linux-kernel - Re: [PATCH v2 1/5] mm/swapfile: add percpu

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
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <87eef7kmzw.fsf@yhuang6-desk1.ccr.corp.intel.com>
Date:   Mon, 19 Apr 2021 10:48:51 +0800
From:   "Huang, Ying" <ying.huang@...el.com>
To:     Miaohe Lin <linmiaohe@...wei.com>
Cc:     <akpm@...ux-foundation.org>, <dennis@...nel.org>,
        <tim.c.chen@...ux.intel.com>, <hughd@...gle.com>,
        <hannes@...xchg.org>, <mhocko@...e.com>, <iamjoonsoo.kim@....com>,
        <alexs@...nel.org>, <david@...hat.com>, <minchan@...nel.org>,
        <richard.weiyang@...il.com>, <linux-kernel@...r.kernel.org>,
        <linux-mm@...ck.org>
Subject: Re: [PATCH v2 1/5] mm/swapfile: add percpu_ref support for swap

Miaohe Lin <linmiaohe@...wei.com> writes:

> We will use percpu-refcount to serialize against concurrent swapoff. This
> patch adds the percpu_ref support for swap.
>
> Signed-off-by: Miaohe Lin <linmiaohe@...wei.com>
> ---
>  include/linux/swap.h |  3 +++
>  mm/swapfile.c        | 33 +++++++++++++++++++++++++++++----
>  2 files changed, 32 insertions(+), 4 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 144727041e78..8be36eb58b7a 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -240,6 +240,7 @@ struct swap_cluster_list {
>   * The in-memory structure used to track swap areas.
>   */
>  struct swap_info_struct {
> +	struct percpu_ref users;	/* serialization against concurrent swapoff */

The comments aren't general enough.  We use this to check whether the
swap device has been fully initialized, etc. May be something as below?

/* indicate and keep swap device valid */

>  	unsigned long	flags;		/* SWP_USED etc: see above */
>  	signed short	prio;		/* swap priority of this type */
>  	struct plist_node list;		/* entry in swap_active_head */
> @@ -260,6 +261,8 @@ struct swap_info_struct {
>  	struct block_device *bdev;	/* swap device or bdev of swap file */
>  	struct file *swap_file;		/* seldom referenced */
>  	unsigned int old_block_size;	/* seldom referenced */
> +	bool ref_initialized;		/* seldom referenced */
> +	struct completion comp;		/* seldom referenced */
>  #ifdef CONFIG_FRONTSWAP
>  	unsigned long *frontswap_map;	/* frontswap in-use, one bit per page */
>  	atomic_t frontswap_pages;	/* frontswap pages in-use counter */
> diff --git a/mm/swapfile.c b/mm/swapfile.c
> index 149e77454e3c..66515a3a2824 100644
> --- a/mm/swapfile.c
> +++ b/mm/swapfile.c
> @@ -39,6 +39,7 @@
>  #include <linux/export.h>
>  #include <linux/swap_slots.h>
>  #include <linux/sort.h>
> +#include <linux/completion.h>
>  
>  #include <asm/tlbflush.h>
>  #include <linux/swapops.h>
> @@ -511,6 +512,14 @@ static void swap_discard_work(struct work_struct *work)
>  	spin_unlock(&si->lock);
>  }
>  
> +static void swap_users_ref_free(struct percpu_ref *ref)
> +{
> +	struct swap_info_struct *si;
> +
> +	si = container_of(ref, struct swap_info_struct, users);
> +	complete(&si->comp);
> +}
> +
>  static void alloc_cluster(struct swap_info_struct *si, unsigned long idx)
>  {
>  	struct swap_cluster_info *ci = si->cluster_info;
> @@ -2500,7 +2509,7 @@ static void enable_swap_info(struct swap_info_struct *p, int prio,
>  	 * Guarantee swap_map, cluster_info, etc. fields are valid
>  	 * between get/put_swap_device() if SWP_VALID bit is set
>  	 */
> -	synchronize_rcu();

You cannot remove this without changing get/put_swap_device().  It's
better to squash at least PATCH 1-2.

> +	percpu_ref_resurrect(&p->users);
>  	spin_lock(&swap_lock);
>  	spin_lock(&p->lock);
>  	_enable_swap_info(p);
> @@ -2621,11 +2630,18 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
>  	p->flags &= ~SWP_VALID;		/* mark swap device as invalid */
>  	spin_unlock(&p->lock);
>  	spin_unlock(&swap_lock);
> +
> +	percpu_ref_kill(&p->users);
>  	/*
> -	 * wait for swap operations protected by get/put_swap_device()
> -	 * to complete
> +	 * We need synchronize_rcu() here to protect the accessing
> +	 * to the swap cache data structure.
>  	 */
>  	synchronize_rcu();
> +	/*
> +	 * Wait for swap operations protected by get/put_swap_device()
> +	 * to complete.
> +	 */

I think the comments (after some revision) can be moved before
percpu_ref_kill().  The synchronize_rcu() comments can be merged.

> +	wait_for_completion(&p->comp);
>  
>  	flush_work(&p->discard_work);
>  
> @@ -3132,7 +3148,7 @@ static bool swap_discardable(struct swap_info_struct *si)
>  SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
>  {
>  	struct swap_info_struct *p;
> -	struct filename *name;
> +	struct filename *name = NULL;
>  	struct file *swap_file = NULL;
>  	struct address_space *mapping;
>  	int prio;
> @@ -3163,6 +3179,15 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
>  
>  	INIT_WORK(&p->discard_work, swap_discard_work);
>  
> +	if (!p->ref_initialized) {

I don't think it's necessary to add another flag p->ref_initialized.  We
can distinguish newly allocated and reused swap_info_struct in alloc_swap_info().

Best Regards,
Huang, Ying

> +		error = percpu_ref_init(&p->users, swap_users_ref_free,
> +					PERCPU_REF_INIT_DEAD, GFP_KERNEL);
> +		if (unlikely(error))
> +			goto bad_swap;
> +		init_completion(&p->comp);
> +		p->ref_initialized = true;
> +	}
> +
>  	name = getname(specialfile);
>  	if (IS_ERR(name)) {
>  		error = PTR_ERR(name);