Re: [PATCH v11 4/4] xfs: replace mrlock_t with rw_semaphores

[Brian Foster <bfoster@redhat.com>]

On Fri, Oct 09, 2020 at 09:55:15PM +0200, Pavel Reichl wrote:
> Remove mrlock_t as it does not provide any extra value over
> rw_semaphores. Make i_lock and i_mmaplock native rw_semaphores and
> replace mr*() functions with native rwsem calls.
> 
> Release the lock in xfs_btree_split() just before the work-queue
> executing xfs_btree_split_worker() is scheduled and make
> xfs_btree_split_worker() to acquire the lock as a first thing and
> release it just before returning from the function. This it done so the
> ownership of the lock is transfered between kernel threads and thus
> lockdep won't complain about lock being held by a different kernel
> thread.
> 
> Signed-off-by: Pavel Reichl <preichl@redhat.com>
> ---
>  fs/xfs/libxfs/xfs_btree.c | 24 ++++++++++++
>  fs/xfs/mrlock.h           | 78 ---------------------------------------
>  fs/xfs/xfs_inode.c        | 50 +++++++++++++------------
>  fs/xfs/xfs_inode.h        |  4 +-
>  fs/xfs/xfs_iops.c         |  4 +-
>  fs/xfs/xfs_linux.h        |  2 +-
>  fs/xfs/xfs_super.c        |  6 +--
>  7 files changed, 57 insertions(+), 111 deletions(-)
>  delete mode 100644 fs/xfs/mrlock.h
> 
> diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
> index 2d25bab68764..d1fdb180f7ae 100644
> --- a/fs/xfs/libxfs/xfs_btree.c
> +++ b/fs/xfs/libxfs/xfs_btree.c
...
> @@ -2863,8 +2875,20 @@ xfs_btree_split(
>  	args.done = &done;
>  	args.kswapd = current_is_kswapd();
>  	INIT_WORK_ONSTACK(&args.work, xfs_btree_split_worker);
> +	/*
> +	 * Update lockdep's ownership information to reflect that we
> +	 * will be transferring the ilock from this thread to the
> +	 * worker.
> +	 */

Can we update this comment to explain why we need to do this? E.g., I'm
assuming there's a lockdep splat somewhere down in the split worker
without it, but it's not immediately clear where and so it might not be
obvious if we're ever able to remove this.

> +	rwsem_release(&cur->bc_ino.ip->i_lock.dep_map, _THIS_IP_);
>  	queue_work(xfs_alloc_wq, &args.work);
>  	wait_for_completion(&done);
> +	/*
> +	 * Update lockdep's lock ownership information to point to
> +	 * this thread as the lock owner now that the worker item is
> +	 * done.
> +	 */
> +	rwsem_acquire(&cur->bc_ino.ip->i_lock.dep_map, 0, 0, _RET_IP_);
>  	destroy_work_on_stack(&args.work);
>  	return args.result;
>  }
...
> diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
> index a3baec1c5bcf..213a4a947854 100644
> --- a/fs/xfs/xfs_inode.c
> +++ b/fs/xfs/xfs_inode.c
...
> @@ -384,16 +385,17 @@ xfs_isilocked(
>  	struct xfs_inode	*ip,
>  	uint			lock_flags)
>  {
> -	if (lock_flags & (XFS_ILOCK_EXCL|XFS_ILOCK_SHARED)) {
> -		if (!(lock_flags & XFS_ILOCK_SHARED))
> -			return !!ip->i_lock.mr_writer;
> -		return rwsem_is_locked(&ip->i_lock.mr_lock);
> +	if (lock_flags & (XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)) {
> +		ASSERT(!(lock_flags & ~(XFS_ILOCK_EXCL | XFS_ILOCK_SHARED)));
> +		return __xfs_rwsem_islocked(&ip->i_lock,
> +				(lock_flags >> XFS_ILOCK_FLAG_SHIFT));
>  	}
>  
> -	if (lock_flags & (XFS_MMAPLOCK_EXCL|XFS_MMAPLOCK_SHARED)) {
> -		if (!(lock_flags & XFS_MMAPLOCK_SHARED))
> -			return !!ip->i_mmaplock.mr_writer;
> -		return rwsem_is_locked(&ip->i_mmaplock.mr_lock);
> +	if (lock_flags & (XFS_MMAPLOCK_EXCL | XFS_MMAPLOCK_SHARED)) {
> +		ASSERT(!(lock_flags &
> +			~(XFS_MMAPLOCK_EXCL | XFS_MMAPLOCK_SHARED)));
> +		return __xfs_rwsem_islocked(&ip->i_mmaplock,
> +				(lock_flags >> XFS_MMAPLOCK_FLAG_SHIFT));
>  	}
>  
>  	if (lock_flags & (XFS_IOLOCK_EXCL | XFS_IOLOCK_SHARED)) {

Can we add a similar assert for this case as we have for the others?
Otherwise the rest looks fairly straightforward to me.

Brian

> diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
> index 77776af75c77..896a088989f2 100644
> --- a/fs/xfs/xfs_inode.h
> +++ b/fs/xfs/xfs_inode.h
> @@ -39,8 +39,8 @@ typedef struct xfs_inode {
>  
>  	/* Transaction and locking information. */
>  	struct xfs_inode_log_item *i_itemp;	/* logging information */
> -	mrlock_t		i_lock;		/* inode lock */
> -	mrlock_t		i_mmaplock;	/* inode mmap IO lock */
> +	struct rw_semaphore	i_lock;		/* inode lock */
> +	struct rw_semaphore	i_mmaplock;	/* inode mmap IO lock */
>  	atomic_t		i_pincount;	/* inode pin count */
>  
>  	/*
> diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
> index 80a13c8561d8..66cca3e599c7 100644
> --- a/fs/xfs/xfs_iops.c
> +++ b/fs/xfs/xfs_iops.c
> @@ -1336,9 +1336,9 @@ xfs_setup_inode(
>  		 */
>  		lockdep_set_class(&inode->i_rwsem,
>  				  &inode->i_sb->s_type->i_mutex_dir_key);
> -		lockdep_set_class(&ip->i_lock.mr_lock, &xfs_dir_ilock_class);
> +		lockdep_set_class(&ip->i_lock, &xfs_dir_ilock_class);
>  	} else {
> -		lockdep_set_class(&ip->i_lock.mr_lock, &xfs_nondir_ilock_class);
> +		lockdep_set_class(&ip->i_lock, &xfs_nondir_ilock_class);
>  	}
>  
>  	/*
> diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
> index ab737fed7b12..ba37217f86d2 100644
> --- a/fs/xfs/xfs_linux.h
> +++ b/fs/xfs/xfs_linux.h
> @@ -22,7 +22,6 @@ typedef __u32			xfs_nlink_t;
>  #include "xfs_types.h"
>  
>  #include "kmem.h"
> -#include "mrlock.h"
>  
>  #include <linux/semaphore.h>
>  #include <linux/mm.h>
> @@ -61,6 +60,7 @@ typedef __u32			xfs_nlink_t;
>  #include <linux/ratelimit.h>
>  #include <linux/rhashtable.h>
>  #include <linux/xattr.h>
> +#include <linux/rwsem.h>
>  
>  #include <asm/page.h>
>  #include <asm/div64.h>
> diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
> index 71ac6c1cdc36..00be9cfa29fa 100644
> --- a/fs/xfs/xfs_super.c
> +++ b/fs/xfs/xfs_super.c
> @@ -708,10 +708,8 @@ xfs_fs_inode_init_once(
>  	atomic_set(&ip->i_pincount, 0);
>  	spin_lock_init(&ip->i_flags_lock);
>  
> -	mrlock_init(&ip->i_mmaplock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
> -		     "xfsino", ip->i_ino);
> -	mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
> -		     "xfsino", ip->i_ino);
> +	init_rwsem(&ip->i_mmaplock);
> +	init_rwsem(&ip->i_lock);
>  }
>  
>  /*
> -- 
> 2.26.2
>