Re: [PATCH 1/2] remove mapping from balance_dirty_pages*()

[Jan Kara <jack@suse.cz>]

On Wed 10-08-16 10:27:33, Jan Kara wrote:
> On Tue 09-08-16 15:08:26, Josef Bacik wrote:
> > The only reason we pass in the mapping is to get the inode in order to see if
> > writeback cgroups is enabled, and even then it only checks the bdi and a super
> > block flag.  balance_dirty_pages() doesn't even use the mapping.  Since
> > balance_dirty_pages*() works on a bdi level, just pass in the bdi and super
> > block directly so we can avoid using mapping.  This will allow us to still use
> > balance_dirty_pages for dirty metadata pages that are not backed by an
> > address_mapping.
> >
> > Signed-off-by: Josef Bacik <jbacik@fb.com>
> 
> The patch looks good. You can add:
> 
> Reviewed-by: Jan Kara <jack@suse.cz>

Well, modulo those build failures which obviously need to be sorted out...
But they should be trivial to deal with.

								Honza

> > ---
> >  fs/btrfs/disk-io.c          |  4 ++--
> >  fs/btrfs/file.c             |  3 ++-
> >  fs/btrfs/ioctl.c            |  3 ++-
> >  fs/btrfs/relocation.c       |  3 ++-
> >  fs/buffer.c                 |  3 ++-
> >  fs/iomap.c                  |  3 ++-
> >  include/linux/backing-dev.h | 23 +++++++++++++++++------
> >  include/linux/writeback.h   |  3 ++-
> >  mm/filemap.c                |  4 +++-
> >  mm/memory.c                 |  9 +++++++--
> >  mm/page-writeback.c         | 15 +++++++--------
> >  11 files changed, 48 insertions(+), 25 deletions(-)
> > 
> > diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
> > index 17346f7..c1d951a 100644
> > --- a/fs/btrfs/disk-io.c
> > +++ b/fs/btrfs/disk-io.c
> > @@ -4024,8 +4024,8 @@ static void __btrfs_btree_balance_dirty(struct btrfs_root *root,
> >  	ret = percpu_counter_compare(&root->fs_info->dirty_metadata_bytes,
> >  				     BTRFS_DIRTY_METADATA_THRESH);
> >  	if (ret > 0) {
> > -		balance_dirty_pages_ratelimited(
> > -				   root->fs_info->btree_inode->i_mapping);
> > +		balance_dirty_pages_ratelimited(&root->fs_info->bdi,
> > +						root->fs_info->sb);
> >  	}
> >  }
> >  
> > diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
> > index 9404121..f060b08 100644
> > --- a/fs/btrfs/file.c
> > +++ b/fs/btrfs/file.c
> > @@ -1686,7 +1686,8 @@ again:
> >  
> >  		cond_resched();
> >  
> > -		balance_dirty_pages_ratelimited(inode->i_mapping);
> > +		balance_dirty_pages_ratelimited(inode_to_bdi(inode),
> > +						inode->i_sb);
> >  		if (dirty_pages < (root->nodesize >> PAGE_SHIFT) + 1)
> >  			btrfs_btree_balance_dirty(root);
> >  
> > diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
> > index 14ed1e9..a222bad 100644
> > --- a/fs/btrfs/ioctl.c
> > +++ b/fs/btrfs/ioctl.c
> > @@ -1410,7 +1410,8 @@ int btrfs_defrag_file(struct inode *inode, struct file *file,
> >  		}
> >  
> >  		defrag_count += ret;
> > -		balance_dirty_pages_ratelimited(inode->i_mapping);
> > +		balance_dirty_pages_ratelimited(inode_to_bdi(inode),
> > +						inode->i_sb);
> >  		inode_unlock(inode);
> >  
> >  		if (newer_than) {
> > diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
> > index 4598e29..7fc6ea7 100644
> > --- a/fs/btrfs/relocation.c
> > +++ b/fs/btrfs/relocation.c
> > @@ -3202,7 +3202,8 @@ static int relocate_file_extent_cluster(struct inode *inode,
> >  		put_page(page);
> >  
> >  		index++;
> > -		balance_dirty_pages_ratelimited(inode->i_mapping);
> > +		balance_dirty_pages_ratelimited(inode_to_bdi(inode),
> > +						inode->i_sb);
> >  		btrfs_throttle(BTRFS_I(inode)->root);
> >  	}
> >  	WARN_ON(nr != cluster->nr);
> > diff --git a/fs/buffer.c b/fs/buffer.c
> > index 9c8eb9b..9bbe30d 100644
> > --- a/fs/buffer.c
> > +++ b/fs/buffer.c
> > @@ -2386,7 +2386,8 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
> >  		BUG_ON(err != len);
> >  		err = 0;
> >  
> > -		balance_dirty_pages_ratelimited(mapping);
> > +		balance_dirty_pages_ratelimited(inode_to_bdi(inode),
> > +						inode->i_sb);
> >  
> >  		if (unlikely(fatal_signal_pending(current))) {
> >  			err = -EINTR;
> > diff --git a/fs/iomap.c b/fs/iomap.c
> > index 48141b8..937e266 100644
> > --- a/fs/iomap.c
> > +++ b/fs/iomap.c
> > @@ -226,7 +226,8 @@ again:
> >  		written += copied;
> >  		length -= copied;
> >  
> > -		balance_dirty_pages_ratelimited(inode->i_mapping);
> > +		balance_dirty_pages_ratelimited(inode_to_bdi(inode),
> > +						inode->i_sb);
> >  	} while (iov_iter_count(i) && length);
> >  
> >  	return written ? written : status;
> > diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h
> > index 491a917..3b76eeb 100644
> > --- a/include/linux/backing-dev.h
> > +++ b/include/linux/backing-dev.h
> > @@ -252,8 +252,9 @@ void wb_blkcg_offline(struct blkcg *blkcg);
> >  int inode_congested(struct inode *inode, int cong_bits);
> >  
> >  /**
> > - * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode
> > - * @inode: inode of interest
> > + * bdi_cgwb_enabled - test wether cgroup writeback is enabled on a filesystem
> > + * @bdi: the bdi we care about
> > + * @sb: the super for the bdi
> >   *
> >   * cgroup writeback requires support from both the bdi and filesystem.
> >   * Also, both memcg and iocg have to be on the default hierarchy.  Test
> > @@ -262,15 +263,25 @@ int inode_congested(struct inode *inode, int cong_bits);
> >   * Note that the test result may change dynamically on the same inode
> >   * depending on how memcg and iocg are configured.
> >   */
> > -static inline bool inode_cgwb_enabled(struct inode *inode)
> > +static inline bool bdi_cgwb_enabled(struct backing_dev_info *bdi,
> > +				    struct super_block *sb)
> >  {
> > -	struct backing_dev_info *bdi = inode_to_bdi(inode);
> > -
> >  	return cgroup_subsys_on_dfl(memory_cgrp_subsys) &&
> >  		cgroup_subsys_on_dfl(io_cgrp_subsys) &&
> >  		bdi_cap_account_dirty(bdi) &&
> >  		(bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) &&
> > -		(inode->i_sb->s_iflags & SB_I_CGROUPWB);
> > +		(sb->s_iflags & SB_I_CGROUPWB);
> > +}
> > +
> > +/**
> > + * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode
> > + * @inode: inode of interest
> > + *
> > + * Does the inode have cgroup writeback support.
> > + */
> > +static inline bool inode_cgwb_enabled(struct inode *inode)
> > +{
> > +	return bdi_cgwb_enabled(inode_to_bdi(inode), inode->i_sb);
> >  }
> >  
> >  /**
> > diff --git a/include/linux/writeback.h b/include/linux/writeback.h
> > index fc1e16c..256ffc3 100644
> > --- a/include/linux/writeback.h
> > +++ b/include/linux/writeback.h
> > @@ -364,7 +364,8 @@ unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh);
> >  
> >  void wb_update_bandwidth(struct bdi_writeback *wb, unsigned long start_time);
> >  void page_writeback_init(void);
> > -void balance_dirty_pages_ratelimited(struct address_space *mapping);
> > +void balance_dirty_pages_ratelimited(struct backing_dev_info *bdi,
> > +				     struct super_block *sb);
> >  bool wb_over_bg_thresh(struct bdi_writeback *wb);
> >  
> >  typedef int (*writepage_t)(struct page *page, struct writeback_control *wbc,
> > diff --git a/mm/filemap.c b/mm/filemap.c
> > index 3083ded..abb0e98 100644
> > --- a/mm/filemap.c
> > +++ b/mm/filemap.c
> > @@ -2667,6 +2667,7 @@ ssize_t generic_perform_write(struct file *file,
> >  				struct iov_iter *i, loff_t pos)
> >  {
> >  	struct address_space *mapping = file->f_mapping;
> > +	struct inode *inode = mapping->host;
> >  	const struct address_space_operations *a_ops = mapping->a_ops;
> >  	long status = 0;
> >  	ssize_t written = 0;
> > @@ -2746,7 +2747,8 @@ again:
> >  		pos += copied;
> >  		written += copied;
> >  
> > -		balance_dirty_pages_ratelimited(mapping);
> > +		balance_dirty_pages_ratelimited(inode_to_bdi(inode),
> > +						inode->i_sb);
> >  	} while (iov_iter_count(i));
> >  
> >  	return written ? written : status;
> > diff --git a/mm/memory.c b/mm/memory.c
> > index 83be99d..d43e73b 100644
> > --- a/mm/memory.c
> > +++ b/mm/memory.c
> > @@ -64,6 +64,7 @@
> >  #include <linux/debugfs.h>
> >  #include <linux/userfaultfd_k.h>
> >  #include <linux/dax.h>
> > +#include <linux/backing-dev.h>
> >  
> >  #include <asm/io.h>
> >  #include <asm/mmu_context.h>
> > @@ -2105,11 +2106,13 @@ static inline int wp_page_reuse(struct fault_env *fe, pte_t orig_pte,
> >  		put_page(page);
> >  
> >  		if ((dirtied || page_mkwrite) && mapping) {
> > +			struct inode *inode = mapping->host;
> >  			/*
> >  			 * Some device drivers do not set page.mapping
> >  			 * but still dirty their pages
> >  			 */
> > -			balance_dirty_pages_ratelimited(mapping);
> > +			balance_dirty_pages_ratelimited(inode_to_bdi(inode),
> > +							inode->i_sb);
> >  		}
> >  
> >  		if (!page_mkwrite)
> > @@ -3291,11 +3294,13 @@ static int do_shared_fault(struct fault_env *fe, pgoff_t pgoff)
> >  	mapping = page_rmapping(fault_page);
> >  	unlock_page(fault_page);
> >  	if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
> > +		struct inode *inode = mapping->host;
> >  		/*
> >  		 * Some device drivers do not set page.mapping but still
> >  		 * dirty their pages
> >  		 */
> > -		balance_dirty_pages_ratelimited(mapping);
> > +		balance_dirty_pages_ratelimited(inode_to_bdi(inode),
> > +						inode->i_sb);
> >  	}
> >  
> >  	if (!vma->vm_ops->page_mkwrite)
> > diff --git a/mm/page-writeback.c b/mm/page-writeback.c
> > index f4cd7d8..121a6e3 100644
> > --- a/mm/page-writeback.c
> > +++ b/mm/page-writeback.c
> > @@ -1559,8 +1559,7 @@ static inline void wb_dirty_limits(struct dirty_throttle_control *dtc)
> >   * If we're over `background_thresh' then the writeback threads are woken to
> >   * perform some writeout.
> >   */
> > -static void balance_dirty_pages(struct address_space *mapping,
> > -				struct bdi_writeback *wb,
> > +static void balance_dirty_pages(struct bdi_writeback *wb,
> >  				unsigned long pages_dirtied)
> >  {
> >  	struct dirty_throttle_control gdtc_stor = { GDTC_INIT(wb) };
> > @@ -1849,7 +1848,8 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
> >  
> >  /**
> >   * balance_dirty_pages_ratelimited - balance dirty memory state
> > - * @mapping: address_space which was dirtied
> > + * @bdi: the bdi that was dirtied
> > + * @sb: the super block that was dirtied
> >   *
> >   * Processes which are dirtying memory should call in here once for each page
> >   * which was newly dirtied.  The function will periodically check the system's
> > @@ -1860,10 +1860,9 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;
> >   * limit we decrease the ratelimiting by a lot, to prevent individual processes
> >   * from overshooting the limit by (ratelimit_pages) each.
> >   */
> > -void balance_dirty_pages_ratelimited(struct address_space *mapping)
> > +void balance_dirty_pages_ratelimited(struct backing_dev_info *bdi,
> > +				     struct super_block *sb)
> >  {
> > -	struct inode *inode = mapping->host;
> > -	struct backing_dev_info *bdi = inode_to_bdi(inode);
> >  	struct bdi_writeback *wb = NULL;
> >  	int ratelimit;
> >  	int *p;
> > @@ -1871,7 +1870,7 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping)
> >  	if (!bdi_cap_account_dirty(bdi))
> >  		return;
> >  
> > -	if (inode_cgwb_enabled(inode))
> > +	if (bdi_cgwb_enabled(bdi, sb))
> >  		wb = wb_get_create_current(bdi, GFP_KERNEL);
> >  	if (!wb)
> >  		wb = &bdi->wb;
> > @@ -1909,7 +1908,7 @@ void balance_dirty_pages_ratelimited(struct address_space *mapping)
> >  	preempt_enable();
> >  
> >  	if (unlikely(current->nr_dirtied >= ratelimit))
> > -		balance_dirty_pages(mapping, wb, current->nr_dirtied);
> > +		balance_dirty_pages(wb, current->nr_dirtied);
> >  
> >  	wb_put(wb);
> >  }
> > -- 
> > 1.8.3.1
> > 
> > 
> -- 
> Jan Kara <jack@suse.com>
> SUSE Labs, CR
-- 
Jan Kara <jack@suse.com>
SUSE Labs, CR