Commit a601e637 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'for-linus-v3.7-rc5' of git://oss.sgi.com/xfs/xfs 

Pull xfs bugfixes from Ben Myers:

 - fix for large transactions spanning multiple iclog buffers

 - zero the allocation_args structure on the stack before using it to
   determine whether to use a worker for allocation
 - move allocation stack switch to xfs_bmapi_allocate in order to
   prevent deadlock on AGF buffers

 - growfs no longer reads in garbage for new secondary superblocks

 - silence a build warning

 - ensure that invalid buffers never get written to disk while on free
   list

 - don't vmap inode cluster buffers during free

 - fix buffer shutdown reference count mismatch

 - fix reading of wrapped log data

* tag 'for-linus-v3.7-rc5' of git://oss.sgi.com/xfs/xfs:
  xfs: fix reading of wrapped log data
  xfs: fix buffer shudown reference count mismatch
  xfs: don't vmap inode cluster buffers during free
  xfs: invalidate allocbt blocks moved to the free list
  xfs: silence uninitialised f.file warning.
  xfs: growfs: don't read garbage for new secondary superblocks
  xfs: move allocation stack switch up to xfs_bmapi_allocate
  xfs: introduce XFS_BMAPI_STACK_SWITCH
  xfs: zero allocation_args on the kernel stack
  xfs: only update the last_sync_lsn when a transaction completes
parents 0e4a43ed 6ce377af

fs/xfs/xfs_alloc.c

+2 −41
Original line number Diff line number Diff line
@@ -1866,6 +1866,7 @@ xfs_alloc_fix_freelist( 
	/*

	 * Initialize the args structure.

	 */

	memset(&targs, 0, sizeof(targs));

	targs.tp = tp;

	targs.mp = mp;

	targs.agbp = agbp;
@@ -2207,7 +2208,7 @@ xfs_alloc_read_agf( 
 * group or loop over the allocation groups to find the result.

 */

int				/* error */

__xfs_alloc_vextent(

xfs_alloc_vextent(

	xfs_alloc_arg_t	*args)	/* allocation argument structure */

{

	xfs_agblock_t	agsize;	/* allocation group size */
@@ -2417,46 +2418,6 @@ error0: 
	return error;

}



static void

xfs_alloc_vextent_worker(

	struct work_struct	*work)

{

	struct xfs_alloc_arg	*args = container_of(work,

						struct xfs_alloc_arg, work);

	unsigned long		pflags;



	/* we are in a transaction context here */

	current_set_flags_nested(&pflags, PF_FSTRANS);



	args->result = __xfs_alloc_vextent(args);

	complete(args->done);



	current_restore_flags_nested(&pflags, PF_FSTRANS);

}



/*

 * Data allocation requests often come in with little stack to work on. Push

 * them off to a worker thread so there is lots of stack to use. Metadata

 * requests, OTOH, are generally from low stack usage paths, so avoid the

 * context switch overhead here.

 */

int

xfs_alloc_vextent(

	struct xfs_alloc_arg	*args)

{

	DECLARE_COMPLETION_ONSTACK(done);



	if (!args->userdata)

		return __xfs_alloc_vextent(args);





	args->done = &done;

	INIT_WORK_ONSTACK(&args->work, xfs_alloc_vextent_worker);

	queue_work(xfs_alloc_wq, &args->work);

	wait_for_completion(&done);

	return args->result;

}



/*

 * Free an extent.

 * Just break up the extent address and hand off to xfs_free_ag_extent

fs/xfs/xfs_alloc.h

+0 −3
Original line number Diff line number Diff line
@@ -120,9 +120,6 @@ typedef struct xfs_alloc_arg { 
	char		isfl;		/* set if is freelist blocks - !acctg */

	char		userdata;	/* set if this is user data */

	xfs_fsblock_t	firstblock;	/* io first block allocated */

	struct completion *done;

	struct work_struct work;

	int		result;

} xfs_alloc_arg_t;



/*

fs/xfs/xfs_alloc_btree.c

+2 −0
Original line number Diff line number Diff line
@@ -121,6 +121,8 @@ xfs_allocbt_free_block( 
	xfs_extent_busy_insert(cur->bc_tp, be32_to_cpu(agf->agf_seqno), bno, 1,

			      XFS_EXTENT_BUSY_SKIP_DISCARD);

	xfs_trans_agbtree_delta(cur->bc_tp, -1);



	xfs_trans_binval(cur->bc_tp, bp);

	return 0;

}

fs/xfs/xfs_bmap.c

+54 −9
Original line number Diff line number Diff line
@@ -2437,6 +2437,7 @@ xfs_bmap_btalloc( 
	 * Normal allocation, done through xfs_alloc_vextent.

	 */

	tryagain = isaligned = 0;

	memset(&args, 0, sizeof(args));

	args.tp = ap->tp;

	args.mp = mp;

	args.fsbno = ap->blkno;
@@ -3082,6 +3083,7 @@ xfs_bmap_extents_to_btree( 
	 * Convert to a btree with two levels, one record in root.

	 */

	XFS_IFORK_FMT_SET(ip, whichfork, XFS_DINODE_FMT_BTREE);

	memset(&args, 0, sizeof(args));

	args.tp = tp;

	args.mp = mp;

	args.firstblock = *firstblock;
@@ -3237,6 +3239,7 @@ xfs_bmap_local_to_extents( 
		xfs_buf_t	*bp;	/* buffer for extent block */

		xfs_bmbt_rec_host_t *ep;/* extent record pointer */



		memset(&args, 0, sizeof(args));

		args.tp = tp;

		args.mp = ip->i_mount;

		args.firstblock = *firstblock;
@@ -4616,12 +4619,11 @@ xfs_bmapi_delay( 




STATIC int

xfs_bmapi_allocate(

	struct xfs_bmalloca	*bma,

	int			flags)

__xfs_bmapi_allocate(

	struct xfs_bmalloca	*bma)

{

	struct xfs_mount	*mp = bma->ip->i_mount;

	int			whichfork = (flags & XFS_BMAPI_ATTRFORK) ?

	int			whichfork = (bma->flags & XFS_BMAPI_ATTRFORK) ?

						XFS_ATTR_FORK : XFS_DATA_FORK;

	struct xfs_ifork	*ifp = XFS_IFORK_PTR(bma->ip, whichfork);

	int			tmp_logflags = 0;
@@ -4654,24 +4656,27 @@ xfs_bmapi_allocate( 
	 * Indicate if this is the first user data in the file, or just any

	 * user data.

	 */

	if (!(flags & XFS_BMAPI_METADATA)) {

	if (!(bma->flags & XFS_BMAPI_METADATA)) {

		bma->userdata = (bma->offset == 0) ?

			XFS_ALLOC_INITIAL_USER_DATA : XFS_ALLOC_USERDATA;

	}



	bma->minlen = (flags & XFS_BMAPI_CONTIG) ? bma->length : 1;

	bma->minlen = (bma->flags & XFS_BMAPI_CONTIG) ? bma->length : 1;



	/*

	 * Only want to do the alignment at the eof if it is userdata and

	 * allocation length is larger than a stripe unit.

	 */

	if (mp->m_dalign && bma->length >= mp->m_dalign &&

	    !(flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) {

	    !(bma->flags & XFS_BMAPI_METADATA) && whichfork == XFS_DATA_FORK) {

		error = xfs_bmap_isaeof(bma, whichfork);

		if (error)

			return error;

	}



	if (bma->flags & XFS_BMAPI_STACK_SWITCH)

		bma->stack_switch = 1;



	error = xfs_bmap_alloc(bma);

	if (error)

		return error;
@@ -4706,7 +4711,7 @@ xfs_bmapi_allocate( 
	 * A wasdelay extent has been initialized, so shouldn't be flagged

	 * as unwritten.

	 */

	if (!bma->wasdel && (flags & XFS_BMAPI_PREALLOC) &&

	if (!bma->wasdel && (bma->flags & XFS_BMAPI_PREALLOC) &&

	    xfs_sb_version_hasextflgbit(&mp->m_sb))

		bma->got.br_state = XFS_EXT_UNWRITTEN;
@@ -4734,6 +4739,45 @@ xfs_bmapi_allocate( 
	return 0;

}



static void

xfs_bmapi_allocate_worker(

	struct work_struct	*work)

{

	struct xfs_bmalloca	*args = container_of(work,

						struct xfs_bmalloca, work);

	unsigned long		pflags;



	/* we are in a transaction context here */

	current_set_flags_nested(&pflags, PF_FSTRANS);



	args->result = __xfs_bmapi_allocate(args);

	complete(args->done);



	current_restore_flags_nested(&pflags, PF_FSTRANS);

}



/*

 * Some allocation requests often come in with little stack to work on. Push

 * them off to a worker thread so there is lots of stack to use. Otherwise just

 * call directly to avoid the context switch overhead here.

 */

int

xfs_bmapi_allocate(

	struct xfs_bmalloca	*args)

{

	DECLARE_COMPLETION_ONSTACK(done);



	if (!args->stack_switch)

		return __xfs_bmapi_allocate(args);





	args->done = &done;

	INIT_WORK_ONSTACK(&args->work, xfs_bmapi_allocate_worker);

	queue_work(xfs_alloc_wq, &args->work);

	wait_for_completion(&done);

	return args->result;

}



STATIC int

xfs_bmapi_convert_unwritten(

	struct xfs_bmalloca	*bma,
@@ -4919,6 +4963,7 @@ xfs_bmapi_write( 
			bma.conv = !!(flags & XFS_BMAPI_CONVERT);

			bma.wasdel = wasdelay;

			bma.offset = bno;

			bma.flags = flags;



			/*

			 * There's a 32/64 bit type mismatch between the
@@ -4934,7 +4979,7 @@ xfs_bmapi_write( 


			ASSERT(len > 0);

			ASSERT(bma.length > 0);

			error = xfs_bmapi_allocate(&bma, flags);

			error = xfs_bmapi_allocate(&bma);

			if (error)

				goto error0;

			if (bma.blkno == NULLFSBLOCK)

fs/xfs/xfs_bmap.h

+8 −1
Original line number Diff line number Diff line
@@ -77,6 +77,7 @@ typedef struct xfs_bmap_free 
 * from written to unwritten, otherwise convert from unwritten to written.

 */

#define XFS_BMAPI_CONVERT	0x040

#define XFS_BMAPI_STACK_SWITCH	0x080



#define XFS_BMAPI_FLAGS \

	{ XFS_BMAPI_ENTIRE,	"ENTIRE" }, \
@@ -85,7 +86,8 @@ typedef struct xfs_bmap_free 
	{ XFS_BMAPI_PREALLOC,	"PREALLOC" }, \

	{ XFS_BMAPI_IGSTATE,	"IGSTATE" }, \

	{ XFS_BMAPI_CONTIG,	"CONTIG" }, \

	{ XFS_BMAPI_CONVERT,	"CONVERT" }

	{ XFS_BMAPI_CONVERT,	"CONVERT" }, \

	{ XFS_BMAPI_STACK_SWITCH, "STACK_SWITCH" }





static inline int xfs_bmapi_aflag(int w)
@@ -133,6 +135,11 @@ typedef struct xfs_bmalloca { 
	char			userdata;/* set if is user data */

	char			aeof;	/* allocated space at eof */

	char			conv;	/* overwriting unwritten extents */

	char			stack_switch;

	int			flags;

	struct completion	*done;

	struct work_struct	work;

	int			result;

} xfs_bmalloca_t;



/*

CRA Git | Maintained and supported by SUSTech CRA and CCSE