On Tue, 2016-05-24 at 11:49 +0300, Vladimir Davydov wrote:
> Pipes can consume a significant amount of system memory, hence they
> should be accounted to kmemcg.
>
> This patch marks pipe_inode_info and anonymous pipe buffer page
> allocations as __GFP_ACCOUNT so that they would be charged to kmemcg.
> Note, since a pipe buffer page can be "stolen" and get reused for other
> purposes, including mapping to userspace, we clear PageKmemcg thus
> resetting page->_mapcount and uncharge it in anon_pipe_buf_steal, which
> is introduced by this patch.
>
> Signed-off-by: Vladimir Davydov <vdavy...@virtuozzo.com>
> Cc: Alexander Viro <v...@zeniv.linux.org.uk>
> ---
> fs/pipe.c | 32 ++++++++++++++++++++++++++------
> 1 file changed, 26 insertions(+), 6 deletions(-)
>
> diff --git a/fs/pipe.c b/fs/pipe.c
> index 0d3f5165cb0b..4b32928f5426 100644
> --- a/fs/pipe.c
> +++ b/fs/pipe.c
> @@ -21,6 +21,7 @@
> #include <linux/audit.h>
> #include <linux/syscalls.h>
> #include <linux/fcntl.h>
> +#include <linux/memcontrol.h>
>
> #include <asm/uaccess.h>
> #include <asm/ioctls.h>
> @@ -137,6 +138,22 @@ static void anon_pipe_buf_release(struct pipe_inode_info
> *pipe,
> put_page(page);
> }
>
> +static int anon_pipe_buf_steal(struct pipe_inode_info *pipe,
> + struct pipe_buffer *buf)
> +{
> + struct page *page = buf->page;
> +
> + if (page_count(page) == 1) {
This looks racy : some cpu could have temporarily elevated page count.
> + if (memcg_kmem_enabled()) {
> + memcg_kmem_uncharge(page, 0);
> + __ClearPageKmemcg(page);
> + }
> + __SetPageLocked(page);
> + return 0;
> + }
> + return 1;
> +}
> +
