed improvement comes from.
>>
>>   From experience, the speed improvement is probably worthwhile,
>> and probably isn't gained at the expense of worse performance
>> on other work-loads.
>>
>> But this is a guestimate, based on the fact timings 2 and 3
>> (2.8s v 2.7s) are almost identical.  Which implies the v2
>> patch isn't now doing any more work than the previous
>> baseline before the "mm: put readahead pages in cache earlier"
>> patch (*).
>>
>> As such the speed improvement must be coming from increased
>> parallelism.  Such as moving from serially reading the
>> readahead blocks to parallel reading.
>>
> Thanks for the idea. I checked this by offlining other cores until
> only one core exists. Removing loops still results in less time.
> 
> But after counting the #traces lines in squashfs_read_data():
> If we remove the for loop (timings 4), the logs are less: 2.3K lines,
> while v2 (timings 3) has 3.7K (other timings are also around 3.7K), so
> removing loop doesn't look right.

If a lot less data is being read than the other timings, then this does
look incorrect.

> 
> I think v2 should be fine considering the slightly to none regression
> compared to before.
> 

The fact the timings are almost identical implies all that needs
to be done to remove the performance regression has been done.

There are two things missing from the patch which need to
be handled.  These are not related to performance but error
handling and correctness.  So I have waited until now to
raise it.

If you look at the code for file_direct.c::squashfs_readpage_block()

https://elixir.bootlin.com/linux/latest/source/fs/squashfs/file_direct.c#L93

****
	res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
	if (res < 0)
		goto mark_errored;

	if (res != expected) {
		res = -EIO;
		goto mark_errored;
	}
****

You will see that it checks for two return conditions from 
squashfs_read_data().

If the decompressor returns error, or if the decompressed block
is different in size to that expected, then this is an error situation
(e.g. corrupted filesystem), and the read is marked as bad.

The current V2 patch doesn't check that the block decompressed
to the correct size (res != expected), and this could mean
filesystem corruption is not detected, which will be an
error handling regression.

Secondly, if you look at
https://elixir.bootlin.com/linux/latest/source/fs/squashfs/file_direct.c#L102

****
	/* Last page may have trailing bytes not filled */
	bytes = res % PAGE_SIZE;
	if (bytes) {
		pageaddr = kmap_atomic(page[pages - 1]);
		memset(pageaddr + bytes, 0, PAGE_SIZE - bytes);
		kunmap_atomic(pageaddr);
	}
****

The V2 patch is always reading max_pages, but at the
end of a file the last page may not be a full page.  This
is because the last block may not be complete (i.e. it is
only 126 Kbytes rather than the block_size of 128 Kbytes).

This will leave part of the last page unfilled by the decompressor,
and it should be zero filled, to avoid leaking data to user-space.

Phillip


> Hi Matthew, what do you think? Do you have other comments? If not,
> should I send a v3 to change Xiongwei Song's email address or can you
> help modify it?
> 
> Thanks
> 
>> But, without looking at any trace output, that is just a
>> guestimate.
>>
>> Phillip
>>
>> (*) multiply decompressing the same blocks, which
>>       is the cause of the performance regression.
>>>
>>> Thanks.
>>>
>>> testing env:
>>> - arm64 on kernel 5.10
>>> - data: ~ 300K pack file contains some android files
>>>
>>>>    fs/squashfs/file.c | 77 +++++++++++++++++++++++++++++++++++++++++++++-
>>>>    1 file changed, 76 insertions(+), 1 deletion(-)
>>>>
>>>> diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
>>>> index a8e495d8eb86..e10a55c5b1eb 100644
>>>> --- a/fs/squashfs/file.c
>>>> +++ b/fs/squashfs/file.c
>>>> @@ -39,6 +39,7 @@
>>>>    #include "squashfs_fs_sb.h"
>>>>    #include "squashfs_fs_i.h"
>>>>    #include "squashfs.h"
>>>> +#include "page_actor.h"
>>>>
>>>>    /*
>>>>     * Locate cache slot in range [offset, index] for specified inode.  If
>>>> @@ -495,7 +496,81 @@ static int squashfs_read_folio(struct file *file, struct folio *folio)
>>>>           return 0;
>>>>    }
>>>>
>>>> +static void squashfs_readahead(struct readahead_control *ractl)
>>>> +{
>>>> +       struct inode *inode = ractl->mapping->host;
>>>> +       struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
>>>> +       size_t mask = (1UL << msblk->block_log) - 1;
>>>> +       size_t shift = msblk->block_log - PAGE_SHIFT;
>>>> +       loff_t start = readahead_pos(ractl) &~ mask;
>>>> +       size_t len = readahead_length(ractl) + readahead_pos(ractl) - start;
>>>> +       struct squashfs_page_actor *actor;
>>>> +       unsigned int nr_pages = 0;
>>>> +       struct page **pages;
>>>> +       u64 block = 0;
>>>> +       int bsize, res, i, index;
>>>> +       int file_end = i_size_read(inode) >> msblk->block_log;
>>>> +       unsigned int max_pages = 1UL << shift;
>>>> +
>>>> +       readahead_expand(ractl, start, (len | mask) + 1);
>>>> +
>>>> +       if (file_end == 0)
>>>> +               return;
>>>> +
>>>> +       pages = kmalloc_array(max_pages, sizeof(void *), GFP_KERNEL);
>>>> +       if (!pages)
>>>> +               return;
>>>> +
>>>> +       actor = squashfs_page_actor_init_special(pages, max_pages, 0);
>>>> +       if (!actor)
>>>> +               goto out;
>>>> +
>>>> +       for (;;) {
>>>> +               nr_pages = __readahead_batch(ractl, pages, max_pages);
>>>> +               if (!nr_pages)
>>>> +                       break;
>>>> +
>>>> +               if (readahead_pos(ractl) >= i_size_read(inode) ||
>>>> +                   nr_pages < max_pages)
>>>> +                       goto skip_pages;
>>>> +
>>>> +               index = pages[0]->index >> shift;
>>>> +               if ((pages[nr_pages - 1]->index >> shift) != index)
>>>> +                       goto skip_pages;
>>>> +
>>>> +               bsize = read_blocklist(inode, index, &block);
>>>> +               if (bsize == 0)
>>>> +                       goto skip_pages;
>>>> +
>>>> +               res = squashfs_read_data(inode->i_sb, block, bsize, NULL,
>>>> +                                        actor);
>>>> +
>>>> +               if (res >= 0)
>>>> +                       for (i = 0; i < nr_pages; i++)
>>>> +                               SetPageUptodate(pages[i]);
>>>> +
>>>> +               for (i = 0; i < nr_pages; i++) {
>>>> +                       unlock_page(pages[i]);
>>>> +                       put_page(pages[i]);
>>>> +               }
>>>> +       }
>>>> +
>>>> +       kfree(actor);
>>>> +       kfree(pages);
>>>> +       return;
>>>> +
>>>> +skip_pages:
>>>> +       for (i = 0; i < nr_pages; i++) {
>>>> +               unlock_page(pages[i]);
>>>> +               put_page(pages[i]);
>>>> +       }
>>>> +
>>>> +       kfree(actor);
>>>> +out:
>>>> +       kfree(pages);
>>>> +}
>>>>
>>>>    const struct address_space_operations squashfs_aops = {
>>>> -       .read_folio = squashfs_read_folio
>>>> +       .read_folio = squashfs_read_folio,
>>>> +       .readahead = squashfs_readahead
>>>>    };
>>>> --
>>>> 2.36.0.550.gb090851708-goog
>>>>
>>

Re: [PATCH v2 3/3] squashfs: implement readahead

[Hsin-Yi Wang]

On Sat, May 21, 2022 at 4:22 AM Phillip Lougher <phillip@squashfs.org.uk> wrote:
>
> On 20/05/2022 08:38, Hsin-Yi Wang wrote:
> > On Fri, May 20, 2022 at 11:02 AM Phillip Lougher
> > <phillip@squashfs.org.uk> wrote:
> >>
> >> On 19/05/2022 09:09, Hsin-Yi Wang wrote:
> >>> On Tue, May 17, 2022 at 4:28 PM Hsin-Yi Wang <hsinyi@chromium.org> wrote:
> >>>>
> >>>> Implement readahead callback for squashfs. It will read datablocks
> >>>> which cover pages in readahead request. For a few cases it will
> >>>> not mark page as uptodate, including:
> >>>> - file end is 0.
> >>>> - zero filled blocks.
> >>>> - current batch of pages isn't in the same datablock or not enough in a
> >>>>     datablock.
> >>>> Otherwise pages will be marked as uptodate. The unhandled pages will be
> >>>> updated by readpage later.
> >>>>
> >>>> Suggested-by: Matthew Wilcox <willy@infradead.org>
> >>>> Signed-off-by: Hsin-Yi Wang <hsinyi@chromium.org>
> >>>> Reported-by: Matthew Wilcox <willy@infradead.org>
> >>>> Reported-by: Phillip Lougher <phillip@squashfs.org.uk>
> >>>> Reported-by: Xiongwei Song <sxwjean@gmail.com>
> >>>> ---
> >>>> v1->v2: remove unused check on readahead_expand().
> >>>> v1: https://lore.kernel.org/lkml/20220516105100.1412740-3-hsinyi@chromium.org/
> >>>> ---
> >>>
> >>> Hi Phillip and Matthew,
> >>>
> >>> Regarding the performance issue of this patch, I saw a possible
> >>> performance gain if we only read the first block instead of reading
> >>> until nr_pages == 0.
> >>>
> >>> To be more clear, apply the following diff (Please ignore the skipping
> >>> of nr_pages check first. This is a demonstration of "only read and
> >>> update the first block per readahead call"):
> >>>
> >>> diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
> >>> index aad6823f0615..c52f7c4a7cfe 100644
> >>> --- a/fs/squashfs/file.c
> >>> +++ b/fs/squashfs/file.c
> >>> @@ -524,10 +524,8 @@ static void squashfs_readahead(struct
> >>> readahead_control *ractl)
> >>>           if (!actor)
> >>>                   goto out;
> >>>
> >>> -       for (;;) {
> >>> +       {
> >>>                   nr_pages = __readahead_batch(ractl, pages, max_pages);
> >>> -               if (!nr_pages)
> >>> -                       break;
> >>>
> >>>                   if (readahead_pos(ractl) >= i_size_read(inode) ||
> >>>                       nr_pages < max_pages)
> >>>
> >>>
> >>> All the performance numbers:
> >>> 1. original: 39s
> >>> 2. revert "mm: put readahead pages in cache earlier": 2.8s
> >>> 3. v2 of this patch: 2.7s
> >>> 4. v2 of this patch and apply the diff: 1.8s
> >>>
> >>> In my testing data, normally it reads and updates 1~2 blocks per
> >>> readahead call. The change might not make sense since the performance
> >>> improvement may only happen in certain cases.
> >>> What do you think? Or is the performance of the current patch
> >>> considered reasonable?
> >>
> >> It entirely depends on where the speed improvement comes from.
> >>
> >>   From experience, the speed improvement is probably worthwhile,
> >> and probably isn't gained at the expense of worse performance
> >> on other work-loads.
> >>
> >> But this is a guestimate, based on the fact timings 2 and 3
> >> (2.8s v 2.7s) are almost identical.  Which implies the v2
> >> patch isn't now doing any more work than the previous
> >> baseline before the "mm: put readahead pages in cache earlier"
> >> patch (*).
> >>
> >> As such the speed improvement must be coming from increased
> >> parallelism.  Such as moving from serially reading the
> >> readahead blocks to parallel reading.
> >>
> > Thanks for the idea. I checked this by offlining other cores until
> > only one core exists. Removing loops still results in less time.
> >
> > But after counting the #traces lines in squashfs_read_data():
> > If we remove the for loop (timings 4), the logs are less: 2.3K lines,
> > while v2 (timings 3) has 3.7K (other timings are also around 3.7K), so
> > removing loop doesn't look right.
>
> If a lot less data is being read than the other timings, then this does
> look incorrect.
>
> >
> > I think v2 should be fine considering the slightly to none regression
> > compared to before.
> >
>
> The fact the timings are almost identical implies all that needs
> to be done to remove the performance regression has been done.
>
> There are two things missing from the patch which need to
> be handled.  These are not related to performance but error
> handling and correctness.  So I have waited until now to
> raise it.
>
> If you look at the code for file_direct.c::squashfs_readpage_block()
>
> https://elixir.bootlin.com/linux/latest/source/fs/squashfs/file_direct.c#L93
>
> ****
>         res = squashfs_read_data(inode->i_sb, block, bsize, NULL, actor);
>         if (res < 0)
>                 goto mark_errored;
>
>         if (res != expected) {
>                 res = -EIO;
>                 goto mark_errored;
>         }
> ****
>
> You will see that it checks for two return conditions from
> squashfs_read_data().
>
> If the decompressor returns error, or if the decompressed block
> is different in size to that expected, then this is an error situation
> (e.g. corrupted filesystem), and the read is marked as bad.
>
> The current V2 patch doesn't check that the block decompressed
> to the correct size (res != expected), and this could mean
> filesystem corruption is not detected, which will be an
> error handling regression.
>
Thanks for the review. In v3:

Added the check to see if the returned size is expected too. Since we
didn't mark error pages here (in readahead), if the size wasn't
expected, we just don't mark the page as Uptodate.

> Secondly, if you look at
> https://elixir.bootlin.com/linux/latest/source/fs/squashfs/file_direct.c#L102
>
> ****
>         /* Last page may have trailing bytes not filled */
>         bytes = res % PAGE_SIZE;
>         if (bytes) {
>                 pageaddr = kmap_atomic(page[pages - 1]);
>                 memset(pageaddr + bytes, 0, PAGE_SIZE - bytes);
>                 kunmap_atomic(pageaddr);
>         }
> ****
>
> The V2 patch is always reading max_pages, but at the
> end of a file the last page may not be a full page.  This
> is because the last block may not be complete (i.e. it is
> only 126 Kbytes rather than the block_size of 128 Kbytes).
>
> This will leave part of the last page unfilled by the decompressor,
> and it should be zero filled, to avoid leaking data to user-space.

If the size was expected, further check if it's not a full page. If
so, fill it with zeros at the end.

Performance is the same as v2.


>
> Phillip
>
>
> > Hi Matthew, what do you think? Do you have other comments? If not,
> > should I send a v3 to change Xiongwei Song's email address or can you
> > help modify it?
> >
> > Thanks
> >
> >> But, without looking at any trace output, that is just a
> >> guestimate.
> >>
> >> Phillip
> >>
> >> (*) multiply decompressing the same blocks, which
> >>       is the cause of the performance regression.
> >>>
> >>> Thanks.
> >>>
> >>> testing env:
> >>> - arm64 on kernel 5.10
> >>> - data: ~ 300K pack file contains some android files
> >>>
> >>>>    fs/squashfs/file.c | 77 +++++++++++++++++++++++++++++++++++++++++++++-
> >>>>    1 file changed, 76 insertions(+), 1 deletion(-)
> >>>>
> >>>> diff --git a/fs/squashfs/file.c b/fs/squashfs/file.c
> >>>> index a8e495d8eb86..e10a55c5b1eb 100644
> >>>> --- a/fs/squashfs/file.c
> >>>> +++ b/fs/squashfs/file.c
> >>>> @@ -39,6 +39,7 @@
> >>>>    #include "squashfs_fs_sb.h"
> >>>>    #include "squashfs_fs_i.h"
> >>>>    #include "squashfs.h"
> >>>> +#include "page_actor.h"
> >>>>
> >>>>    /*
> >>>>     * Locate cache slot in range [offset, index] for specified inode.  If
> >>>> @@ -495,7 +496,81 @@ static int squashfs_read_folio(struct file *file, struct folio *folio)
> >>>>           return 0;
> >>>>    }
> >>>>
> >>>> +static void squashfs_readahead(struct readahead_control *ractl)
> >>>> +{
> >>>> +       struct inode *inode = ractl->mapping->host;
> >>>> +       struct squashfs_sb_info *msblk = inode->i_sb->s_fs_info;
> >>>> +       size_t mask = (1UL << msblk->block_log) - 1;
> >>>> +       size_t shift = msblk->block_log - PAGE_SHIFT;
> >>>> +       loff_t start = readahead_pos(ractl) &~ mask;
> >>>> +       size_t len = readahead_length(ractl) + readahead_pos(ractl) - start;
> >>>> +       struct squashfs_page_actor *actor;
> >>>> +       unsigned int nr_pages = 0;
> >>>> +       struct page **pages;
> >>>> +       u64 block = 0;
> >>>> +       int bsize, res, i, index;
> >>>> +       int file_end = i_size_read(inode) >> msblk->block_log;
> >>>> +       unsigned int max_pages = 1UL << shift;
> >>>> +
> >>>> +       readahead_expand(ractl, start, (len | mask) + 1);
> >>>> +
> >>>> +       if (file_end == 0)
> >>>> +               return;
> >>>> +
> >>>> +       pages = kmalloc_array(max_pages, sizeof(void *), GFP_KERNEL);
> >>>> +       if (!pages)
> >>>> +               return;
> >>>> +
> >>>> +       actor = squashfs_page_actor_init_special(pages, max_pages, 0);
> >>>> +       if (!actor)
> >>>> +               goto out;
> >>>> +
> >>>> +       for (;;) {
> >>>> +               nr_pages = __readahead_batch(ractl, pages, max_pages);
> >>>> +               if (!nr_pages)
> >>>> +                       break;
> >>>> +
> >>>> +               if (readahead_pos(ractl) >= i_size_read(inode) ||
> >>>> +                   nr_pages < max_pages)
> >>>> +                       goto skip_pages;
> >>>> +
> >>>> +               index = pages[0]->index >> shift;
> >>>> +               if ((pages[nr_pages - 1]->index >> shift) != index)
> >>>> +                       goto skip_pages;
> >>>> +
> >>>> +               bsize = read_blocklist(inode, index, &block);
> >>>> +               if (bsize == 0)
> >>>> +                       goto skip_pages;
> >>>> +
> >>>> +               res = squashfs_read_data(inode->i_sb, block, bsize, NULL,
> >>>> +                                        actor);
> >>>> +
> >>>> +               if (res >= 0)
> >>>> +                       for (i = 0; i < nr_pages; i++)
> >>>> +                               SetPageUptodate(pages[i]);
> >>>> +
> >>>> +               for (i = 0; i < nr_pages; i++) {
> >>>> +                       unlock_page(pages[i]);
> >>>> +                       put_page(pages[i]);
> >>>> +               }
> >>>> +       }
> >>>> +
> >>>> +       kfree(actor);
> >>>> +       kfree(pages);
> >>>> +       return;
> >>>> +
> >>>> +skip_pages:
> >>>> +       for (i = 0; i < nr_pages; i++) {
> >>>> +               unlock_page(pages[i]);
> >>>> +               put_page(pages[i]);
> >>>> +       }
> >>>> +
> >>>> +       kfree(actor);
> >>>> +out:
> >>>> +       kfree(pages);
> >>>> +}
> >>>>
> >>>>    const struct address_space_operations squashfs_aops = {
> >>>> -       .read_folio = squashfs_read_folio
> >>>> +       .read_folio = squashfs_read_folio,
> >>>> +       .readahead = squashfs_readahead
> >>>>    };
> >>>> --
> >>>> 2.36.0.550.gb090851708-goog
> >>>>
> >>
>