| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 14 Aug 2014 14:22:25 -0700
From: Andrew Morton <akpm@...ux-foundation.org>
To: Gioh Kim <gioh.kim@....com>
Cc: Alexander Viro <viro@...iv.linux.org.uk>,
"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
Peter Zijlstra <peterz@...radead.org>, Jan Kara <jack@...e.cz>,
linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
"Theodore Ts'o" <tytso@....edu>,
Andreas Dilger <adilger.kernel@...ger.ca>,
linux-ext4@...r.kernel.org, Minchan Kim <minchan@...nel.org>,
Joonsoo Kim <js1304@...il.com>,
이건호
<gunho.lee@....com>
Subject: Re: [PATCH 1/2] fs/buffer.c: allocate buffer cache from non-movable
area
On Thu, 14 Aug 2014 14:15:40 +0900 Gioh Kim <gioh.kim@....com> wrote:
> A buffer cache is allocated from movable area
> because it is referred for a while and released soon.
> But some filesystems are taking buffer cache for a long time
> and it can disturb page migration.
>
> A new API should be introduced to allocate buffer cache from
> non-movable area.
I think the API could and should be more flexible than this.
Rather than making the API be "movable or not movable", let's permit
callers to specify the gfp_t and leave it at that. That way, if
someone later wants to allocate a buffer head with, I dunno,
__GFP_NOTRACK then they can do so.
So the word "movable" shouldn't appear in buffer.c at all, except in a
single place.
> --- a/fs/buffer.c
> +++ b/fs/buffer.c
> @@ -993,7 +993,7 @@ init_page_buffers(struct page *page, struct block_device *bdev,
> */
> static int
> grow_dev_page(struct block_device *bdev, sector_t block,
> - pgoff_t index, int size, int sizebits)
> + pgoff_t index, int size, int sizebits, gfp_t movable_mask)
s/movable_mask/gfp/
> {
> struct inode *inode = bdev->bd_inode;
> struct page *page;
> @@ -1003,7 +1003,8 @@ grow_dev_page(struct block_device *bdev, sector_t block,
> gfp_t gfp_mask;
>
> gfp_mask = mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS;
> - gfp_mask |= __GFP_MOVABLE;
> + if (movable_mask & __GFP_MOVABLE)
> + gfp_mask |= __GFP_MOVABLE;
This becomes
gfp_mask |= gfp;
> /*
> * XXX: __getblk_slow() can not really deal with failure and
> * will endlessly loop on improvised global reclaim. Prefer
> @@ -1058,7 +1059,8 @@ failed:
> * that page was dirty, the buffers are set dirty also.
> */
> static int
> -grow_buffers(struct block_device *bdev, sector_t block, int size)
> +grow_buffers(struct block_device *bdev, sector_t block,
> + int size, gfp_t movable_mask)
gfp
> {
> pgoff_t index;
> int sizebits;
> @@ -1085,11 +1087,12 @@ grow_buffers(struct block_device *bdev, sector_t block, int size)
> }
>
> /* Create a page with the proper size buffers.. */
> - return grow_dev_page(bdev, block, index, size, sizebits);
> + return grow_dev_page(bdev, block, index, size, sizebits, movable_mask);
> }
>
> static struct buffer_head *
> -__getblk_slow(struct block_device *bdev, sector_t block, int size)
> +__getblk_slow(struct block_device *bdev, sector_t block,
> + int size, gfp_t movable_mask)
gfp
> {
> /* Size must be multiple of hard sectorsize */
> if (unlikely(size & (bdev_logical_block_size(bdev)-1) ||
> @@ -1111,7 +1114,7 @@ __getblk_slow(struct block_device *bdev, sector_t block, int size)
> if (bh)
> return bh;
>
> - ret = grow_buffers(bdev, block, size);
> + ret = grow_buffers(bdev, block, size, movable_mask);
gfp
> if (ret < 0)
> return NULL;
> if (ret == 0)
> @@ -1385,11 +1388,34 @@ __getblk(struct block_device *bdev, sector_t block, unsigned size)
>
> might_sleep();
> if (bh == NULL)
> - bh = __getblk_slow(bdev, block, size);
> + bh = __getblk_slow(bdev, block, size, __GFP_MOVABLE);
Here is the place where buffer.c. mentions "movable".
> return bh;
> }
> EXPORT_SYMBOL(__getblk);
>
> + /*
> + * __getblk_nonmovable will locate (and, if necessary, create) the buffer_head
> + * which corresponds to the passed block_device, block and size. The
> + * returned buffer has its reference count incremented.
> + *
> + * The page cache is allocated from non-movable area
> + * not to prevent page migration.
> + *
> + * __getblk()_nonmovable will lock up the machine
> + * if grow_dev_page's try_to_free_buffers() attempt is failing. FIXME, perhaps?
> + */
> +struct buffer_head *
> +__getblk_nonmovable(struct block_device *bdev, sector_t block, unsigned size)
> +{
> + struct buffer_head *bh = __find_get_block(bdev, block, size);
> +
> + might_sleep();
> + if (bh == NULL)
> + bh = __getblk_slow(bdev, block, size, 0);
> + return bh;
> +}
> +EXPORT_SYMBOL(__getblk_nonmovable);
Suggest this be called __getblk_gfp(bdev, block, size, gfp) and then
__getblk() be changed to call __getblk_gfp(..., __GFP_MOVABLE).
We could then write a __getblk_nonmovable() which calls __getblk_gfp()
(a static inlined one-line function) or we can just call
__getblk_gfp(..., 0) directly from filesystems.
> @@ -1423,6 +1450,28 @@ __bread(struct block_device *bdev, sector_t block, unsigned size)
> }
> EXPORT_SYMBOL(__bread);
>
> +/**
> + * __bread_nonmovable() - reads a specified block and returns the bh
> + * @bdev: the block_device to read from
> + * @block: number of block
> + * @size: size (in bytes) to read
> + *
> + * Reads a specified block, and returns buffer head that contains it.
> + * The page cache is allocated from non-movable area
> + * not to prevent page migration.
> + * It returns NULL if the block was unreadable.
> + */
> +struct buffer_head *
> +__bread_nonmovable(struct block_device *bdev, sector_t block, unsigned size)
> +{
> + struct buffer_head *bh = __getblk_slow(bdev, block, size, 0);
> +
> + if (likely(bh) && !buffer_uptodate(bh))
> + bh = __bread_slow(bh);
> + return bh;
> +}
> +EXPORT_SYMBOL(__bread_nonmovable);
Treat this in the same fashion as __getblk_nonmovable().
--
To unsubscribe from this list: send the line "unsubscribe linux-ext4" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists