[PATCH v3] xfs: reserve enough blocks to handle btree splits when remapping

[PATCH v3] xfs: reserve enough blocks to handle btree splits when remapping

[Darrick J. Wong]

In xfs_reflink_end_cow, we erroneously reserve only enough blocks to
handle adding 1 extent.  This is problematic if we fragment free space,
have to do CoW, and then have to perform multiple bmap btree expansions.
Furthermore, the BUI recovery routine doesn't reserve /any/ blocks to
handle btree splits, so log recovery fails after our first error causes
the filesystem to go down.

Therefore, refactor the transaction block reservation macros until we
have a macro that works for our deferred (re)mapping activities, and fix
both problems by using that macro.

With 1k blocks we can hit this fairly often in g/187 if the scratch fs
is big enough.

Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
---
v3: don't use the swap-extents-with-rmap block reservation for cow
remapping; we should already have sufficient per-ag reservation
v2: avoid 64-bit division when calculating block reservation
---
 fs/xfs/libxfs/xfs_trans_space.h |   13 +++++++------
 fs/xfs/xfs_bmap_item.c          |    7 ++++++-
 fs/xfs/xfs_reflink.c            |   12 ++++++++++--
 3 files changed, 23 insertions(+), 9 deletions(-)

diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h
index 7917f6e..0044e14 100644
--- a/fs/xfs/libxfs/xfs_trans_space.h
+++ b/fs/xfs/libxfs/xfs_trans_space.h
@@ -23,6 +23,11 @@
  */
 #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)    \
 		(((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0]))
+#define XFS_RMAPADD_SPACE_RES(mp) ((mp)->m_rmap_maxlevels)
+#define XFS_NRMAPADD_SPACE_RES(mp,b,w)\
+	(((b + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) - 1) / \
+	  XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * \
+	  XFS_RMAPADD_SPACE_RES(mp))
 #define XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)    \
 		(((mp)->m_alloc_mxr[0]) - ((mp)->m_alloc_mnr[0]))
 #define	XFS_EXTENTADD_SPACE_RES(mp,w)	(XFS_BM_MAXLEVELS(mp,w) - 1)
@@ -31,12 +36,8 @@
 	  XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)) * \
 	  XFS_EXTENTADD_SPACE_RES(mp,w))
 #define XFS_SWAP_RMAP_SPACE_RES(mp,b,w)\
-	(((b + XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp) - 1) / \
-	  XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)) * \
-	  XFS_EXTENTADD_SPACE_RES(mp,w) + \
-	 ((b + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) - 1) / \
-	  XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * \
-	  (mp)->m_rmap_maxlevels)
+	(XFS_NEXTENTADD_SPACE_RES((mp), (b), (w)) + \
+	 XFS_NRMAPADD_SPACE_RES((mp), (b), (w)))
 #define	XFS_DAENTER_1B(mp,w)	\
 	((w) == XFS_DATA_FORK ? (mp)->m_dir_geo->fsbcount : 1)
 #define	XFS_DAENTER_DBS(mp,w)	\
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 2d70173..378f144 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -34,6 +34,8 @@
 #include "xfs_bmap.h"
 #include "xfs_icache.h"
 #include "xfs_trace.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
 
 
 kmem_zone_t	*xfs_bui_zone;
@@ -403,6 +405,7 @@ xfs_bui_recover(
 	struct xfs_inode		*ip = NULL;
 	struct xfs_defer_ops		dfops;
 	xfs_fsblock_t			firstfsb;
+	unsigned int			resblks;
 
 	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
 
@@ -447,7 +450,9 @@ xfs_bui_recover(
 		return -EIO;
 	}
 
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
+	resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, resblks, 0,
+			0, &tp);
 	if (error)
 		return error;
 	budp = xfs_trans_get_bud(tp, buip);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index c0f3754..aab156a 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -705,8 +705,16 @@ xfs_reflink_end_cow(
 	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
 	end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
 
-	/* Start a rolling transaction to switch the mappings */
-	resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
+	/*
+	 * Start a rolling transaction to switch the mappings.  We're
+	 * unlikely ever to have to remap 16T worth of single-block
+	 * extents, so just cap the worst case extent count to 2^32-1.
+	 * Stick a warning in just in case, and avoid 64-bit division.
+	 */
+	WARN_ON(end_fsb - offset_fsb + 1 > UINT_MAX);
+	resblks = min_t(xfs_fileoff_t, UINT_MAX, end_fsb - offset_fsb + 1);
+	resblks = XFS_NEXTENTADD_SPACE_RES(ip->i_mount, resblks,
+			XFS_DATA_FORK);
 	error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write,
 			resblks, 0, 0, &tp);
 	if (error)

Re: [PATCH v3] xfs: reserve enough blocks to handle btree splits when remapping

[Brian Foster]

On Mon, Apr 24, 2017 at 06:58:37PM -0700, Darrick J. Wong wrote:
> In xfs_reflink_end_cow, we erroneously reserve only enough blocks to
> handle adding 1 extent.  This is problematic if we fragment free space,
> have to do CoW, and then have to perform multiple bmap btree expansions.
> Furthermore, the BUI recovery routine doesn't reserve /any/ blocks to
> handle btree splits, so log recovery fails after our first error causes
> the filesystem to go down.
> 
> Therefore, refactor the transaction block reservation macros until we
> have a macro that works for our deferred (re)mapping activities, and fix
> both problems by using that macro.
> 
> With 1k blocks we can hit this fairly often in g/187 if the scratch fs
> is big enough.
> 
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---

Reviewed-by: Brian Foster <bfoster@redhat.com>

> v3: don't use the swap-extents-with-rmap block reservation for cow
> remapping; we should already have sufficient per-ag reservation
> v2: avoid 64-bit division when calculating block reservation
> ---
>  fs/xfs/libxfs/xfs_trans_space.h |   13 +++++++------
>  fs/xfs/xfs_bmap_item.c          |    7 ++++++-
>  fs/xfs/xfs_reflink.c            |   12 ++++++++++--
>  3 files changed, 23 insertions(+), 9 deletions(-)
> 
> diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h
> index 7917f6e..0044e14 100644
> --- a/fs/xfs/libxfs/xfs_trans_space.h
> +++ b/fs/xfs/libxfs/xfs_trans_space.h
> @@ -23,6 +23,11 @@
>   */
>  #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)    \
>  		(((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0]))
> +#define XFS_RMAPADD_SPACE_RES(mp) ((mp)->m_rmap_maxlevels)
> +#define XFS_NRMAPADD_SPACE_RES(mp,b,w)\
> +	(((b + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) - 1) / \
> +	  XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * \
> +	  XFS_RMAPADD_SPACE_RES(mp))
>  #define XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)    \
>  		(((mp)->m_alloc_mxr[0]) - ((mp)->m_alloc_mnr[0]))
>  #define	XFS_EXTENTADD_SPACE_RES(mp,w)	(XFS_BM_MAXLEVELS(mp,w) - 1)
> @@ -31,12 +36,8 @@
>  	  XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)) * \
>  	  XFS_EXTENTADD_SPACE_RES(mp,w))
>  #define XFS_SWAP_RMAP_SPACE_RES(mp,b,w)\
> -	(((b + XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp) - 1) / \
> -	  XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)) * \
> -	  XFS_EXTENTADD_SPACE_RES(mp,w) + \
> -	 ((b + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) - 1) / \
> -	  XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * \
> -	  (mp)->m_rmap_maxlevels)
> +	(XFS_NEXTENTADD_SPACE_RES((mp), (b), (w)) + \
> +	 XFS_NRMAPADD_SPACE_RES((mp), (b), (w)))
>  #define	XFS_DAENTER_1B(mp,w)	\
>  	((w) == XFS_DATA_FORK ? (mp)->m_dir_geo->fsbcount : 1)
>  #define	XFS_DAENTER_DBS(mp,w)	\
> diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
> index 2d70173..378f144 100644
> --- a/fs/xfs/xfs_bmap_item.c
> +++ b/fs/xfs/xfs_bmap_item.c
> @@ -34,6 +34,8 @@
>  #include "xfs_bmap.h"
>  #include "xfs_icache.h"
>  #include "xfs_trace.h"
> +#include "xfs_bmap_btree.h"
> +#include "xfs_trans_space.h"
>  
>  
>  kmem_zone_t	*xfs_bui_zone;
> @@ -403,6 +405,7 @@ xfs_bui_recover(
>  	struct xfs_inode		*ip = NULL;
>  	struct xfs_defer_ops		dfops;
>  	xfs_fsblock_t			firstfsb;
> +	unsigned int			resblks;
>  
>  	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
>  
> @@ -447,7 +450,9 @@ xfs_bui_recover(
>  		return -EIO;
>  	}
>  
> -	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
> +	resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
> +	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, resblks, 0,
> +			0, &tp);
>  	if (error)
>  		return error;
>  	budp = xfs_trans_get_bud(tp, buip);
> diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
> index c0f3754..aab156a 100644
> --- a/fs/xfs/xfs_reflink.c
> +++ b/fs/xfs/xfs_reflink.c
> @@ -705,8 +705,16 @@ xfs_reflink_end_cow(
>  	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
>  	end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
>  
> -	/* Start a rolling transaction to switch the mappings */
> -	resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
> +	/*
> +	 * Start a rolling transaction to switch the mappings.  We're
> +	 * unlikely ever to have to remap 16T worth of single-block
> +	 * extents, so just cap the worst case extent count to 2^32-1.
> +	 * Stick a warning in just in case, and avoid 64-bit division.
> +	 */
> +	WARN_ON(end_fsb - offset_fsb + 1 > UINT_MAX);
> +	resblks = min_t(xfs_fileoff_t, UINT_MAX, end_fsb - offset_fsb + 1);
> +	resblks = XFS_NEXTENTADD_SPACE_RES(ip->i_mount, resblks,
> +			XFS_DATA_FORK);
>  	error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write,
>  			resblks, 0, 0, &tp);
>  	if (error)
> --
> To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v3] xfs: reserve enough blocks to handle btree splits when remapping

[Christoph Hellwig]

On Mon, Apr 24, 2017 at 06:58:37PM -0700, Darrick J. Wong wrote:
> In xfs_reflink_end_cow, we erroneously reserve only enough blocks to
> handle adding 1 extent.  This is problematic if we fragment free space,
> have to do CoW, and then have to perform multiple bmap btree expansions.
> Furthermore, the BUI recovery routine doesn't reserve /any/ blocks to
> handle btree splits, so log recovery fails after our first error causes
> the filesystem to go down.
> 
> Therefore, refactor the transaction block reservation macros until we
> have a macro that works for our deferred (re)mapping activities, and fix
> both problems by using that macro.
> 
> With 1k blocks we can hit this fairly often in g/187 if the scratch fs
> is big enough.
> 
> Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> ---
> v3: don't use the swap-extents-with-rmap block reservation for cow
> remapping; we should already have sufficient per-ag reservation
> v2: avoid 64-bit division when calculating block reservation
> ---
>  fs/xfs/libxfs/xfs_trans_space.h |   13 +++++++------
>  fs/xfs/xfs_bmap_item.c          |    7 ++++++-
>  fs/xfs/xfs_reflink.c            |   12 ++++++++++--
>  3 files changed, 23 insertions(+), 9 deletions(-)
> 
> diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h
> index 7917f6e..0044e14 100644
> --- a/fs/xfs/libxfs/xfs_trans_space.h
> +++ b/fs/xfs/libxfs/xfs_trans_space.h
> @@ -23,6 +23,11 @@
>   */
>  #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)    \
>  		(((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0]))
> +#define XFS_RMAPADD_SPACE_RES(mp) ((mp)->m_rmap_maxlevels)
> +#define XFS_NRMAPADD_SPACE_RES(mp,b,w)\
> +	(((b + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) - 1) / \
> +	  XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * \
> +	  XFS_RMAPADD_SPACE_RES(mp))

Comments, please!  (I know the existing defintions don't have any,
but that's bad enough to start with..)


>  	xfs_fsblock_t			firstfsb;
> +	unsigned int			resblks;
>  
>  	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
>  
> @@ -447,7 +450,9 @@ xfs_bui_recover(
>  		return -EIO;
>  	}
>  
> -	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
> +	resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
> +	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, resblks, 0,
> +			0, &tp);

Do we really need that resblks variable?

>  	if (error)
>  		return error;
>  	budp = xfs_trans_get_bud(tp, buip);
> diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
> index c0f3754..aab156a 100644
> --- a/fs/xfs/xfs_reflink.c
> +++ b/fs/xfs/xfs_reflink.c
> @@ -705,8 +705,16 @@ xfs_reflink_end_cow(
>  	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
>  	end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
>  
> -	/* Start a rolling transaction to switch the mappings */
> -	resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
> +	/*
> +	 * Start a rolling transaction to switch the mappings.  We're
> +	 * unlikely ever to have to remap 16T worth of single-block
> +	 * extents, so just cap the worst case extent count to 2^32-1.
> +	 * Stick a warning in just in case, and avoid 64-bit division.
> +	 */
> +	WARN_ON(end_fsb - offset_fsb + 1 > UINT_MAX);
> +	resblks = min_t(xfs_fileoff_t, UINT_MAX, end_fsb - offset_fsb + 1);

I don't like unlikely statements.  What prevents us from doing so?
I think the way Linux limits writes to 32-bits using MAX_RW_COUNT
does, but then the language should be more assertive here.  I think
we should also shut down the fs here if the assert fails - otherwise
we'll leave a partially converted region around.

A BUILD_BUG_ON on MAX_RW_COUNT might also be useful to make the whole
scheme even safer.

Re: [PATCH v3] xfs: reserve enough blocks to handle btree splits when remapping

[Darrick J. Wong]

On Thu, Apr 27, 2017 at 12:23:03AM -0700, Christoph Hellwig wrote:
> On Mon, Apr 24, 2017 at 06:58:37PM -0700, Darrick J. Wong wrote:
> > In xfs_reflink_end_cow, we erroneously reserve only enough blocks to
> > handle adding 1 extent.  This is problematic if we fragment free space,
> > have to do CoW, and then have to perform multiple bmap btree expansions.
> > Furthermore, the BUI recovery routine doesn't reserve /any/ blocks to
> > handle btree splits, so log recovery fails after our first error causes
> > the filesystem to go down.
> > 
> > Therefore, refactor the transaction block reservation macros until we
> > have a macro that works for our deferred (re)mapping activities, and fix
> > both problems by using that macro.
> > 
> > With 1k blocks we can hit this fairly often in g/187 if the scratch fs
> > is big enough.
> > 
> > Signed-off-by: Darrick J. Wong <darrick.wong@oracle.com>
> > ---
> > v3: don't use the swap-extents-with-rmap block reservation for cow
> > remapping; we should already have sufficient per-ag reservation
> > v2: avoid 64-bit division when calculating block reservation
> > ---
> >  fs/xfs/libxfs/xfs_trans_space.h |   13 +++++++------
> >  fs/xfs/xfs_bmap_item.c          |    7 ++++++-
> >  fs/xfs/xfs_reflink.c            |   12 ++++++++++--
> >  3 files changed, 23 insertions(+), 9 deletions(-)
> > 
> > diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h
> > index 7917f6e..0044e14 100644
> > --- a/fs/xfs/libxfs/xfs_trans_space.h
> > +++ b/fs/xfs/libxfs/xfs_trans_space.h
> > @@ -23,6 +23,11 @@
> >   */
> >  #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)    \
> >  		(((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0]))
> > +#define XFS_RMAPADD_SPACE_RES(mp) ((mp)->m_rmap_maxlevels)
> > +#define XFS_NRMAPADD_SPACE_RES(mp,b,w)\
> > +	(((b + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) - 1) / \
> > +	  XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * \
> > +	  XFS_RMAPADD_SPACE_RES(mp))
> 
> Comments, please!  (I know the existing defintions don't have any,
> but that's bad enough to start with..)

Ok.

> >  	xfs_fsblock_t			firstfsb;
> > +	unsigned int			resblks;
> >  
> >  	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
> >  
> > @@ -447,7 +450,9 @@ xfs_bui_recover(
> >  		return -EIO;
> >  	}
> >  
> > -	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
> > +	resblks = XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK);
> > +	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, resblks, 0,
> > +			0, &tp);
> 
> Do we really need that resblks variable?

No.

> >  	if (error)
> >  		return error;
> >  	budp = xfs_trans_get_bud(tp, buip);
> > diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
> > index c0f3754..aab156a 100644
> > --- a/fs/xfs/xfs_reflink.c
> > +++ b/fs/xfs/xfs_reflink.c
> > @@ -705,8 +705,16 @@ xfs_reflink_end_cow(
> >  	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
> >  	end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
> >  
> > -	/* Start a rolling transaction to switch the mappings */
> > -	resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
> > +	/*
> > +	 * Start a rolling transaction to switch the mappings.  We're
> > +	 * unlikely ever to have to remap 16T worth of single-block
> > +	 * extents, so just cap the worst case extent count to 2^32-1.
> > +	 * Stick a warning in just in case, and avoid 64-bit division.
> > +	 */
> > +	WARN_ON(end_fsb - offset_fsb + 1 > UINT_MAX);
> > +	resblks = min_t(xfs_fileoff_t, UINT_MAX, end_fsb - offset_fsb + 1);
> 
> I don't like unlikely statements.  What prevents us from doing so?
> I think the way Linux limits writes to 32-bits using MAX_RW_COUNT
> does, but then the language should be more assertive here.  I think
> we should also shut down the fs here if the assert fails - otherwise
> we'll leave a partially converted region around.

In the long run, I should just rewrite this to loop around if we are
asked to do too much at once.

> A BUILD_BUG_ON on MAX_RW_COUNT might also be useful to make the whole
> scheme even safer.

Yeah, we could do that too.

--D

> --
> To unsubscribe from this list: send the line "unsubscribe linux-xfs" in
> the body of a message to majordomo@vger.kernel.org
> More majordomo info at  http://vger.kernel.org/majordomo-info.html