linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Johannes Berg <johannes@sipsolutions.net>
To: Nicolai Stange <nicstange@gmail.com>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: "Paul E.McKenney" <paulmck@linux.vnet.ibm.com>,
	linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH 8/9] debugfs: defer debugfs_fsdata allocation to first usage
Date: Tue, 18 Apr 2017 11:36:44 +0200	[thread overview]
Message-ID: <1492508204.2472.7.camel@sipsolutions.net> (raw)
In-Reply-To: <20170416095137.2784-9-nicstange@gmail.com> (sfid-20170416_115200_841095_0D158B2F)

On Sun, 2017-04-16 at 11:51 +0200, Nicolai Stange wrote:
> 
> +++ b/fs/debugfs/file.c
> @@ -53,6 +53,7 @@ const struct file_operations
> *debugfs_real_fops(const struct file *filp)
>  {
>  	struct debugfs_fsdata *fsd = F_DENTRY(filp)->d_fsdata;
>  
> +	WARN_ON((unsigned long)fsd &
> DEBUGFS_FSDATA_IS_REAL_FOPS_BIT);
>  	return fsd->real_fops;

I'm not a fan of BUG_ON(), but in this case, if you have a completely
bogus pointer here, and then you return fsd->real_fops which will be
even more bogus, and *then* you call a function from within it... that
seems like a recipe for disaster.

So either you could return some valid ops (perhaps
debugfs_noop_file_operations although those don't have .name or .poll,
so it doesn't cover everything), or you can just BUG_ON() here
directly, saving the incomprehensible crash later.

johannes

>  EXPORT_SYMBOL_GPL(debugfs_real_fops);
> @@ -74,9 +75,35 @@ EXPORT_SYMBOL_GPL(debugfs_real_fops);
>   */
>  int debugfs_file_get(struct dentry *dentry)
>  {
> -	struct debugfs_fsdata *fsd = dentry->d_fsdata;
> +	struct debugfs_fsdata *fsd;
> +	void *d_fsd;
> +
> +	d_fsd = READ_ONCE(dentry->d_fsdata);
> +	if (!((unsigned long)d_fsd &
> DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)) {
> +		fsd = d_fsd;
> +	} else {
> +		fsd = kmalloc(sizeof(*fsd), GFP_KERNEL);
> +		if (!fsd)
> +			return -ENOMEM;
> +
> +		fsd->real_fops = (void *)((unsigned long)d_fsd &
> +					~DEBUGFS_FSDATA_IS_REAL_FOPS
> _BIT);
> +		refcount_set(&fsd->active_users, 1);
> +		init_completion(&fsd->active_users_drained);
> +		if (cmpxchg(&dentry->d_fsdata, d_fsd, fsd) != d_fsd)
> {
> +			kfree(fsd);
> +			fsd = READ_ONCE(dentry->d_fsdata);
> +		}
> +	}
>  
> -	/* Avoid starvation of removers. */
> +	/*
> +	 * In case of a successful cmpxchg() above, this check is
> +	 * strictly necessary and must follow it, see the comment in
> +	 * __debugfs_remove_file().
> +	 * OTOH, if the cmpxchg() hasn't been executed or wasn't
> +	 * successful, this serves the purpose of not starving
> +	 * removers.
> +	 */
>  	if (d_unlinked(dentry))
>  		return -EIO;
>  
> @@ -98,7 +125,7 @@ EXPORT_SYMBOL_GPL(debugfs_file_get);
>   */
>  void debugfs_file_put(struct dentry *dentry)
>  {
> -	struct debugfs_fsdata *fsd = dentry->d_fsdata;
> +	struct debugfs_fsdata *fsd = READ_ONCE(dentry->d_fsdata);
>  
>  	if (refcount_dec_and_test(&fsd->active_users))
>  		complete(&fsd->active_users_drained);
> @@ -109,10 +136,11 @@ static int open_proxy_open(struct inode *inode,
> struct file *filp)
>  {
>  	struct dentry *dentry = F_DENTRY(filp);
>  	const struct file_operations *real_fops = NULL;
> -	int r = 0;
> +	int r;
>  
> -	if (debugfs_file_get(dentry))
> -		return -ENOENT;
> +	r = debugfs_file_get(dentry);
> +	if (r)
> +		return r == -EIO ? -ENOENT : r;
>  
>  	real_fops = debugfs_real_fops(filp);
>  	real_fops = fops_get(real_fops);
> @@ -233,10 +261,11 @@ static int full_proxy_open(struct inode *inode,
> struct file *filp)
>  	struct dentry *dentry = F_DENTRY(filp);
>  	const struct file_operations *real_fops = NULL;
>  	struct file_operations *proxy_fops = NULL;
> -	int r = 0;
> +	int r;
>  
> -	if (debugfs_file_get(dentry))
> -		return -ENOENT;
> +	r = debugfs_file_get(dentry);
> +	if (r)
> +		return r == -EIO ? -ENOENT : r;
>  
>  	real_fops = debugfs_real_fops(filp);
>  	real_fops = fops_get(real_fops);
> diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
> index 5550f11d60bd..2360c17ec00a 100644
> --- a/fs/debugfs/inode.c
> +++ b/fs/debugfs/inode.c
> @@ -184,7 +184,10 @@ static const struct super_operations
> debugfs_super_operations = {
>  
>  static void debugfs_release_dentry(struct dentry *dentry)
>  {
> -	kfree(dentry->d_fsdata);
> +	void *fsd = dentry->d_fsdata;
> +
> +	if (!((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT))
> +		kfree(dentry->d_fsdata);
>  }
>  
>  static struct vfsmount *debugfs_automount(struct path *path)
> @@ -346,35 +349,25 @@ static struct dentry
> *__debugfs_create_file(const char *name, umode_t mode,
>  {
>  	struct dentry *dentry;
>  	struct inode *inode;
> -	struct debugfs_fsdata *fsd;
> -
> -	fsd = kmalloc(sizeof(*fsd), GFP_KERNEL);
> -	if (!fsd)
> -		return NULL;
>  
>  	if (!(mode & S_IFMT))
>  		mode |= S_IFREG;
>  	BUG_ON(!S_ISREG(mode));
>  	dentry = start_creating(name, parent);
>  
> -	if (IS_ERR(dentry)) {
> -		kfree(fsd);
> +	if (IS_ERR(dentry))
>  		return NULL;
> -	}
>  
>  	inode = debugfs_get_inode(dentry->d_sb);
> -	if (unlikely(!inode)) {
> -		kfree(fsd);
> +	if (unlikely(!inode))
>  		return failed_creating(dentry);
> -	}
>  
>  	inode->i_mode = mode;
>  	inode->i_private = data;
>  
>  	inode->i_fop = proxy_fops;
> -	fsd->real_fops = real_fops;
> -	refcount_set(&fsd->active_users, 1);
> -	dentry->d_fsdata = fsd;
> +	dentry->d_fsdata = (void *)((unsigned long)real_fops |
> +				DEBUGFS_FSDATA_IS_REAL_FOPS_BIT);
>  
>  	d_instantiate(dentry, inode);
>  	fsnotify_create(d_inode(dentry->d_parent), dentry);
> @@ -637,8 +630,17 @@ static void __debugfs_remove_file(struct dentry
> *dentry, struct dentry *parent)
>  
>  	simple_unlink(d_inode(parent), dentry);
>  	d_delete(dentry);
> -	fsd = dentry->d_fsdata;
> -	init_completion(&fsd->active_users_drained);
> +
> +	/*
> +	 * Paired with the closing smp_mb() implied by a successful
> +	 * cmpxchg() in debugfs_file_get(): either
> +	 * debugfs_file_get() must see a dead dentry or we must see
> a
> +	 * debugfs_fsdata instance at ->d_fsdata here (or both).
> +	 */
> +	smp_mb();
> +	fsd = READ_ONCE(dentry->d_fsdata);
> +	if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT)
> +		return;
>  	if (!refcount_dec_and_test(&fsd->active_users))
>  		wait_for_completion(&fsd->active_users_drained);
>  }
> diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h
> index 0eea99432840..cb1e8139c398 100644
> --- a/fs/debugfs/internal.h
> +++ b/fs/debugfs/internal.h
> @@ -25,4 +25,12 @@ struct debugfs_fsdata {
>  	struct completion active_users_drained;
>  };
>  
> +/*
> + * A dentry's ->d_fsdata either points to the real fops or to a
> + * dynamically allocated debugfs_fsdata instance.
> + * In order to distinguish between these two cases, a real fops
> + * pointer gets its lowest bit set.
> + */
> +#define DEBUGFS_FSDATA_IS_REAL_FOPS_BIT BIT(0)
> +
>  #endif /* _DEBUGFS_INTERNAL_H_ */

  reply	other threads:[~2017-04-18  9:36 UTC|newest]

Thread overview: 43+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-03-23 14:54 deadlock in synchronize_srcu() in debugfs? Johannes Berg
2017-03-23 15:29 ` Johannes Berg
2017-03-24  8:56   ` Johannes Berg
2017-03-24  9:24     ` Johannes Berg
2017-03-24 17:45       ` Paul E. McKenney
2017-03-24 18:51         ` Johannes Berg
2017-03-24 19:33           ` Paul E. McKenney
2017-03-24 20:20             ` Paul E. McKenney
2017-03-27 11:18               ` Johannes Berg
2017-03-23 15:36 ` Nicolai Stange
2017-03-23 15:47   ` Johannes Berg
2017-03-27 11:36   ` Johannes Berg
2017-03-30  7:32     ` Nicolai Stange
2017-03-30  7:55       ` Johannes Berg
2017-03-30 10:27         ` Nicolai Stange
2017-03-30 11:11           ` Johannes Berg
2017-03-31  9:03             ` Nicolai Stange
2017-03-31  9:44               ` Johannes Berg
2017-04-16  9:51               ` [RFC PATCH 0/9] debugfs: per-file removal protection Nicolai Stange
2017-04-16  9:51                 ` [RFC PATCH 1/9] debugfs: add support for more elaborate ->d_fsdata Nicolai Stange
2017-04-16  9:51                 ` [RFC PATCH 2/9] debugfs: implement per-file removal protection Nicolai Stange
2017-04-18  2:23                   ` [lkp-robot] [debugfs] f3e7155d08: BUG:unable_to_handle_kernel kernel test robot
2017-04-23 18:37                     ` Nicolai Stange
2017-04-24  6:36                       ` Ye Xiaolong
2017-04-16  9:51                 ` [RFC PATCH 3/9] debugfs: debugfs_real_fops(): drop __must_hold sparse annotation Nicolai Stange
2017-04-16  9:51                 ` [RFC PATCH 4/9] debugfs: convert to debugfs_file_get() and -put() Nicolai Stange
2017-04-16  9:51                 ` [RFC PATCH 5/9] IB/hfi1: " Nicolai Stange
2017-04-16  9:51                 ` [RFC PATCH 6/9] debugfs: purge obsolete SRCU based removal protection Nicolai Stange
2017-04-16  9:51                 ` [RFC PATCH 7/9] debugfs: call debugfs_real_fops() only after debugfs_file_get() Nicolai Stange
2017-04-16  9:51                 ` [RFC PATCH 8/9] debugfs: defer debugfs_fsdata allocation to first usage Nicolai Stange
2017-04-18  9:36                   ` Johannes Berg [this message]
2017-05-02 20:05                     ` Nicolai Stange
2017-05-03  5:43                       ` Johannes Berg
2017-04-16  9:51                 ` [RFC PATCH 9/9] debugfs: free debugfs_fsdata instances Nicolai Stange
2017-04-17 16:01                   ` Paul E. McKenney
2017-04-18  9:39                     ` Johannes Berg
2017-04-18 13:31                       ` Paul E. McKenney
2017-04-18 13:40                         ` Johannes Berg
2017-04-18 15:17                           ` Paul E. McKenney
2017-04-18 15:20                             ` Johannes Berg
2017-04-18 17:19                               ` Paul E. McKenney
2017-03-23 15:37 ` deadlock in synchronize_srcu() in debugfs? Paul E. McKenney
2017-03-23 15:46   ` Johannes Berg

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=1492508204.2472.7.camel@sipsolutions.net \
    --to=johannes@sipsolutions.net \
    --cc=gregkh@linuxfoundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nicstange@gmail.com \
    --cc=paulmck@linux.vnet.ibm.com \
    /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).