Commit c148bc75 authored by Linus Torvalds's avatar Linus Torvalds
Browse files

Merge tag 'xfs-6.15-merge' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux 

Pull xfs updates from Carlos Maiolino:

 - XFS zoned allocator: Enables XFS to support zoned devices using its
   real-time allocator

 - Use folios/vmalloc for buffer cache backing memory

 - Some code cleanups and bug fixes

* tag 'xfs-6.15-merge' of git://git.kernel.org/pub/scm/fs/xfs/xfs-linux: (70 commits)
  xfs: remove the flags argument to xfs_buf_get_uncached
  xfs: remove the flags argument to xfs_buf_read_uncached
  xfs: remove xfs_buf_free_maps
  xfs: remove xfs_buf_get_maps
  xfs: call xfs_buf_alloc_backing_mem from _xfs_buf_alloc
  xfs: remove unnecessary NULL check before kvfree()
  xfs: don't wake zone space waiters without m_zone_info
  xfs: don't increment m_generation for all errors in xfs_growfs_data
  xfs: fix a missing unlock in xfs_growfs_data
  xfs: Remove duplicate xfs_rtbitmap.h header
  xfs: trigger zone GC when out of available rt blocks
  xfs: trace what memory backs a buffer
  xfs: cleanup mapping tmpfs folios into the buffer cache
  xfs: use vmalloc instead of vm_map_area for buffer backing memory
  xfs: buffer items don't straddle pages anymore
  xfs: kill XBF_UNMAPPED
  xfs: convert buffer cache to use high order folios
  xfs: remove the kmalloc to page allocator fallback
  xfs: refactor backing memory allocations for buffers
  xfs: remove xfs_buf_is_vmapped
  ...
parents 0de1e842 b3f8f290

fs/xfs/Makefile

+6 −1
Original line number Diff line number Diff line
@@ -64,6 +64,7 @@ xfs-y += $(addprefix libxfs/, \ 
xfs-$(CONFIG_XFS_RT)		+= $(addprefix libxfs/, \

				   xfs_rtbitmap.o \

				   xfs_rtgroup.o \

				   xfs_zones.o \

				   )



# highlevel code
@@ -136,7 +137,11 @@ xfs-$(CONFIG_XFS_QUOTA) += xfs_dquot.o \ 
				   xfs_quotaops.o



# xfs_rtbitmap is shared with libxfs

xfs-$(CONFIG_XFS_RT)		+= xfs_rtalloc.o

xfs-$(CONFIG_XFS_RT)		+= xfs_rtalloc.o \

				   xfs_zone_alloc.o \

				   xfs_zone_gc.o \

				   xfs_zone_info.o \

				   xfs_zone_space_resv.o



xfs-$(CONFIG_XFS_POSIX_ACL)	+= xfs_acl.o

xfs-$(CONFIG_SYSCTL)		+= xfs_sysctl.o

fs/xfs/libxfs/xfs_ag.c

+1 −1
Original line number Diff line number Diff line
@@ -301,7 +301,7 @@ xfs_get_aghdr_buf( 
	struct xfs_buf		*bp;

	int			error;



	error = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, 0, &bp);

	error = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, &bp);

	if (error)

		return error;

fs/xfs/libxfs/xfs_bmap.c

+23 −293
Original line number Diff line number Diff line
@@ -34,13 +34,13 @@ 
#include "xfs_ag.h"

#include "xfs_ag_resv.h"

#include "xfs_refcount.h"

#include "xfs_icache.h"

#include "xfs_iomap.h"

#include "xfs_health.h"

#include "xfs_bmap_item.h"

#include "xfs_symlink_remote.h"

#include "xfs_inode_util.h"

#include "xfs_rtgroup.h"

#include "xfs_zone_alloc.h"



struct kmem_cache		*xfs_bmap_intent_cache;
@@ -171,18 +171,16 @@ xfs_bmbt_update( 
 * Compute the worst-case number of indirect blocks that will be used

 * for ip's delayed extent of length "len".

 */

STATIC xfs_filblks_t

xfs_filblks_t

xfs_bmap_worst_indlen(

	xfs_inode_t	*ip,		/* incore inode pointer */

	struct xfs_inode	*ip,		/* incore inode pointer */

	xfs_filblks_t		len)		/* delayed extent length */

{

	int		level;		/* btree level number */

	int		maxrecs;	/* maximum record count at this level */

	xfs_mount_t	*mp;		/* mount structure */

	xfs_filblks_t	rval;		/* return value */

	struct xfs_mount	*mp = ip->i_mount;

	int			maxrecs = mp->m_bmap_dmxr[0];

	int			level;

	xfs_filblks_t		rval;



	mp = ip->i_mount;

	maxrecs = mp->m_bmap_dmxr[0];

	for (level = 0, rval = 0;

	     level < XFS_BM_MAXLEVELS(mp, XFS_DATA_FORK);

	     level++) {
@@ -2571,146 +2569,6 @@ xfs_bmap_add_extent_unwritten_real( 
#undef	PREV

}



/*

 * Convert a hole to a delayed allocation.

 */

STATIC void

xfs_bmap_add_extent_hole_delay(

	xfs_inode_t		*ip,	/* incore inode pointer */

	int			whichfork,

	struct xfs_iext_cursor	*icur,

	xfs_bmbt_irec_t		*new)	/* new data to add to file extents */

{

	struct xfs_ifork	*ifp;	/* inode fork pointer */

	xfs_bmbt_irec_t		left;	/* left neighbor extent entry */

	xfs_filblks_t		newlen=0;	/* new indirect size */

	xfs_filblks_t		oldlen=0;	/* old indirect size */

	xfs_bmbt_irec_t		right;	/* right neighbor extent entry */

	uint32_t		state = xfs_bmap_fork_to_state(whichfork);

	xfs_filblks_t		temp;	 /* temp for indirect calculations */



	ifp = xfs_ifork_ptr(ip, whichfork);

	ASSERT(isnullstartblock(new->br_startblock));



	/*

	 * Check and set flags if this segment has a left neighbor

	 */

	if (xfs_iext_peek_prev_extent(ifp, icur, &left)) {

		state |= BMAP_LEFT_VALID;

		if (isnullstartblock(left.br_startblock))

			state |= BMAP_LEFT_DELAY;

	}



	/*

	 * Check and set flags if the current (right) segment exists.

	 * If it doesn't exist, we're converting the hole at end-of-file.

	 */

	if (xfs_iext_get_extent(ifp, icur, &right)) {

		state |= BMAP_RIGHT_VALID;

		if (isnullstartblock(right.br_startblock))

			state |= BMAP_RIGHT_DELAY;

	}



	/*

	 * Set contiguity flags on the left and right neighbors.

	 * Don't let extents get too large, even if the pieces are contiguous.

	 */

	if ((state & BMAP_LEFT_VALID) && (state & BMAP_LEFT_DELAY) &&

	    left.br_startoff + left.br_blockcount == new->br_startoff &&

	    left.br_blockcount + new->br_blockcount <= XFS_MAX_BMBT_EXTLEN)

		state |= BMAP_LEFT_CONTIG;



	if ((state & BMAP_RIGHT_VALID) && (state & BMAP_RIGHT_DELAY) &&

	    new->br_startoff + new->br_blockcount == right.br_startoff &&

	    new->br_blockcount + right.br_blockcount <= XFS_MAX_BMBT_EXTLEN &&

	    (!(state & BMAP_LEFT_CONTIG) ||

	     (left.br_blockcount + new->br_blockcount +

	      right.br_blockcount <= XFS_MAX_BMBT_EXTLEN)))

		state |= BMAP_RIGHT_CONTIG;



	/*

	 * Switch out based on the contiguity flags.

	 */

	switch (state & (BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG)) {

	case BMAP_LEFT_CONTIG | BMAP_RIGHT_CONTIG:

		/*

		 * New allocation is contiguous with delayed allocations

		 * on the left and on the right.

		 * Merge all three into a single extent record.

		 */

		temp = left.br_blockcount + new->br_blockcount +

			right.br_blockcount;



		oldlen = startblockval(left.br_startblock) +

			startblockval(new->br_startblock) +

			startblockval(right.br_startblock);

		newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),

					 oldlen);

		left.br_startblock = nullstartblock(newlen);

		left.br_blockcount = temp;



		xfs_iext_remove(ip, icur, state);

		xfs_iext_prev(ifp, icur);

		xfs_iext_update_extent(ip, state, icur, &left);

		break;



	case BMAP_LEFT_CONTIG:

		/*

		 * New allocation is contiguous with a delayed allocation

		 * on the left.

		 * Merge the new allocation with the left neighbor.

		 */

		temp = left.br_blockcount + new->br_blockcount;



		oldlen = startblockval(left.br_startblock) +

			startblockval(new->br_startblock);

		newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),

					 oldlen);

		left.br_blockcount = temp;

		left.br_startblock = nullstartblock(newlen);



		xfs_iext_prev(ifp, icur);

		xfs_iext_update_extent(ip, state, icur, &left);

		break;



	case BMAP_RIGHT_CONTIG:

		/*

		 * New allocation is contiguous with a delayed allocation

		 * on the right.

		 * Merge the new allocation with the right neighbor.

		 */

		temp = new->br_blockcount + right.br_blockcount;

		oldlen = startblockval(new->br_startblock) +

			startblockval(right.br_startblock);

		newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),

					 oldlen);

		right.br_startoff = new->br_startoff;

		right.br_startblock = nullstartblock(newlen);

		right.br_blockcount = temp;

		xfs_iext_update_extent(ip, state, icur, &right);

		break;



	case 0:

		/*

		 * New allocation is not contiguous with another

		 * delayed allocation.

		 * Insert a new entry.

		 */

		oldlen = newlen = 0;

		xfs_iext_insert(ip, icur, new, state);

		break;

	}

	if (oldlen != newlen) {

		ASSERT(oldlen > newlen);

		xfs_add_fdblocks(ip->i_mount, oldlen - newlen);



		/*

		 * Nothing to do for disk quota accounting here.

		 */

		xfs_mod_delalloc(ip, 0, (int64_t)newlen - oldlen);

	}

}



/*

 * Convert a hole to a real allocation.

 */
@@ -4039,144 +3897,6 @@ xfs_bmapi_read( 
	return 0;

}



/*

 * Add a delayed allocation extent to an inode. Blocks are reserved from the

 * global pool and the extent inserted into the inode in-core extent tree.

 *

 * On entry, got refers to the first extent beyond the offset of the extent to

 * allocate or eof is specified if no such extent exists. On return, got refers

 * to the extent record that was inserted to the inode fork.

 *

 * Note that the allocated extent may have been merged with contiguous extents

 * during insertion into the inode fork. Thus, got does not reflect the current

 * state of the inode fork on return. If necessary, the caller can use lastx to

 * look up the updated record in the inode fork.

 */

int

xfs_bmapi_reserve_delalloc(

	struct xfs_inode	*ip,

	int			whichfork,

	xfs_fileoff_t		off,

	xfs_filblks_t		len,

	xfs_filblks_t		prealloc,

	struct xfs_bmbt_irec	*got,

	struct xfs_iext_cursor	*icur,

	int			eof)

{

	struct xfs_mount	*mp = ip->i_mount;

	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);

	xfs_extlen_t		alen;

	xfs_extlen_t		indlen;

	uint64_t		fdblocks;

	int			error;

	xfs_fileoff_t		aoff;

	bool			use_cowextszhint =

					whichfork == XFS_COW_FORK && !prealloc;



retry:

	/*

	 * Cap the alloc length. Keep track of prealloc so we know whether to

	 * tag the inode before we return.

	 */

	aoff = off;

	alen = XFS_FILBLKS_MIN(len + prealloc, XFS_MAX_BMBT_EXTLEN);

	if (!eof)

		alen = XFS_FILBLKS_MIN(alen, got->br_startoff - aoff);

	if (prealloc && alen >= len)

		prealloc = alen - len;



	/*

	 * If we're targetting the COW fork but aren't creating a speculative

	 * posteof preallocation, try to expand the reservation to align with

	 * the COW extent size hint if there's sufficient free space.

	 *

	 * Unlike the data fork, the CoW cancellation functions will free all

	 * the reservations at inactivation, so we don't require that every

	 * delalloc reservation have a dirty pagecache.

	 */

	if (use_cowextszhint) {

		struct xfs_bmbt_irec	prev;

		xfs_extlen_t		extsz = xfs_get_cowextsz_hint(ip);



		if (!xfs_iext_peek_prev_extent(ifp, icur, &prev))

			prev.br_startoff = NULLFILEOFF;



		error = xfs_bmap_extsize_align(mp, got, &prev, extsz, 0, eof,

					       1, 0, &aoff, &alen);

		ASSERT(!error);

	}



	/*

	 * Make a transaction-less quota reservation for delayed allocation

	 * blocks.  This number gets adjusted later.  We return if we haven't

	 * allocated blocks already inside this loop.

	 */

	error = xfs_quota_reserve_blkres(ip, alen);

	if (error)

		goto out;



	/*

	 * Split changing sb for alen and indlen since they could be coming

	 * from different places.

	 */

	indlen = (xfs_extlen_t)xfs_bmap_worst_indlen(ip, alen);

	ASSERT(indlen > 0);



	fdblocks = indlen;

	if (XFS_IS_REALTIME_INODE(ip)) {

		error = xfs_dec_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));

		if (error)

			goto out_unreserve_quota;

	} else {

		fdblocks += alen;

	}



	error = xfs_dec_fdblocks(mp, fdblocks, false);

	if (error)

		goto out_unreserve_frextents;



	ip->i_delayed_blks += alen;

	xfs_mod_delalloc(ip, alen, indlen);



	got->br_startoff = aoff;

	got->br_startblock = nullstartblock(indlen);

	got->br_blockcount = alen;

	got->br_state = XFS_EXT_NORM;



	xfs_bmap_add_extent_hole_delay(ip, whichfork, icur, got);



	/*

	 * Tag the inode if blocks were preallocated. Note that COW fork

	 * preallocation can occur at the start or end of the extent, even when

	 * prealloc == 0, so we must also check the aligned offset and length.

	 */

	if (whichfork == XFS_DATA_FORK && prealloc)

		xfs_inode_set_eofblocks_tag(ip);

	if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len))

		xfs_inode_set_cowblocks_tag(ip);



	return 0;



out_unreserve_frextents:

	if (XFS_IS_REALTIME_INODE(ip))

		xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, alen));

out_unreserve_quota:

	if (XFS_IS_QUOTA_ON(mp))

		xfs_quota_unreserve_blkres(ip, alen);

out:

	if (error == -ENOSPC || error == -EDQUOT) {

		trace_xfs_delalloc_enospc(ip, off, len);



		if (prealloc || use_cowextszhint) {

			/* retry without any preallocation */

			use_cowextszhint = false;

			prealloc = 0;

			goto retry;

		}

	}

	return error;

}



static int

xfs_bmapi_allocate(

	struct xfs_bmalloca	*bma)
@@ -4948,7 +4668,8 @@ xfs_bmap_del_extent_delay( 
	int			whichfork,

	struct xfs_iext_cursor	*icur,

	struct xfs_bmbt_irec	*got,

	struct xfs_bmbt_irec	*del)

	struct xfs_bmbt_irec	*del,

	uint32_t		bflags)	/* bmapi flags */

{

	struct xfs_mount	*mp = ip->i_mount;

	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
@@ -5068,10 +4789,18 @@ xfs_bmap_del_extent_delay( 
	da_diff = da_old - da_new;

	fdblocks = da_diff;



	if (isrt)

		xfs_add_frextents(mp, xfs_blen_to_rtbxlen(mp, del->br_blockcount));

	else

	if (bflags & XFS_BMAPI_REMAP) {

		;

	} else if (isrt) {

		xfs_rtbxlen_t	rtxlen;



		rtxlen = xfs_blen_to_rtbxlen(mp, del->br_blockcount);

		if (xfs_is_zoned_inode(ip))

			xfs_zoned_add_available(mp, rtxlen);

		xfs_add_frextents(mp, rtxlen);

	} else {

		fdblocks += del->br_blockcount;

	}



	xfs_add_fdblocks(mp, fdblocks);

	xfs_mod_delalloc(ip, -(int64_t)del->br_blockcount, -da_diff);
@@ -5670,7 +5399,8 @@ __xfs_bunmapi( 


delete:

		if (wasdel) {

			xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got, &del);

			xfs_bmap_del_extent_delay(ip, whichfork, &icur, &got,

					&del, flags);

		} else {

			error = xfs_bmap_del_extent_real(ip, tp, &icur, cur,

					&del, &tmp_logflags, whichfork,

fs/xfs/libxfs/xfs_bmap.h

+2 −5
Original line number Diff line number Diff line
@@ -204,7 +204,7 @@ int xfs_bunmapi(struct xfs_trans *tp, struct xfs_inode *ip, 
		xfs_extnum_t nexts, int *done);

void	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,

		struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,

		struct xfs_bmbt_irec *del);

		struct xfs_bmbt_irec *del, uint32_t bflags);

void	xfs_bmap_del_extent_cow(struct xfs_inode *ip,

		struct xfs_iext_cursor *cur, struct xfs_bmbt_irec *got,

		struct xfs_bmbt_irec *del);
@@ -219,10 +219,6 @@ int xfs_bmap_insert_extents(struct xfs_trans *tp, struct xfs_inode *ip, 
		bool *done, xfs_fileoff_t stop_fsb);

int	xfs_bmap_split_extent(struct xfs_trans *tp, struct xfs_inode *ip,

		xfs_fileoff_t split_offset);

int	xfs_bmapi_reserve_delalloc(struct xfs_inode *ip, int whichfork,

		xfs_fileoff_t off, xfs_filblks_t len, xfs_filblks_t prealloc,

		struct xfs_bmbt_irec *got, struct xfs_iext_cursor *cur,

		int eof);

int	xfs_bmapi_convert_delalloc(struct xfs_inode *ip, int whichfork,

		xfs_off_t offset, struct iomap *iomap, unsigned int *seq);

int	xfs_bmap_add_extent_unwritten_real(struct xfs_trans *tp,
@@ -233,6 +229,7 @@ xfs_extlen_t xfs_bmapi_minleft(struct xfs_trans *tp, struct xfs_inode *ip, 
		int fork);

int	xfs_bmap_btalloc_low_space(struct xfs_bmalloca *ap,

		struct xfs_alloc_arg *args);

xfs_filblks_t xfs_bmap_worst_indlen(struct xfs_inode *ip, xfs_filblks_t len);



enum xfs_bmap_intent_type {

	XFS_BMAP_MAP = 1,

fs/xfs/libxfs/xfs_format.h

+16 −4
Original line number Diff line number Diff line
@@ -178,9 +178,10 @@ typedef struct xfs_sb { 


	xfs_rgnumber_t	sb_rgcount;	/* number of realtime groups */

	xfs_rtxlen_t	sb_rgextents;	/* size of a realtime group in rtx */



	uint8_t		sb_rgblklog;    /* rt group number shift */

	uint8_t		sb_pad[7];	/* zeroes */

	xfs_rfsblock_t	sb_rtstart;	/* start of internal RT section (FSB) */

	xfs_filblks_t	sb_rtreserved;	/* reserved (zoned) RT blocks */



	/* must be padded to 64 bit alignment */

} xfs_sb_t;
@@ -270,9 +271,10 @@ struct xfs_dsb { 
	__be64		sb_metadirino;	/* metadata directory tree root */

	__be32		sb_rgcount;	/* # of realtime groups */

	__be32		sb_rgextents;	/* size of rtgroup in rtx */



	__u8		sb_rgblklog;    /* rt group number shift */

	__u8		sb_pad[7];	/* zeroes */

	__be64		sb_rtstart;	/* start of internal RT section (FSB) */

	__be64		sb_rtreserved;	/* reserved (zoned) RT blocks */



	/*

	 * The size of this structure must be padded to 64 bit alignment.
@@ -395,6 +397,9 @@ xfs_sb_has_ro_compat_feature( 
#define XFS_SB_FEAT_INCOMPAT_EXCHRANGE	(1 << 6)  /* exchangerange supported */

#define XFS_SB_FEAT_INCOMPAT_PARENT	(1 << 7)  /* parent pointers */

#define XFS_SB_FEAT_INCOMPAT_METADIR	(1 << 8)  /* metadata dir tree */

#define XFS_SB_FEAT_INCOMPAT_ZONED	(1 << 9)  /* zoned RT allocator */

#define XFS_SB_FEAT_INCOMPAT_ZONE_GAPS	(1 << 10) /* RTGs have LBA gaps */



#define XFS_SB_FEAT_INCOMPAT_ALL \

		(XFS_SB_FEAT_INCOMPAT_FTYPE | \

		 XFS_SB_FEAT_INCOMPAT_SPINODES | \
@@ -404,7 +409,9 @@ xfs_sb_has_ro_compat_feature( 
		 XFS_SB_FEAT_INCOMPAT_NREXT64 | \

		 XFS_SB_FEAT_INCOMPAT_EXCHRANGE | \

		 XFS_SB_FEAT_INCOMPAT_PARENT | \

		 XFS_SB_FEAT_INCOMPAT_METADIR)

		 XFS_SB_FEAT_INCOMPAT_METADIR | \

		 XFS_SB_FEAT_INCOMPAT_ZONED | \

		 XFS_SB_FEAT_INCOMPAT_ZONE_GAPS)



#define XFS_SB_FEAT_INCOMPAT_UNKNOWN	~XFS_SB_FEAT_INCOMPAT_ALL

static inline bool
@@ -952,7 +959,12 @@ struct xfs_dinode { 
	__be64		di_changecount;	/* number of attribute changes */

	__be64		di_lsn;		/* flush sequence */

	__be64		di_flags2;	/* more random flags */

	__be32		di_cowextsize;	/* basic cow extent size for file */

	union {

		/* basic cow extent size for (regular) file */

		__be32		di_cowextsize;

		/* used blocks in RTG for (zoned) rtrmap inode */

		__be32		di_used_blocks;

	};

	__u8		di_pad2[12];	/* more padding for future expansion */



	/* fields only written to during inode creation */