linux-fsdevel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: Dave Chinner <david@fromorbit.com>
Cc: viro@ZenIV.linux.org.uk, linux-fsdevel@vger.kernel.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 3/3] fs: rcu protect inode hash lookups
Date: Tue, 16 Nov 2010 15:56:42 -0800	[thread overview]
Message-ID: <20101116235642.GM2503@linux.vnet.ibm.com> (raw)
In-Reply-To: <1288589624-15251-4-git-send-email-david@fromorbit.com>

On Mon, Nov 01, 2010 at 04:33:44PM +1100, Dave Chinner wrote:
> From: Dave Chinner <dchinner@redhat.com>
> 
> Now that inodes are using RCU freeing, we can walk the hash lists
> using RCU protection during lookups. Convert all the hash list
> operations to use RCU-based operators and drop the inode_hash_lock
> around pure lookup operations.
> 
> Signed-off-by: Dave Chinner <dchinner@redhat.com>
> ---
>  fs/inode.c |   89 ++++++++++++++++++++++++++++++++++++++---------------------
>  1 files changed, 57 insertions(+), 32 deletions(-)
> 
> diff --git a/fs/inode.c b/fs/inode.c
> index 106ec7a..6bead3d 100644
> --- a/fs/inode.c
> +++ b/fs/inode.c
> @@ -50,11 +50,12 @@
>   *   inode->i_lock
>   *
>   * inode_hash_lock
> - *   inode_sb_list_lock
> - *   inode->i_lock
> + *   rcu_read_lock
> + *     inode_sb_list_lock
> + *     inode->i_lock
>   *
>   * iunique_lock
> - *   inode_hash_lock
> + *   rcu_read_lock
>   */
> 
>  /*
> @@ -413,7 +414,7 @@ void __insert_inode_hash(struct inode *inode, unsigned long hashval)
> 
>  	spin_lock(&inode_hash_lock);
>  	spin_lock(&inode->i_lock);
> -	hlist_add_head(&inode->i_hash, b);
> +	hlist_add_head_rcu(&inode->i_hash, b);
>  	spin_unlock(&inode->i_lock);
>  	spin_unlock(&inode_hash_lock);
>  }
> @@ -429,7 +430,7 @@ void remove_inode_hash(struct inode *inode)
>  {
>  	spin_lock(&inode_hash_lock);
>  	spin_lock(&inode->i_lock);
> -	hlist_del_init(&inode->i_hash);
> +	hlist_del_init_rcu(&inode->i_hash);
>  	spin_unlock(&inode->i_lock);
>  	spin_unlock(&inode_hash_lock);
>  }
> @@ -741,26 +742,38 @@ static void __wait_on_freeing_inode(struct inode *inode);
>  static struct inode *find_inode(struct super_block *sb,
>  				struct hlist_head *head,
>  				int (*test)(struct inode *, void *),
> -				void *data)
> +				void *data, bool locked)
>  {
>  	struct hlist_node *node;
>  	struct inode *inode = NULL;
> 
>  repeat:
> +	rcu_read_lock();
>  	hlist_for_each_entry(inode, node, head, i_hash) {

The above needs to be hlist_for_each_entry_rcu(), correct?

This is needed even in the SLAB_DESTROY_BY_RCU case, because you
are still inserting elements into this list concurrently with
readers traversing it.

That said, this seems to be replaced by hlist_bl_for_each_entry()
in your git tree with the caller doing hlist_bl_lock(), though it is
entirely possible that I am looking at the wrong branch.  I feel
slow and late to the party...  ;-)

							Thanx, Paul

>  		if (inode->i_sb != sb)
>  			continue;
>  		if (!test(inode, data))
>  			continue;
>  		spin_lock(&inode->i_lock);
> +		if (inode_unhashed(inode)) {
> +			spin_unlock(&inode->i_lock);
> +			continue;
> +		}
>  		if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
> +			rcu_read_unlock();
> +			if (locked)
> +				spin_unlock(&inode_hash_lock);
>  			__wait_on_freeing_inode(inode);
> +			if (locked)
> +				spin_lock(&inode_hash_lock);
>  			goto repeat;
>  		}
>  		__iget(inode);
>  		spin_unlock(&inode->i_lock);
> +		rcu_read_unlock();
>  		return inode;
>  	}
> +	rcu_read_unlock();
>  	return NULL;
>  }
> 
> @@ -769,26 +782,39 @@ repeat:
>   * iget_locked for details.
>   */
>  static struct inode *find_inode_fast(struct super_block *sb,
> -				struct hlist_head *head, unsigned long ino)
> +				struct hlist_head *head, unsigned long ino,
> +				bool locked)
>  {
>  	struct hlist_node *node;
>  	struct inode *inode = NULL;
> 
>  repeat:
> +	rcu_read_lock();
>  	hlist_for_each_entry(inode, node, head, i_hash) {
>  		if (inode->i_ino != ino)
>  			continue;
>  		if (inode->i_sb != sb)
>  			continue;
>  		spin_lock(&inode->i_lock);
> +		if (inode_unhashed(inode)) {
> +			spin_unlock(&inode->i_lock);
> +			continue;
> +		}
>  		if (inode->i_state & (I_FREEING|I_WILL_FREE)) {
> +			rcu_read_unlock();
> +			if (locked)
> +				spin_unlock(&inode_hash_lock);
>  			__wait_on_freeing_inode(inode);
> +			if (locked)
> +				spin_lock(&inode_hash_lock);
>  			goto repeat;
>  		}
>  		__iget(inode);
>  		spin_unlock(&inode->i_lock);
> +		rcu_read_unlock();
>  		return inode;
>  	}
> +	rcu_read_unlock();
>  	return NULL;
>  }
> 
> @@ -913,14 +939,14 @@ static struct inode *get_new_inode(struct super_block *sb,
> 
>  		spin_lock(&inode_hash_lock);
>  		/* We released the lock, so.. */
> -		old = find_inode(sb, head, test, data);
> +		old = find_inode(sb, head, test, data, true);
>  		if (!old) {
>  			if (set(inode, data))
>  				goto set_failed;
> 
>  			spin_lock(&inode->i_lock);
>  			inode->i_state = I_NEW;
> -			hlist_add_head(&inode->i_hash, head);
> +			hlist_add_head_rcu(&inode->i_hash, head);
>  			spin_unlock(&inode->i_lock);
>  			inode_sb_list_add(inode);
>  			spin_unlock(&inode_hash_lock);
> @@ -964,12 +990,12 @@ static struct inode *get_new_inode_fast(struct super_block *sb,
> 
>  		spin_lock(&inode_hash_lock);
>  		/* We released the lock, so.. */
> -		old = find_inode_fast(sb, head, ino);
> +		old = find_inode_fast(sb, head, ino, true);
>  		if (!old) {
>  			inode->i_ino = ino;
>  			spin_lock(&inode->i_lock);
>  			inode->i_state = I_NEW;
> -			hlist_add_head(&inode->i_hash, head);
> +			hlist_add_head_rcu(&inode->i_hash, head);
>  			spin_unlock(&inode->i_lock);
>  			inode_sb_list_add(inode);
>  			spin_unlock(&inode_hash_lock);
> @@ -1006,15 +1032,22 @@ static int test_inode_iunique(struct super_block *sb, unsigned long ino)
>  	struct hlist_node *node;
>  	struct inode *inode;
> 
> -	spin_lock(&inode_hash_lock);
> -	hlist_for_each_entry(inode, node, b, i_hash) {
> -		if (inode->i_ino == ino && inode->i_sb == sb) {
> -			spin_unlock(&inode_hash_lock);
> -			return 0;
> +	rcu_read_lock();
> +	hlist_for_each_entry_rcu(inode, node, b, i_hash) {
> +		if (inode->i_ino != ino)
> +			continue;
> +		if (inode->i_sb != sb)
> +			continue;
> +		spin_lock(&inode->i_lock);
> +		if (inode_unhashed(inode)) {
> +			spin_unlock(&inode->i_lock);
> +			continue;
>  		}
> +		spin_unlock(&inode->i_lock);
> +		rcu_read_unlock();
> +		return 0;
>  	}
> -	spin_unlock(&inode_hash_lock);
> -
> +	rcu_read_unlock();
>  	return 1;
>  }
> 
> @@ -1099,15 +1132,12 @@ static struct inode *ifind(struct super_block *sb,
>  {
>  	struct inode *inode;
> 
> -	spin_lock(&inode_hash_lock);
> -	inode = find_inode(sb, head, test, data);
> +	inode = find_inode(sb, head, test, data, false);
>  	if (inode) {
> -		spin_unlock(&inode_hash_lock);
>  		if (likely(wait))
>  			wait_on_inode(inode);
>  		return inode;
>  	}
> -	spin_unlock(&inode_hash_lock);
>  	return NULL;
>  }
> 
> @@ -1131,14 +1161,11 @@ static struct inode *ifind_fast(struct super_block *sb,
>  {
>  	struct inode *inode;
> 
> -	spin_lock(&inode_hash_lock);
> -	inode = find_inode_fast(sb, head, ino);
> +	inode = find_inode_fast(sb, head, ino, false);
>  	if (inode) {
> -		spin_unlock(&inode_hash_lock);
>  		wait_on_inode(inode);
>  		return inode;
>  	}
> -	spin_unlock(&inode_hash_lock);
>  	return NULL;
>  }
> 
> @@ -1301,7 +1328,7 @@ int insert_inode_locked(struct inode *inode)
>  		struct hlist_node *node;
>  		struct inode *old = NULL;
>  		spin_lock(&inode_hash_lock);
> -		hlist_for_each_entry(old, node, head, i_hash) {
> +		hlist_for_each_entry_rcu(old, node, head, i_hash) {
>  			if (old->i_ino != ino)
>  				continue;
>  			if (old->i_sb != sb)
> @@ -1316,7 +1343,7 @@ int insert_inode_locked(struct inode *inode)
>  		if (likely(!node)) {
>  			spin_lock(&inode->i_lock);
>  			inode->i_state |= I_NEW;
> -			hlist_add_head(&inode->i_hash, head);
> +			hlist_add_head_rcu(&inode->i_hash, head);
>  			spin_unlock(&inode->i_lock);
>  			spin_unlock(&inode_hash_lock);
>  			return 0;
> @@ -1345,7 +1372,7 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
>  		struct inode *old = NULL;
> 
>  		spin_lock(&inode_hash_lock);
> -		hlist_for_each_entry(old, node, head, i_hash) {
> +		hlist_for_each_entry_rcu(old, node, head, i_hash) {
>  			if (old->i_sb != sb)
>  				continue;
>  			if (!test(old, data))
> @@ -1360,7 +1387,7 @@ int insert_inode_locked4(struct inode *inode, unsigned long hashval,
>  		if (likely(!node)) {
>  			spin_lock(&inode->i_lock);
>  			inode->i_state |= I_NEW;
> -			hlist_add_head(&inode->i_hash, head);
> +			hlist_add_head_rcu(&inode->i_hash, head);
>  			spin_unlock(&inode->i_lock);
>  			spin_unlock(&inode_hash_lock);
>  			return 0;
> @@ -1646,10 +1673,8 @@ static void __wait_on_freeing_inode(struct inode *inode)
>  	wq = bit_waitqueue(&inode->i_state, __I_NEW);
>  	prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
>  	spin_unlock(&inode->i_lock);
> -	spin_unlock(&inode_hash_lock);
>  	schedule();
>  	finish_wait(wq, &wait.wait);
> -	spin_lock(&inode_hash_lock);
>  }
> 
>  static __initdata unsigned long ihash_entries;
> -- 
> 1.7.1
> 
> --
> To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
> Please read the FAQ at  http://www.tux.org/lkml/

      parent reply	other threads:[~2010-11-16 23:56 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-11-01  5:33 fs: inode freeing and hash lookup via RCU Dave Chinner
2010-11-01  5:33 ` [PATCH 1/3] fs: pull inode->i_lock up out of writeback_single_inode Dave Chinner
2010-11-01  5:33 ` [PATCH 2/3] fs: Use RCU freeing of inodes via SLAB_DESTROY_BY_RCU Dave Chinner
2010-11-01 15:31   ` Christoph Hellwig
2010-11-01  5:33 ` [PATCH 3/3] fs: rcu protect inode hash lookups Dave Chinner
2010-11-01  9:38   ` Eric Dumazet
2010-11-01 13:44     ` Dave Chinner
2010-11-01 15:29       ` Eric Dumazet
2010-11-02  0:01         ` Dave Chinner
2010-11-02  4:46           ` Eric Dumazet
2010-11-02 12:11           ` Paul E. McKenney
2010-11-16 23:56   ` Paul E. McKenney [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20101116235642.GM2503@linux.vnet.ibm.com \
    --to=paulmck@linux.vnet.ibm.com \
    --cc=david@fromorbit.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=viro@ZenIV.linux.org.uk \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).