summaryrefslogtreecommitdiff
path: root/fs/xfs/libxfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs/libxfs')
-rw-r--r--fs/xfs/libxfs/xfs_ag.c2
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.h19
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c235
-rw-r--r--fs/xfs/libxfs/xfs_alloc.h18
-rw-r--r--fs/xfs/libxfs/xfs_alloc_btree.c64
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c55
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h3
-rw-r--r--fs/xfs/libxfs/xfs_bmap_btree.c2
-rw-r--r--fs/xfs/libxfs/xfs_btree.c51
-rw-r--r--fs/xfs/libxfs/xfs_btree.h16
-rw-r--r--fs/xfs/libxfs/xfs_defer.c4
-rw-r--r--fs/xfs/libxfs/xfs_dir2.c661
-rw-r--r--fs/xfs/libxfs/xfs_dir2.h49
-rw-r--r--fs/xfs/libxfs/xfs_dir2_data.c31
-rw-r--r--fs/xfs/libxfs/xfs_dir2_priv.h7
-rw-r--r--fs/xfs/libxfs/xfs_format.h9
-rw-r--r--fs/xfs/libxfs/xfs_ialloc.c20
-rw-r--r--fs/xfs/libxfs/xfs_ialloc_btree.c2
-rw-r--r--fs/xfs/libxfs/xfs_inode_util.c749
-rw-r--r--fs/xfs/libxfs/xfs_inode_util.h62
-rw-r--r--fs/xfs/libxfs/xfs_ondisk.h1
-rw-r--r--fs/xfs/libxfs/xfs_refcount.c156
-rw-r--r--fs/xfs/libxfs/xfs_refcount.h11
-rw-r--r--fs/xfs/libxfs/xfs_refcount_btree.c2
-rw-r--r--fs/xfs/libxfs/xfs_rmap.c266
-rw-r--r--fs/xfs/libxfs/xfs_rmap.h15
-rw-r--r--fs/xfs/libxfs/xfs_rmap_btree.c7
-rw-r--r--fs/xfs/libxfs/xfs_shared.h7
-rw-r--r--fs/xfs/libxfs/xfs_trans_inode.c2
-rw-r--r--fs/xfs/libxfs/xfs_trans_resv.c1
30 files changed, 1949 insertions, 578 deletions
diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c
index 240e079cb3fb..7e80732cb547 100644
--- a/fs/xfs/libxfs/xfs_ag.c
+++ b/fs/xfs/libxfs/xfs_ag.c
@@ -1008,7 +1008,7 @@ xfs_ag_shrink_space(
goto resv_err;
err2 = xfs_free_extent_later(*tpp, args.fsbno, delta, NULL,
- XFS_AG_RESV_NONE, true);
+ XFS_AG_RESV_NONE, XFS_FREE_EXTENT_SKIP_DISCARD);
if (err2)
goto resv_err;
diff --git a/fs/xfs/libxfs/xfs_ag_resv.h b/fs/xfs/libxfs/xfs_ag_resv.h
index ff20ed93de77..f247eeff7358 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.h
+++ b/fs/xfs/libxfs/xfs_ag_resv.h
@@ -33,23 +33,4 @@ xfs_perag_resv(
}
}
-/*
- * RMAPBT reservation accounting wrappers. Since rmapbt blocks are sourced from
- * the AGFL, they are allocated one at a time and the reservation updates don't
- * require a transaction.
- */
-static inline void
-xfs_ag_resv_rmapbt_alloc(
- struct xfs_mount *mp,
- xfs_agnumber_t agno)
-{
- struct xfs_alloc_arg args = { NULL };
- struct xfs_perag *pag;
-
- args.len = 1;
- pag = xfs_perag_get(mp, agno);
- xfs_ag_resv_alloc_extent(pag, XFS_AG_RESV_RMAPBT, &args);
- xfs_perag_put(pag);
-}
-
#endif /* __XFS_AG_RESV_H__ */
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 6c55a6e88eba..59326f84f6a5 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -27,6 +27,7 @@
#include "xfs_ag_resv.h"
#include "xfs_bmap.h"
#include "xfs_health.h"
+#include "xfs_extfree_item.h"
struct kmem_cache *xfs_extfree_item_cache;
@@ -466,6 +467,97 @@ xfs_alloc_fix_len(
}
/*
+ * Determine if the cursor points to the block that contains the right-most
+ * block of records in the by-count btree. This block contains the largest
+ * contiguous free extent in the AG, so if we modify a record in this block we
+ * need to call xfs_alloc_fixup_longest() once the modifications are done to
+ * ensure the agf->agf_longest field is kept up to date with the longest free
+ * extent tracked by the by-count btree.
+ */
+static bool
+xfs_alloc_cursor_at_lastrec(
+ struct xfs_btree_cur *cnt_cur)
+{
+ struct xfs_btree_block *block;
+ union xfs_btree_ptr ptr;
+ struct xfs_buf *bp;
+
+ block = xfs_btree_get_block(cnt_cur, 0, &bp);
+
+ xfs_btree_get_sibling(cnt_cur, block, &ptr, XFS_BB_RIGHTSIB);
+ return xfs_btree_ptr_is_null(cnt_cur, &ptr);
+}
+
+/*
+ * Find the rightmost record of the cntbt, and return the longest free space
+ * recorded in it. Simply set both the block number and the length to their
+ * maximum values before searching.
+ */
+static int
+xfs_cntbt_longest(
+ struct xfs_btree_cur *cnt_cur,
+ xfs_extlen_t *longest)
+{
+ struct xfs_alloc_rec_incore irec;
+ union xfs_btree_rec *rec;
+ int stat = 0;
+ int error;
+
+ memset(&cnt_cur->bc_rec, 0xFF, sizeof(cnt_cur->bc_rec));
+ error = xfs_btree_lookup(cnt_cur, XFS_LOOKUP_LE, &stat);
+ if (error)
+ return error;
+ if (!stat) {
+ /* totally empty tree */
+ *longest = 0;
+ return 0;
+ }
+
+ error = xfs_btree_get_rec(cnt_cur, &rec, &stat);
+ if (error)
+ return error;
+ if (XFS_IS_CORRUPT(cnt_cur->bc_mp, !stat)) {
+ xfs_btree_mark_sick(cnt_cur);
+ return -EFSCORRUPTED;
+ }
+
+ xfs_alloc_btrec_to_irec(rec, &irec);
+ *longest = irec.ar_blockcount;
+ return 0;
+}
+
+/*
+ * Update the longest contiguous free extent in the AG from the by-count cursor
+ * that is passed to us. This should be done at the end of any allocation or
+ * freeing operation that touches the longest extent in the btree.
+ *
+ * Needing to update the longest extent can be determined by calling
+ * xfs_alloc_cursor_at_lastrec() after the cursor is positioned for record
+ * modification but before the modification begins.
+ */
+static int
+xfs_alloc_fixup_longest(
+ struct xfs_btree_cur *cnt_cur)
+{
+ struct xfs_perag *pag = cnt_cur->bc_ag.pag;
+ struct xfs_buf *bp = cnt_cur->bc_ag.agbp;
+ struct xfs_agf *agf = bp->b_addr;
+ xfs_extlen_t longest = 0;
+ int error;
+
+ /* Lookup last rec in order to update AGF. */
+ error = xfs_cntbt_longest(cnt_cur, &longest);
+ if (error)
+ return error;
+
+ pag->pagf_longest = longest;
+ agf->agf_longest = cpu_to_be32(pag->pagf_longest);
+ xfs_alloc_log_agf(cnt_cur->bc_tp, bp, XFS_AGF_LONGEST);
+
+ return 0;
+}
+
+/*
* Update the two btrees, logically removing from freespace the extent
* starting at rbno, rlen blocks. The extent is contained within the
* actual (current) free extent fbno for flen blocks.
@@ -489,6 +581,7 @@ xfs_alloc_fixup_trees(
xfs_extlen_t nflen1=0; /* first new free length */
xfs_extlen_t nflen2=0; /* second new free length */
struct xfs_mount *mp;
+ bool fixup_longest = false;
mp = cnt_cur->bc_mp;
@@ -577,6 +670,10 @@ xfs_alloc_fixup_trees(
nfbno2 = rbno + rlen;
nflen2 = (fbno + flen) - nfbno2;
}
+
+ if (xfs_alloc_cursor_at_lastrec(cnt_cur))
+ fixup_longest = true;
+
/*
* Delete the entry from the by-size btree.
*/
@@ -654,6 +751,10 @@ xfs_alloc_fixup_trees(
return -EFSCORRUPTED;
}
}
+
+ if (fixup_longest)
+ return xfs_alloc_fixup_longest(cnt_cur);
+
return 0;
}
@@ -1932,7 +2033,7 @@ out_nominleft:
/*
* Free the extent starting at agno/bno for length.
*/
-STATIC int
+int
xfs_free_ag_extent(
struct xfs_trans *tp,
struct xfs_buf *agbp,
@@ -1956,6 +2057,7 @@ xfs_free_ag_extent(
int i;
int error;
struct xfs_perag *pag = agbp->b_pag;
+ bool fixup_longest = false;
bno_cur = cnt_cur = NULL;
mp = tp->t_mountp;
@@ -2219,8 +2321,13 @@ xfs_free_ag_extent(
}
xfs_btree_del_cursor(bno_cur, XFS_BTREE_NOERROR);
bno_cur = NULL;
+
/*
* In all cases we need to insert the new freespace in the by-size tree.
+ *
+ * If this new freespace is being inserted in the block that contains
+ * the largest free space in the btree, make sure we also fix up the
+ * agf->agf-longest tracker field.
*/
if ((error = xfs_alloc_lookup_eq(cnt_cur, nbno, nlen, &i)))
goto error0;
@@ -2229,6 +2336,8 @@ xfs_free_ag_extent(
error = -EFSCORRUPTED;
goto error0;
}
+ if (xfs_alloc_cursor_at_lastrec(cnt_cur))
+ fixup_longest = true;
if ((error = xfs_btree_insert(cnt_cur, &i)))
goto error0;
if (XFS_IS_CORRUPT(mp, i != 1)) {
@@ -2236,6 +2345,12 @@ xfs_free_ag_extent(
error = -EFSCORRUPTED;
goto error0;
}
+ if (fixup_longest) {
+ error = xfs_alloc_fixup_longest(cnt_cur);
+ if (error)
+ goto error0;
+ }
+
xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
cnt_cur = NULL;
@@ -2422,32 +2537,6 @@ xfs_alloc_space_available(
return true;
}
-int
-xfs_free_agfl_block(
- struct xfs_trans *tp,
- xfs_agnumber_t agno,
- xfs_agblock_t agbno,
- struct xfs_buf *agbp,
- struct xfs_owner_info *oinfo)
-{
- int error;
- struct xfs_buf *bp;
-
- error = xfs_free_ag_extent(tp, agbp, agno, agbno, 1, oinfo,
- XFS_AG_RESV_AGFL);
- if (error)
- return error;
-
- error = xfs_trans_get_buf(tp, tp->t_mountp->m_ddev_targp,
- XFS_AGB_TO_DADDR(tp->t_mountp, agno, agbno),
- tp->t_mountp->m_bsize, 0, &bp);
- if (error)
- return error;
- xfs_trans_binval(tp, bp);
-
- return 0;
-}
-
/*
* Check the agfl fields of the agf for inconsistency or corruption.
*
@@ -2536,48 +2625,6 @@ xfs_agfl_reset(
}
/*
- * Defer an AGFL block free. This is effectively equivalent to
- * xfs_free_extent_later() with some special handling particular to AGFL blocks.
- *
- * Deferring AGFL frees helps prevent log reservation overruns due to too many
- * allocation operations in a transaction. AGFL frees are prone to this problem
- * because for one they are always freed one at a time. Further, an immediate
- * AGFL block free can cause a btree join and require another block free before
- * the real allocation can proceed. Deferring the free disconnects freeing up
- * the AGFL slot from freeing the block.
- */
-static int
-xfs_defer_agfl_block(
- struct xfs_trans *tp,
- xfs_agnumber_t agno,
- xfs_agblock_t agbno,
- struct xfs_owner_info *oinfo)
-{
- struct xfs_mount *mp = tp->t_mountp;
- struct xfs_extent_free_item *xefi;
- xfs_fsblock_t fsbno = XFS_AGB_TO_FSB(mp, agno, agbno);
-
- ASSERT(xfs_extfree_item_cache != NULL);
- ASSERT(oinfo != NULL);
-
- if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, fsbno)))
- return -EFSCORRUPTED;
-
- xefi = kmem_cache_zalloc(xfs_extfree_item_cache,
- GFP_KERNEL | __GFP_NOFAIL);
- xefi->xefi_startblock = fsbno;
- xefi->xefi_blockcount = 1;
- xefi->xefi_owner = oinfo->oi_owner;
- xefi->xefi_agresv = XFS_AG_RESV_AGFL;
-
- trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1);
-
- xfs_extent_free_get_group(mp, xefi);
- xfs_defer_add(tp, &xefi->xefi_list, &xfs_agfl_free_defer_type);
- return 0;
-}
-
-/*
* Add the extent to the list of extents to be free at transaction end.
* The list is maintained sorted (by block number).
*/
@@ -2588,28 +2635,15 @@ xfs_defer_extent_free(
xfs_filblks_t len,
const struct xfs_owner_info *oinfo,
enum xfs_ag_resv_type type,
- bool skip_discard,
+ unsigned int free_flags,
struct xfs_defer_pending **dfpp)
{
struct xfs_extent_free_item *xefi;
struct xfs_mount *mp = tp->t_mountp;
-#ifdef DEBUG
- xfs_agnumber_t agno;
- xfs_agblock_t agbno;
- ASSERT(bno != NULLFSBLOCK);
- ASSERT(len > 0);
ASSERT(len <= XFS_MAX_BMBT_EXTLEN);
ASSERT(!isnullstartblock(bno));
- agno = XFS_FSB_TO_AGNO(mp, bno);
- agbno = XFS_FSB_TO_AGBNO(mp, bno);
- ASSERT(agno < mp->m_sb.sb_agcount);
- ASSERT(agbno < mp->m_sb.sb_agblocks);
- ASSERT(len < mp->m_sb.sb_agblocks);
- ASSERT(agbno + len <= mp->m_sb.sb_agblocks);
-#endif
- ASSERT(xfs_extfree_item_cache != NULL);
- ASSERT(type != XFS_AG_RESV_AGFL);
+ ASSERT(!(free_flags & ~XFS_FREE_EXTENT_ALL_FLAGS));
if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len)))
return -EFSCORRUPTED;
@@ -2619,7 +2653,7 @@ xfs_defer_extent_free(
xefi->xefi_startblock = bno;
xefi->xefi_blockcount = (xfs_extlen_t)len;
xefi->xefi_agresv = type;
- if (skip_discard)
+ if (free_flags & XFS_FREE_EXTENT_SKIP_DISCARD)
xefi->xefi_flags |= XFS_EFI_SKIP_DISCARD;
if (oinfo) {
ASSERT(oinfo->oi_offset == 0);
@@ -2632,12 +2666,8 @@ xfs_defer_extent_free(
} else {
xefi->xefi_owner = XFS_RMAP_OWN_NULL;
}
- trace_xfs_bmap_free_defer(mp,
- XFS_FSB_TO_AGNO(tp->t_mountp, bno), 0,
- XFS_FSB_TO_AGBNO(tp->t_mountp, bno), len);
- xfs_extent_free_get_group(mp, xefi);
- *dfpp = xfs_defer_add(tp, &xefi->xefi_list, &xfs_extent_free_defer_type);
+ xfs_extent_free_defer_add(tp, xefi, dfpp);
return 0;
}
@@ -2648,11 +2678,11 @@ xfs_free_extent_later(
xfs_filblks_t len,
const struct xfs_owner_info *oinfo,
enum xfs_ag_resv_type type,
- bool skip_discard)
+ unsigned int free_flags)
{
struct xfs_defer_pending *dontcare = NULL;
- return xfs_defer_extent_free(tp, bno, len, oinfo, type, skip_discard,
+ return xfs_defer_extent_free(tp, bno, len, oinfo, type, free_flags,
&dontcare);
}
@@ -2677,13 +2707,13 @@ xfs_free_extent_later(
int
xfs_alloc_schedule_autoreap(
const struct xfs_alloc_arg *args,
- bool skip_discard,
+ unsigned int free_flags,
struct xfs_alloc_autoreap *aarp)
{
int error;
error = xfs_defer_extent_free(args->tp, args->fsbno, args->len,
- &args->oinfo, args->resv, skip_discard, &aarp->dfp);
+ &args->oinfo, args->resv, free_flags, &aarp->dfp);
if (error)
return error;
@@ -2895,8 +2925,21 @@ xfs_alloc_fix_freelist(
if (error)
goto out_agbp_relse;
- /* defer agfl frees */
- error = xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo);
+ /*
+ * Defer the AGFL block free.
+ *
+ * This helps to prevent log reservation overruns due to too
+ * many allocation operations in a transaction. AGFL frees are
+ * prone to this problem because for one they are always freed
+ * one at a time. Further, an immediate AGFL block free can
+ * cause a btree join and require another block free before the
+ * real allocation can proceed.
+ * Deferring the free disconnects freeing up the AGFL slot from
+ * freeing the block.
+ */
+ error = xfs_free_extent_later(tp,
+ XFS_AGB_TO_FSB(mp, args->agno, bno), 1,
+ &targs.oinfo, XFS_AG_RESV_AGFL, 0);
if (error)
goto out_agbp_relse;
}
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 0b956f8b9d5a..fae170825be0 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -80,6 +80,10 @@ int xfs_alloc_get_freelist(struct xfs_perag *pag, struct xfs_trans *tp,
int xfs_alloc_put_freelist(struct xfs_perag *pag, struct xfs_trans *tp,
struct xfs_buf *agfbp, struct xfs_buf *agflbp,
xfs_agblock_t bno, int btreeblk);
+int xfs_free_ag_extent(struct xfs_trans *tp, struct xfs_buf *agbp,
+ xfs_agnumber_t agno, xfs_agblock_t bno,
+ xfs_extlen_t len, const struct xfs_owner_info *oinfo,
+ enum xfs_ag_resv_type type);
/*
* Compute and fill in value of m_alloc_maxlevels.
@@ -194,8 +198,6 @@ int xfs_alloc_read_agf(struct xfs_perag *pag, struct xfs_trans *tp, int flags,
struct xfs_buf **agfbpp);
int xfs_alloc_read_agfl(struct xfs_perag *pag, struct xfs_trans *tp,
struct xfs_buf **bpp);
-int xfs_free_agfl_block(struct xfs_trans *, xfs_agnumber_t, xfs_agblock_t,
- struct xfs_buf *, struct xfs_owner_info *);
int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, uint32_t alloc_flags);
int xfs_free_extent_fix_freelist(struct xfs_trans *tp, struct xfs_perag *pag,
struct xfs_buf **agbp);
@@ -233,7 +235,12 @@ xfs_buf_to_agfl_bno(
int xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno,
xfs_filblks_t len, const struct xfs_owner_info *oinfo,
- enum xfs_ag_resv_type type, bool skip_discard);
+ enum xfs_ag_resv_type type, unsigned int free_flags);
+
+/* Don't issue a discard for the blocks freed. */
+#define XFS_FREE_EXTENT_SKIP_DISCARD (1U << 0)
+
+#define XFS_FREE_EXTENT_ALL_FLAGS (XFS_FREE_EXTENT_SKIP_DISCARD)
/*
* List of extents to be free "later".
@@ -249,9 +256,6 @@ struct xfs_extent_free_item {
enum xfs_ag_resv_type xefi_agresv;
};
-void xfs_extent_free_get_group(struct xfs_mount *mp,
- struct xfs_extent_free_item *xefi);
-
#define XFS_EFI_SKIP_DISCARD (1U << 0) /* don't issue discard */
#define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */
#define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */
@@ -262,7 +266,7 @@ struct xfs_alloc_autoreap {
};
int xfs_alloc_schedule_autoreap(const struct xfs_alloc_arg *args,
- bool skip_discard, struct xfs_alloc_autoreap *aarp);
+ unsigned int free_flags, struct xfs_alloc_autoreap *aarp);
void xfs_alloc_cancel_autoreap(struct xfs_trans *tp,
struct xfs_alloc_autoreap *aarp);
void xfs_alloc_commit_autoreap(struct xfs_trans *tp,
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index 6ef5ddd89600..585e98e87ef9 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -115,67 +115,6 @@ xfs_allocbt_free_block(
return 0;
}
-/*
- * Update the longest extent in the AGF
- */
-STATIC void
-xfs_allocbt_update_lastrec(
- struct xfs_btree_cur *cur,
- const struct xfs_btree_block *block,
- const union xfs_btree_rec *rec,
- int ptr,
- int reason)
-{
- struct xfs_agf *agf = cur->bc_ag.agbp->b_addr;
- struct xfs_perag *pag;
- __be32 len;
- int numrecs;
-
- ASSERT(!xfs_btree_is_bno(cur->bc_ops));
-
- switch (reason) {
- case LASTREC_UPDATE:
- /*
- * If this is the last leaf block and it's the last record,
- * then update the size of the longest extent in the AG.
- */
- if (ptr != xfs_btree_get_numrecs(block))
- return;
- len = rec->alloc.ar_blockcount;
- break;
- case LASTREC_INSREC:
- if (be32_to_cpu(rec->alloc.ar_blockcount) <=
- be32_to_cpu(agf->agf_longest))
- return;
- len = rec->alloc.ar_blockcount;
- break;
- case LASTREC_DELREC:
- numrecs = xfs_btree_get_numrecs(block);
- if (ptr <= numrecs)
- return;
- ASSERT(ptr == numrecs + 1);
-
- if (numrecs) {
- xfs_alloc_rec_t *rrp;
-
- rrp = XFS_ALLOC_REC_ADDR(cur->bc_mp, block, numrecs);
- len = rrp->ar_blockcount;
- } else {
- len = 0;
- }
-
- break;
- default:
- ASSERT(0);
- return;
- }
-
- agf->agf_longest = len;
- pag = cur->bc_ag.agbp->b_pag;
- pag->pagf_longest = be32_to_cpu(len);
- xfs_alloc_log_agf(cur->bc_tp, cur->bc_ag.agbp, XFS_AGF_LONGEST);
-}
-
STATIC int
xfs_allocbt_get_minrecs(
struct xfs_btree_cur *cur,
@@ -493,7 +432,6 @@ const struct xfs_btree_ops xfs_bnobt_ops = {
.set_root = xfs_allocbt_set_root,
.alloc_block = xfs_allocbt_alloc_block,
.free_block = xfs_allocbt_free_block,
- .update_lastrec = xfs_allocbt_update_lastrec,
.get_minrecs = xfs_allocbt_get_minrecs,
.get_maxrecs = xfs_allocbt_get_maxrecs,
.init_key_from_rec = xfs_allocbt_init_key_from_rec,
@@ -511,7 +449,6 @@ const struct xfs_btree_ops xfs_bnobt_ops = {
const struct xfs_btree_ops xfs_cntbt_ops = {
.name = "cnt",
.type = XFS_BTREE_TYPE_AG,
- .geom_flags = XFS_BTGEO_LASTREC_UPDATE,
.rec_len = sizeof(xfs_alloc_rec_t),
.key_len = sizeof(xfs_alloc_key_t),
@@ -525,7 +462,6 @@ const struct xfs_btree_ops xfs_cntbt_ops = {
.set_root = xfs_allocbt_set_root,
.alloc_block = xfs_allocbt_alloc_block,
.free_block = xfs_allocbt_free_block,
- .update_lastrec = xfs_allocbt_update_lastrec,
.get_minrecs = xfs_allocbt_get_minrecs,
.get_maxrecs = xfs_allocbt_get_maxrecs,
.init_key_from_rec = xfs_allocbt_init_key_from_rec,
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index 6af6f744fdd6..7df74c35d9f9 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -39,6 +39,7 @@
#include "xfs_health.h"
#include "xfs_bmap_item.h"
#include "xfs_symlink_remote.h"
+#include "xfs_inode_util.h"
struct kmem_cache *xfs_bmap_intent_cache;
@@ -604,7 +605,7 @@ xfs_bmap_btree_to_extents(
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork);
error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo,
- XFS_AG_RESV_NONE, false);
+ XFS_AG_RESV_NONE, 0);
if (error)
return error;
@@ -5380,11 +5381,15 @@ xfs_bmap_del_extent_real(
error = xfs_rtfree_blocks(tp, del->br_startblock,
del->br_blockcount);
} else {
+ unsigned int efi_flags = 0;
+
+ if ((bflags & XFS_BMAPI_NODISCARD) ||
+ del->br_state == XFS_EXT_UNWRITTEN)
+ efi_flags |= XFS_FREE_EXTENT_SKIP_DISCARD;
+
error = xfs_free_extent_later(tp, del->br_startblock,
del->br_blockcount, NULL,
- XFS_AG_RESV_NONE,
- ((bflags & XFS_BMAPI_NODISCARD) ||
- del->br_state == XFS_EXT_UNWRITTEN));
+ XFS_AG_RESV_NONE, efi_flags);
}
if (error)
return error;
@@ -6454,3 +6459,45 @@ xfs_bmap_query_all(
return xfs_btree_query_all(cur, xfs_bmap_query_range_helper, &query);
}
+
+/* Helper function to extract extent size hint from inode */
+xfs_extlen_t
+xfs_get_extsz_hint(
+ struct xfs_inode *ip)
+{
+ /*
+ * No point in aligning allocations if we need to COW to actually
+ * write to them.
+ */
+ if (xfs_is_always_cow_inode(ip))
+ return 0;
+ if ((ip->i_diflags & XFS_DIFLAG_EXTSIZE) && ip->i_extsize)
+ return ip->i_extsize;
+ if (XFS_IS_REALTIME_INODE(ip) &&
+ ip->i_mount->m_sb.sb_rextsize > 1)
+ return ip->i_mount->m_sb.sb_rextsize;
+ return 0;
+}
+
+/*
+ * Helper function to extract CoW extent size hint from inode.
+ * Between the extent size hint and the CoW extent size hint, we
+ * return the greater of the two. If the value is zero (automatic),
+ * use the default size.
+ */
+xfs_extlen_t
+xfs_get_cowextsz_hint(
+ struct xfs_inode *ip)
+{
+ xfs_extlen_t a, b;
+
+ a = 0;
+ if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
+ a = ip->i_cowextsize;
+ b = xfs_get_extsz_hint(ip);
+
+ a = max(a, b);
+ if (a == 0)
+ return XFS_DEFAULT_COWEXTSZ_HINT;
+ return a;
+}
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index 667b0c2b33d1..7592d46e97c6 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -296,4 +296,7 @@ typedef int (*xfs_bmap_query_range_fn)(
int xfs_bmap_query_all(struct xfs_btree_cur *cur, xfs_bmap_query_range_fn fn,
void *priv);
+xfs_extlen_t xfs_get_extsz_hint(struct xfs_inode *ip);
+xfs_extlen_t xfs_get_cowextsz_hint(struct xfs_inode *ip);
+
#endif /* __XFS_BMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index f5d84dcb58da..d1b06ccde19e 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -282,7 +282,7 @@ xfs_bmbt_free_block(
xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork);
error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo,
- XFS_AG_RESV_NONE, false);
+ XFS_AG_RESV_NONE, 0);
if (error)
return error;
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index d29547572a68..a5c4af148853 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -1331,30 +1331,6 @@ xfs_btree_init_block_cur(
xfs_btree_owner(cur));
}
-/*
- * Return true if ptr is the last record in the btree and
- * we need to track updates to this record. The decision
- * will be further refined in the update_lastrec method.
- */
-STATIC int
-xfs_btree_is_lastrec(
- struct xfs_btree_cur *cur,
- struct xfs_btree_block *block,
- int level)
-{
- union xfs_btree_ptr ptr;
-
- if (level > 0)
- return 0;
- if (!(cur->bc_ops->geom_flags & XFS_BTGEO_LASTREC_UPDATE))
- return 0;
-
- xfs_btree_get_sibling(cur, block, &ptr, XFS_BB_RIGHTSIB);
- if (!xfs_btree_ptr_is_null(cur, &ptr))
- return 0;
- return 1;
-}
-
STATIC void
xfs_btree_buf_to_ptr(
struct xfs_btree_cur *cur,
@@ -2420,15 +2396,6 @@ xfs_btree_update(
xfs_btree_copy_recs(cur, rp, rec, 1);
xfs_btree_log_recs(cur, bp, ptr, ptr);
- /*
- * If we are tracking the last record in the tree and
- * we are at the far right edge of the tree, update it.
- */
- if (xfs_btree_is_lastrec(cur, block, 0)) {
- cur->bc_ops->update_lastrec(cur, block, rec,
- ptr, LASTREC_UPDATE);
- }
-
/* Pass new key value up to our parent. */
if (xfs_btree_needs_key_update(cur, ptr)) {
error = xfs_btree_update_keys(cur, 0);
@@ -3618,15 +3585,6 @@ xfs_btree_insrec(
}
/*
- * If we are tracking the last record in the tree and
- * we are at the far right edge of the tree, update it.
- */
- if (xfs_btree_is_lastrec(cur, block, level)) {
- cur->bc_ops->update_lastrec(cur, block, rec,
- ptr, LASTREC_INSREC);
- }
-
- /*
* Return the new block number, if any.
* If there is one, give back a record value and a cursor too.
*/
@@ -3984,15 +3942,6 @@ xfs_btree_delrec(
xfs_btree_log_block(cur, bp, XFS_BB_NUMRECS);
/*
- * If we are tracking the last record in the tree and
- * we are at the far right edge of the tree, update it.
- */
- if (xfs_btree_is_lastrec(cur, block, level)) {
- cur->bc_ops->update_lastrec(cur, block, NULL,
- ptr, LASTREC_DELREC);
- }
-
- /*
* We're at the root level. First, shrink the root block in-memory.
* Try to get rid of the next level down. If we can't then there's
* nothing left to do.
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index f93374278aa1..10b7ddc3b2b3 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -154,12 +154,6 @@ struct xfs_btree_ops {
int *stat);
int (*free_block)(struct xfs_btree_cur *cur, struct xfs_buf *bp);
- /* update last record information */
- void (*update_lastrec)(struct xfs_btree_cur *cur,
- const struct xfs_btree_block *block,
- const union xfs_btree_rec *rec,
- int ptr, int reason);
-
/* records in block/level */
int (*get_minrecs)(struct xfs_btree_cur *cur, int level);
int (*get_maxrecs)(struct xfs_btree_cur *cur, int level);
@@ -222,15 +216,7 @@ struct xfs_btree_ops {
};
/* btree geometry flags */
-#define XFS_BTGEO_LASTREC_UPDATE (1U << 0) /* track last rec externally */
-#define XFS_BTGEO_OVERLAPPING (1U << 1) /* overlapping intervals */
-
-/*
- * Reasons for the update_lastrec method to be called.
- */
-#define LASTREC_UPDATE 0
-#define LASTREC_INSREC 1
-#define LASTREC_DELREC 2
+#define XFS_BTGEO_OVERLAPPING (1U << 0) /* overlapping intervals */
union xfs_btree_irec {
diff --git a/fs/xfs/libxfs/xfs_defer.c b/fs/xfs/libxfs/xfs_defer.c
index 4a078e07e1a0..40021849b42f 100644
--- a/fs/xfs/libxfs/xfs_defer.c
+++ b/fs/xfs/libxfs/xfs_defer.c
@@ -12,12 +12,14 @@
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_trans.h"
+#include "xfs_trans_priv.h"
#include "xfs_buf_item.h"
#include "xfs_inode.h"
#include "xfs_inode_item.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_log.h"
+#include "xfs_log_priv.h"
#include "xfs_rmap.h"
#include "xfs_refcount.h"
#include "xfs_bmap.h"
@@ -556,7 +558,7 @@ xfs_defer_relog(
* the log threshold once per call.
*/
if (threshold_lsn == NULLCOMMITLSN) {
- threshold_lsn = xlog_grant_push_threshold(log, 0);
+ threshold_lsn = xfs_ail_get_push_target(log->l_ailp);
if (threshold_lsn == NULLCOMMITLSN)
break;
}
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 457f9a38f850..202468223bf9 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -19,6 +19,11 @@
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_health.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
+#include "xfs_parent.h"
+#include "xfs_ag.h"
+#include "xfs_ialloc.h"
const struct xfs_name xfs_name_dotdot = {
.name = (const unsigned char *)"..",
@@ -584,9 +589,9 @@ xfs_dir_replace(
*/
int
xfs_dir_canenter(
- xfs_trans_t *tp,
- xfs_inode_t *dp,
- struct xfs_name *name) /* name of entry to add */
+ struct xfs_trans *tp,
+ struct xfs_inode *dp,
+ const struct xfs_name *name) /* name of entry to add */
{
return xfs_dir_createname(tp, dp, name, 0, 0);
}
@@ -756,3 +761,653 @@ xfs_dir2_compname(
return xfs_ascii_ci_compname(args, name, len);
return xfs_da_compname(args, name, len);
}
+
+#ifdef CONFIG_XFS_LIVE_HOOKS
+/*
+ * Use a static key here to reduce the overhead of directory live update hooks.
+ * If the compiler supports jump labels, the static branch will be replaced by
+ * a nop sled when there are no hook users. Online fsck is currently the only
+ * caller, so this is a reasonable tradeoff.
+ *
+ * Note: Patching the kernel code requires taking the cpu hotplug lock. Other
+ * parts of the kernel allocate memory with that lock held, which means that
+ * XFS callers cannot hold any locks that might be used by memory reclaim or
+ * writeback when calling the static_branch_{inc,dec} functions.
+ */
+DEFINE_STATIC_XFS_HOOK_SWITCH(xfs_dir_hooks_switch);
+
+void
+xfs_dir_hook_disable(void)
+{
+ xfs_hooks_switch_off(&xfs_dir_hooks_switch);
+}
+
+void
+xfs_dir_hook_enable(void)
+{
+ xfs_hooks_switch_on(&xfs_dir_hooks_switch);
+}
+
+/* Call hooks for a directory update relating to a child dirent update. */
+inline void
+xfs_dir_update_hook(
+ struct xfs_inode *dp,
+ struct xfs_inode *ip,
+ int delta,
+ const struct xfs_name *name)
+{
+ if (xfs_hooks_switched_on(&xfs_dir_hooks_switch)) {
+ struct xfs_dir_update_params p = {
+ .dp = dp,
+ .ip = ip,
+ .delta = delta,
+ .name = name,
+ };
+ struct xfs_mount *mp = ip->i_mount;
+
+ xfs_hooks_call(&mp->m_dir_update_hooks, 0, &p);
+ }
+}
+
+/* Call the specified function during a directory update. */
+int
+xfs_dir_hook_add(
+ struct xfs_mount *mp,
+ struct xfs_dir_hook *hook)
+{
+ return xfs_hooks_add(&mp->m_dir_update_hooks, &hook->dirent_hook);
+}
+
+/* Stop calling the specified function during a directory update. */
+void
+xfs_dir_hook_del(
+ struct xfs_mount *mp,
+ struct xfs_dir_hook *hook)
+{
+ xfs_hooks_del(&mp->m_dir_update_hooks, &hook->dirent_hook);
+}
+
+/* Configure directory update hook functions. */
+void
+xfs_dir_hook_setup(
+ struct xfs_dir_hook *hook,
+ notifier_fn_t mod_fn)
+{
+ xfs_hook_setup(&hook->dirent_hook, mod_fn);
+}
+#endif /* CONFIG_XFS_LIVE_HOOKS */
+
+/*
+ * Given a directory @dp, a newly allocated inode @ip, and a @name, link @ip
+ * into @dp under the given @name. If @ip is a directory, it will be
+ * initialized. Both inodes must have the ILOCK held and the transaction must
+ * have sufficient blocks reserved.
+ */
+int
+xfs_dir_create_child(
+ struct xfs_trans *tp,
+ unsigned int resblks,
+ struct xfs_dir_update *du)
+{
+ struct xfs_inode *dp = du->dp;
+ const struct xfs_name *name = du->name;
+ struct xfs_inode *ip = du->ip;
+ int error;
+
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
+ xfs_assert_ilocked(dp, XFS_ILOCK_EXCL);
+
+ error = xfs_dir_createname(tp, dp, name, ip->i_ino, resblks);
+ if (error) {
+ ASSERT(error != -ENOSPC);
+ return error;
+ }
+
+ xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+ xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
+
+ if (S_ISDIR(VFS_I(ip)->i_mode)) {
+ error = xfs_dir_init(tp, ip, dp);
+ if (error)
+ return error;
+
+ xfs_bumplink(tp, dp);
+ }
+
+ /*
+ * If we have parent pointers, we need to add the attribute containing
+ * the parent information now.
+ */
+ if (du->ppargs) {
+ error = xfs_parent_addname(tp, du->ppargs, dp, name, ip);
+ if (error)
+ return error;
+ }
+
+ xfs_dir_update_hook(dp, ip, 1, name);
+ return 0;
+}
+
+/*
+ * Given a directory @dp, an existing non-directory inode @ip, and a @name,
+ * link @ip into @dp under the given @name. Both inodes must have the ILOCK
+ * held.
+ */
+int
+xfs_dir_add_child(
+ struct xfs_trans *tp,
+ unsigned int resblks,
+ struct xfs_dir_update *du)
+{
+ struct xfs_inode *dp = du->dp;
+ const struct xfs_name *name = du->name;
+ struct xfs_inode *ip = du->ip;
+ struct xfs_mount *mp = tp->t_mountp;
+ int error;
+
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
+ xfs_assert_ilocked(dp, XFS_ILOCK_EXCL);
+ ASSERT(!S_ISDIR(VFS_I(ip)->i_mode));
+
+ if (!resblks) {
+ error = xfs_dir_canenter(tp, dp, name);
+ if (error)
+ return error;
+ }
+
+ /*
+ * Handle initial link state of O_TMPFILE inode
+ */
+ if (VFS_I(ip)->i_nlink == 0) {
+ struct xfs_perag *pag;
+
+ pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
+ error = xfs_iunlink_remove(tp, pag, ip);
+ xfs_perag_put(pag);
+ if (error)
+ return error;
+ }
+
+ error = xfs_dir_createname(tp, dp, name, ip->i_ino, resblks);
+ if (error)
+ return error;
+
+ xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+ xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
+
+ xfs_bumplink(tp, ip);
+
+ /*
+ * If we have parent pointers, we now need to add the parent record to
+ * the attribute fork of the inode. If this is the initial parent
+ * attribute, we need to create it correctly, otherwise we can just add
+ * the parent to the inode.
+ */
+ if (du->ppargs) {
+ error = xfs_parent_addname(tp, du->ppargs, dp, name, ip);
+ if (error)
+ return error;
+ }
+
+ xfs_dir_update_hook(dp, ip, 1, name);
+ return 0;
+}
+
+/*
+ * Given a directory @dp, a child @ip, and a @name, remove the (@name, @ip)
+ * entry from the directory. Both inodes must have the ILOCK held.
+ */
+int
+xfs_dir_remove_child(
+ struct xfs_trans *tp,
+ unsigned int resblks,
+ struct xfs_dir_update *du)
+{
+ struct xfs_inode *dp = du->dp;
+ const struct xfs_name *name = du->name;
+ struct xfs_inode *ip = du->ip;
+ int error;
+
+ xfs_assert_ilocked(ip, XFS_ILOCK_EXCL);
+ xfs_assert_ilocked(dp, XFS_ILOCK_EXCL);
+
+ /*
+ * If we're removing a directory perform some additional validation.
+ */
+ if (S_ISDIR(VFS_I(ip)->i_mode)) {
+ ASSERT(VFS_I(ip)->i_nlink >= 2);
+ if (VFS_I(ip)->i_nlink != 2)
+ return -ENOTEMPTY;
+ if (!xfs_dir_isempty(ip))
+ return -ENOTEMPTY;
+
+ /* Drop the link from ip's "..". */
+ error = xfs_droplink(tp, dp);
+ if (error)
+ return error;
+
+ /* Drop the "." link from ip to self. */
+ error = xfs_droplink(tp, ip);
+ if (error)
+ return error;
+
+ /*
+ * Point the unlinked child directory's ".." entry to the root
+ * directory to eliminate back-references to inodes that may
+ * get freed before the child directory is closed. If the fs
+ * gets shrunk, this can lead to dirent inode validation errors.
+ */
+ if (dp->i_ino != tp->t_mountp->m_sb.sb_rootino) {
+ error = xfs_dir_replace(tp, ip, &xfs_name_dotdot,
+ tp->t_mountp->m_sb.sb_rootino, 0);
+ if (error)
+ return error;
+ }
+ } else {
+ /*
+ * When removing a non-directory we need to log the parent
+ * inode here. For a directory this is done implicitly
+ * by the xfs_droplink call for the ".." entry.
+ */
+ xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
+ }
+ xfs_trans_ichgtime(tp, dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+
+ /* Drop the link from dp to ip. */
+ error = xfs_droplink(tp, ip);
+ if (error)
+ return error;
+
+ error = xfs_dir_removename(tp, dp, name, ip->i_ino, resblks);
+ if (error) {
+ ASSERT(error != -ENOENT);
+ return error;
+ }
+
+ /* Remove parent pointer. */
+ if (du->ppargs) {
+ error = xfs_parent_removename(tp, du->ppargs, dp, name, ip);
+ if (error)
+ return error;
+ }
+
+ xfs_dir_update_hook(dp, ip, -1, name);
+ return 0;
+}
+
+/*
+ * Exchange the entry (@name1, @ip1) in directory @dp1 with the entry (@name2,
+ * @ip2) in directory @dp2, and update '..' @ip1 and @ip2's entries as needed.
+ * @ip1 and @ip2 need not be of the same type.
+ *
+ * All inodes must have the ILOCK held, and both entries must already exist.
+ */
+int
+xfs_dir_exchange_children(
+ struct xfs_trans *tp,
+ struct xfs_dir_update *du1,
+ struct xfs_dir_update *du2,
+ unsigned int spaceres)
+{
+ struct xfs_inode *dp1 = du1->dp;
+ const struct xfs_name *name1 = du1->name;
+ struct xfs_inode *ip1 = du1->ip;
+ struct xfs_inode *dp2 = du2->dp;
+ const struct xfs_name *name2 = du2->name;
+ struct xfs_inode *ip2 = du2->ip;
+ int ip1_flags = 0;
+ int ip2_flags = 0;
+ int dp2_flags = 0;
+ int error;
+
+ /* Swap inode number for dirent in first parent */
+ error = xfs_dir_replace(tp, dp1, name1, ip2->i_ino, spaceres);
+ if (error)
+ return error;
+
+ /* Swap inode number for dirent in second parent */
+ error = xfs_dir_replace(tp, dp2, name2, ip1->i_ino, spaceres);
+ if (error)
+ return error;
+
+ /*
+ * If we're renaming one or more directories across different parents,
+ * update the respective ".." entries (and link counts) to match the new
+ * parents.
+ */
+ if (dp1 != dp2) {
+ dp2_flags = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+
+ if (S_ISDIR(VFS_I(ip2)->i_mode)) {
+ error = xfs_dir_replace(tp, ip2, &xfs_name_dotdot,
+ dp1->i_ino, spaceres);
+ if (error)
+ return error;
+
+ /* transfer ip2 ".." reference to dp1 */
+ if (!S_ISDIR(VFS_I(ip1)->i_mode)) {
+ error = xfs_droplink(tp, dp2);
+ if (error)
+ return error;
+ xfs_bumplink(tp, dp1);
+ }
+
+ /*
+ * Although ip1 isn't changed here, userspace needs
+ * to be warned about the change, so that applications
+ * relying on it (like backup ones), will properly
+ * notify the change
+ */
+ ip1_flags |= XFS_ICHGTIME_CHG;
+ ip2_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+ }
+
+ if (S_ISDIR(VFS_I(ip1)->i_mode)) {
+ error = xfs_dir_replace(tp, ip1, &xfs_name_dotdot,
+ dp2->i_ino, spaceres);
+ if (error)
+ return error;
+
+ /* transfer ip1 ".." reference to dp2 */
+ if (!S_ISDIR(VFS_I(ip2)->i_mode)) {
+ error = xfs_droplink(tp, dp1);
+ if (error)
+ return error;
+ xfs_bumplink(tp, dp2);
+ }
+
+ /*
+ * Although ip2 isn't changed here, userspace needs
+ * to be warned about the change, so that applications
+ * relying on it (like backup ones), will properly
+ * notify the change
+ */
+ ip1_flags |= XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG;
+ ip2_flags |= XFS_ICHGTIME_CHG;
+ }
+ }
+
+ if (ip1_flags) {
+ xfs_trans_ichgtime(tp, ip1, ip1_flags);
+ xfs_trans_log_inode(tp, ip1, XFS_ILOG_CORE);
+ }
+ if (ip2_flags) {
+ xfs_trans_ichgtime(tp, ip2, ip2_flags);
+ xfs_trans_log_inode(tp, ip2, XFS_ILOG_CORE);
+ }
+ if (dp2_flags) {
+ xfs_trans_ichgtime(tp, dp2, dp2_flags);
+ xfs_trans_log_inode(tp, dp2, XFS_ILOG_CORE);
+ }
+ xfs_trans_ichgtime(tp, dp1, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+ xfs_trans_log_inode(tp, dp1, XFS_ILOG_CORE);
+
+ /* Schedule parent pointer replacements */
+ if (du1->ppargs) {
+ error = xfs_parent_replacename(tp, du1->ppargs, dp1, name1,
+ dp2, name2, ip1);
+ if (error)
+ return error;
+ }
+
+ if (du2->ppargs) {
+ error = xfs_parent_replacename(tp, du2->ppargs, dp2, name2,
+ dp1, name1, ip2);
+ if (error)
+ return error;
+ }
+
+ /*
+ * Inform our hook clients that we've finished an exchange operation as
+ * follows: removed the source and target files from their directories;
+ * added the target to the source directory; and added the source to
+ * the target directory. All inodes are locked, so it's ok to model a
+ * rename this way so long as we say we deleted entries before we add
+ * new ones.
+ */
+ xfs_dir_update_hook(dp1, ip1, -1, name1);
+ xfs_dir_update_hook(dp2, ip2, -1, name2);
+ xfs_dir_update_hook(dp1, ip2, 1, name1);
+ xfs_dir_update_hook(dp2, ip1, 1, name2);
+ return 0;
+}
+
+/*
+ * Given an entry (@src_name, @src_ip) in directory @src_dp, make the entry
+ * @target_name in directory @target_dp point to @src_ip and remove the
+ * original entry, cleaning up everything left behind.
+ *
+ * Cleanup involves dropping a link count on @target_ip, and either removing
+ * the (@src_name, @src_ip) entry from @src_dp or simply replacing the entry
+ * with (@src_name, @wip) if a whiteout inode @wip is supplied.
+ *
+ * All inodes must have the ILOCK held. We assume that if @src_ip is a
+ * directory then its '..' doesn't already point to @target_dp, and that @wip
+ * is a freshly allocated whiteout.
+ */
+int
+xfs_dir_rename_children(
+ struct xfs_trans *tp,
+ struct xfs_dir_update *du_src,
+ struct xfs_dir_update *du_tgt,
+ unsigned int spaceres,
+ struct xfs_dir_update *du_wip)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_inode *src_dp = du_src->dp;
+ const struct xfs_name *src_name = du_src->name;
+ struct xfs_inode *src_ip = du_src->ip;
+ struct xfs_inode *target_dp = du_tgt->dp;
+ const struct xfs_name *target_name = du_tgt->name;
+ struct xfs_inode *target_ip = du_tgt->ip;
+ bool new_parent = (src_dp != target_dp);
+ bool src_is_directory;
+ int error;
+
+ src_is_directory = S_ISDIR(VFS_I(src_ip)->i_mode);
+
+ /*
+ * Check for expected errors before we dirty the transaction
+ * so we can return an error without a transaction abort.
+ */
+ if (target_ip == NULL) {
+ /*
+ * If there's no space reservation, check the entry will
+ * fit before actually inserting it.
+ */
+ if (!spaceres) {
+ error = xfs_dir_canenter(tp, target_dp, target_name);
+ if (error)
+ return error;
+ }
+ } else {
+ /*
+ * If target exists and it's a directory, check that whether
+ * it can be destroyed.
+ */
+ if (S_ISDIR(VFS_I(target_ip)->i_mode) &&
+ (!xfs_dir_isempty(target_ip) ||
+ (VFS_I(target_ip)->i_nlink > 2)))
+ return -EEXIST;
+ }
+
+ /*
+ * Directory entry creation below may acquire the AGF. Remove
+ * the whiteout from the unlinked list first to preserve correct
+ * AGI/AGF locking order. This dirties the transaction so failures
+ * after this point will abort and log recovery will clean up the
+ * mess.
+ *
+ * For whiteouts, we need to bump the link count on the whiteout
+ * inode. After this point, we have a real link, clear the tmpfile
+ * state flag from the inode so it doesn't accidentally get misused
+ * in future.
+ */
+ if (du_wip->ip) {
+ struct xfs_perag *pag;
+
+ ASSERT(VFS_I(du_wip->ip)->i_nlink == 0);
+
+ pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, du_wip->ip->i_ino));
+ error = xfs_iunlink_remove(tp, pag, du_wip->ip);
+ xfs_perag_put(pag);
+ if (error)
+ return error;
+
+ xfs_bumplink(tp, du_wip->ip);
+ }
+
+ /*
+ * Set up the target.
+ */
+ if (target_ip == NULL) {
+ /*
+ * If target does not exist and the rename crosses
+ * directories, adjust the target directory link count
+ * to account for the ".." reference from the new entry.
+ */
+ error = xfs_dir_createname(tp, target_dp, target_name,
+ src_ip->i_ino, spaceres);
+ if (error)
+ return error;
+
+ xfs_trans_ichgtime(tp, target_dp,
+ XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+
+ if (new_parent && src_is_directory) {
+ xfs_bumplink(tp, target_dp);
+ }
+ } else { /* target_ip != NULL */
+ /*
+ * Link the source inode under the target name.
+ * If the source inode is a directory and we are moving
+ * it across directories, its ".." entry will be
+ * inconsistent until we replace that down below.
+ *
+ * In case there is already an entry with the same
+ * name at the destination directory, remove it first.
+ */
+ error = xfs_dir_replace(tp, target_dp, target_name,
+ src_ip->i_ino, spaceres);
+ if (error)
+ return error;
+
+ xfs_trans_ichgtime(tp, target_dp,
+ XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+
+ /*
+ * Decrement the link count on the target since the target
+ * dir no longer points to it.
+ */
+ error = xfs_droplink(tp, target_ip);
+ if (error)
+ return error;
+
+ if (src_is_directory) {
+ /*
+ * Drop the link from the old "." entry.
+ */
+ error = xfs_droplink(tp, target_ip);
+ if (error)
+ return error;
+ }
+ } /* target_ip != NULL */
+
+ /*
+ * Remove the source.
+ */
+ if (new_parent && src_is_directory) {
+ /*
+ * Rewrite the ".." entry to point to the new
+ * directory.
+ */
+ error = xfs_dir_replace(tp, src_ip, &xfs_name_dotdot,
+ target_dp->i_ino, spaceres);
+ ASSERT(error != -EEXIST);
+ if (error)
+ return error;
+ }
+
+ /*
+ * We always want to hit the ctime on the source inode.
+ *
+ * This isn't strictly required by the standards since the source
+ * inode isn't really being changed, but old unix file systems did
+ * it and some incremental backup programs won't work without it.
+ */
+ xfs_trans_ichgtime(tp, src_ip, XFS_ICHGTIME_CHG);
+ xfs_trans_log_inode(tp, src_ip, XFS_ILOG_CORE);
+
+ /*
+ * Adjust the link count on src_dp. This is necessary when
+ * renaming a directory, either within one parent when
+ * the target existed, or across two parent directories.
+ */
+ if (src_is_directory && (new_parent || target_ip != NULL)) {
+
+ /*
+ * Decrement link count on src_directory since the
+ * entry that's moved no longer points to it.
+ */
+ error = xfs_droplink(tp, src_dp);
+ if (error)
+ return error;
+ }
+
+ /*
+ * For whiteouts, we only need to update the source dirent with the
+ * inode number of the whiteout inode rather than removing it
+ * altogether.
+ */
+ if (du_wip->ip)
+ error = xfs_dir_replace(tp, src_dp, src_name, du_wip->ip->i_ino,
+ spaceres);
+ else
+ error = xfs_dir_removename(tp, src_dp, src_name, src_ip->i_ino,
+ spaceres);
+ if (error)
+ return error;
+
+ xfs_trans_ichgtime(tp, src_dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+ xfs_trans_log_inode(tp, src_dp, XFS_ILOG_CORE);
+ if (new_parent)
+ xfs_trans_log_inode(tp, target_dp, XFS_ILOG_CORE);
+
+ /* Schedule parent pointer updates. */
+ if (du_wip->ppargs) {
+ error = xfs_parent_addname(tp, du_wip->ppargs, src_dp,
+ src_name, du_wip->ip);
+ if (error)
+ return error;
+ }
+
+ if (du_src->ppargs) {
+ error = xfs_parent_replacename(tp, du_src->ppargs, src_dp,
+ src_name, target_dp, target_name, src_ip);
+ if (error)
+ return error;
+ }
+
+ if (du_tgt->ppargs) {
+ error = xfs_parent_removename(tp, du_tgt->ppargs, target_dp,
+ target_name, target_ip);
+ if (error)
+ return error;
+ }
+
+ /*
+ * Inform our hook clients that we've finished a rename operation as
+ * follows: removed the source and target files from their directories;
+ * that we've added the source to the target directory; and finally
+ * that we've added the whiteout, if there was one. All inodes are
+ * locked, so it's ok to model a rename this way so long as we say we
+ * deleted entries before we add new ones.
+ */
+ if (target_ip)
+ xfs_dir_update_hook(target_dp, target_ip, -1, target_name);
+ xfs_dir_update_hook(src_dp, src_ip, -1, src_name);
+ xfs_dir_update_hook(target_dp, src_ip, 1, target_name);
+ if (du_wip->ip)
+ xfs_dir_update_hook(src_dp, du_wip->ip, 1, src_name);
+ return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index 6dbe6e9ecb49..576068ed81fa 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -74,7 +74,7 @@ extern int xfs_dir_replace(struct xfs_trans *tp, struct xfs_inode *dp,
const struct xfs_name *name, xfs_ino_t inum,
xfs_extlen_t tot);
extern int xfs_dir_canenter(struct xfs_trans *tp, struct xfs_inode *dp,
- struct xfs_name *name);
+ const struct xfs_name *name);
int xfs_dir_lookup_args(struct xfs_da_args *args);
int xfs_dir_createname_args(struct xfs_da_args *args);
@@ -309,4 +309,51 @@ static inline unsigned char xfs_ascii_ci_xfrm(unsigned char c)
return c;
}
+struct xfs_dir_update_params {
+ const struct xfs_inode *dp;
+ const struct xfs_inode *ip;
+ const struct xfs_name *name;
+ int delta;
+};
+
+#ifdef CONFIG_XFS_LIVE_HOOKS
+void xfs_dir_update_hook(struct xfs_inode *dp, struct xfs_inode *ip,
+ int delta, const struct xfs_name *name);
+
+struct xfs_dir_hook {
+ struct xfs_hook dirent_hook;
+};
+
+void xfs_dir_hook_disable(void);
+void xfs_dir_hook_enable(void);
+
+int xfs_dir_hook_add(struct xfs_mount *mp, struct xfs_dir_hook *hook);
+void xfs_dir_hook_del(struct xfs_mount *mp, struct xfs_dir_hook *hook);
+void xfs_dir_hook_setup(struct xfs_dir_hook *hook, notifier_fn_t mod_fn);
+#else
+# define xfs_dir_update_hook(dp, ip, delta, name) ((void)0)
+#endif /* CONFIG_XFS_LIVE_HOOKS */
+
+struct xfs_parent_args;
+
+struct xfs_dir_update {
+ struct xfs_inode *dp;
+ const struct xfs_name *name;
+ struct xfs_inode *ip;
+ struct xfs_parent_args *ppargs;
+};
+
+int xfs_dir_create_child(struct xfs_trans *tp, unsigned int resblks,
+ struct xfs_dir_update *du);
+int xfs_dir_add_child(struct xfs_trans *tp, unsigned int resblks,
+ struct xfs_dir_update *du);
+int xfs_dir_remove_child(struct xfs_trans *tp, unsigned int resblks,
+ struct xfs_dir_update *du);
+
+int xfs_dir_exchange_children(struct xfs_trans *tp, struct xfs_dir_update *du1,
+ struct xfs_dir_update *du2, unsigned int spaceres);
+int xfs_dir_rename_children(struct xfs_trans *tp, struct xfs_dir_update *du_src,
+ struct xfs_dir_update *du_tgt, unsigned int spaceres,
+ struct xfs_dir_update *du_wip);
+
#endif /* __XFS_DIR2_H__ */
diff --git a/fs/xfs/libxfs/xfs_dir2_data.c b/fs/xfs/libxfs/xfs_dir2_data.c
index ea0b9628df18..a16b05c43e2e 100644
--- a/fs/xfs/libxfs/xfs_dir2_data.c
+++ b/fs/xfs/libxfs/xfs_dir2_data.c
@@ -178,6 +178,14 @@ __xfs_dir3_data_check(
while (offset < end) {
struct xfs_dir2_data_unused *dup = bp->b_addr + offset;
struct xfs_dir2_data_entry *dep = bp->b_addr + offset;
+ unsigned int reclen;
+
+ /*
+ * Are the remaining bytes large enough to hold an
+ * unused entry?
+ */
+ if (offset > end - xfs_dir2_data_unusedsize(1))
+ return __this_address;
/*
* If it's unused, look for the space in the bestfree table.
@@ -187,9 +195,13 @@ __xfs_dir3_data_check(
if (be16_to_cpu(dup->freetag) == XFS_DIR2_DATA_FREE_TAG) {
xfs_failaddr_t fa;
+ reclen = xfs_dir2_data_unusedsize(
+ be16_to_cpu(dup->length));
if (lastfree != 0)
return __this_address;
- if (offset + be16_to_cpu(dup->length) > end)
+ if (be16_to_cpu(dup->length) != reclen)
+ return __this_address;
+ if (offset + reclen > end)
return __this_address;
if (be16_to_cpu(*xfs_dir2_data_unused_tag_p(dup)) !=
offset)
@@ -207,10 +219,18 @@ __xfs_dir3_data_check(
be16_to_cpu(bf[2].length))
return __this_address;
}
- offset += be16_to_cpu(dup->length);
+ offset += reclen;
lastfree = 1;
continue;
}
+
+ /*
+ * This is not an unused entry. Are the remaining bytes
+ * large enough for a dirent with a single-byte name?
+ */
+ if (offset > end - xfs_dir2_data_entsize(mp, 1))
+ return __this_address;
+
/*
* It's a real entry. Validate the fields.
* If this is a block directory then make sure it's
@@ -219,9 +239,10 @@ __xfs_dir3_data_check(
*/
if (dep->namelen == 0)
return __this_address;
- if (!xfs_verify_dir_ino(mp, be64_to_cpu(dep->inumber)))
+ reclen = xfs_dir2_data_entsize(mp, dep->namelen);
+ if (offset + reclen > end)
return __this_address;
- if (offset + xfs_dir2_data_entsize(mp, dep->namelen) > end)
+ if (!xfs_verify_dir_ino(mp, be64_to_cpu(dep->inumber)))
return __this_address;
if (be16_to_cpu(*xfs_dir2_data_entry_tag_p(mp, dep)) != offset)
return __this_address;
@@ -245,7 +266,7 @@ __xfs_dir3_data_check(
if (i >= be32_to_cpu(btp->count))
return __this_address;
}
- offset += xfs_dir2_data_entsize(mp, dep->namelen);
+ offset += reclen;
}
/*
* Need to have seen all the entries and all the bestfree slots.
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index 3befb32509fa..10041350274a 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -190,6 +190,13 @@ extern int xfs_readdir(struct xfs_trans *tp, struct xfs_inode *dp,
struct dir_context *ctx, size_t bufsize);
static inline unsigned int
+xfs_dir2_data_unusedsize(
+ unsigned int len)
+{
+ return round_up(len, XFS_DIR2_DATA_ALIGN);
+}
+
+static inline unsigned int
xfs_dir2_data_entsize(
struct xfs_mount *mp,
unsigned int namelen)
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 61f51becff4f..e1bfee0c3b1a 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -90,8 +90,7 @@ struct xfs_ifork;
#define XFSLABEL_MAX 12
/*
- * Superblock - in core version. Must match the ondisk version below.
- * Must be padded to 64 bit alignment.
+ * Superblock - in core version. Must be padded to 64 bit alignment.
*/
typedef struct xfs_sb {
uint32_t sb_magicnum; /* magic number == XFS_SB_MAGIC */
@@ -178,10 +177,8 @@ typedef struct xfs_sb {
/* must be padded to 64 bit alignment */
} xfs_sb_t;
-#define XFS_SB_CRC_OFF offsetof(struct xfs_sb, sb_crc)
-
/*
- * Superblock - on disk version. Must match the in core version above.
+ * Superblock - on disk version.
* Must be padded to 64 bit alignment.
*/
struct xfs_dsb {
@@ -265,6 +262,8 @@ struct xfs_dsb {
/* must be padded to 64 bit alignment */
};
+#define XFS_SB_CRC_OFF offsetof(struct xfs_dsb, sb_crc)
+
/*
* Misc. Flags - warning - these will be cleared by xfs_repair unless
* a feature bit is set when the flag is used.
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index 14c81f227c5b..0af5b7a33d05 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -1946,6 +1946,21 @@ retry:
}
return -ENOSPC;
}
+
+ /*
+ * Protect against obviously corrupt allocation btree records. Later
+ * xfs_iget checks will catch re-allocation of other active in-memory
+ * and on-disk inodes. If we don't catch reallocating the parent inode
+ * here we will deadlock in xfs_iget() so we have to do these checks
+ * first.
+ */
+ if (ino == parent || !xfs_verify_dir_ino(mp, ino)) {
+ xfs_alert(mp, "Allocated a known in-use inode 0x%llx!", ino);
+ xfs_agno_mark_sick(mp, XFS_INO_TO_AGNO(mp, ino),
+ XFS_SICK_AG_INOBT);
+ return -EFSCORRUPTED;
+ }
+
*new_ino = ino;
return 0;
}
@@ -1975,7 +1990,7 @@ xfs_difree_inode_chunk(
return xfs_free_extent_later(tp,
XFS_AGB_TO_FSB(mp, agno, sagbno),
M_IGEO(mp)->ialloc_blks, &XFS_RMAP_OINFO_INODES,
- XFS_AG_RESV_NONE, false);
+ XFS_AG_RESV_NONE, 0);
}
/* holemask is only 16-bits (fits in an unsigned long) */
@@ -2021,8 +2036,7 @@ xfs_difree_inode_chunk(
ASSERT(contigblk % mp->m_sb.sb_spino_align == 0);
error = xfs_free_extent_later(tp,
XFS_AGB_TO_FSB(mp, agno, agbno), contigblk,
- &XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE,
- false);
+ &XFS_RMAP_OINFO_INODES, XFS_AG_RESV_NONE, 0);
if (error)
return error;
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 42e9fd47f6c7..496e2f72a85b 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -170,7 +170,7 @@ __xfs_inobt_free_block(
xfs_inobt_mod_blockcount(cur, -1);
fsbno = XFS_DADDR_TO_FSB(cur->bc_mp, xfs_buf_daddr(bp));
return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
- &XFS_RMAP_OINFO_INOBT, resv, false);
+ &XFS_RMAP_OINFO_INOBT, resv, 0);
}
STATIC int
diff --git a/fs/xfs/libxfs/xfs_inode_util.c b/fs/xfs/libxfs/xfs_inode_util.c
new file mode 100644
index 000000000000..032333289113
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_inode_util.c
@@ -0,0 +1,749 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2000-2006 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ */
+#include <linux/iversion.h>
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_inode.h"
+#include "xfs_inode_util.h"
+#include "xfs_trans.h"
+#include "xfs_ialloc.h"
+#include "xfs_health.h"
+#include "xfs_bmap.h"
+#include "xfs_error.h"
+#include "xfs_trace.h"
+#include "xfs_ag.h"
+#include "xfs_iunlink_item.h"
+#include "xfs_inode_item.h"
+
+uint16_t
+xfs_flags2diflags(
+ struct xfs_inode *ip,
+ unsigned int xflags)
+{
+ /* can't set PREALLOC this way, just preserve it */
+ uint16_t di_flags =
+ (ip->i_diflags & XFS_DIFLAG_PREALLOC);
+
+ if (xflags & FS_XFLAG_IMMUTABLE)
+ di_flags |= XFS_DIFLAG_IMMUTABLE;
+ if (xflags & FS_XFLAG_APPEND)
+ di_flags |= XFS_DIFLAG_APPEND;
+ if (xflags & FS_XFLAG_SYNC)
+ di_flags |= XFS_DIFLAG_SYNC;
+ if (xflags & FS_XFLAG_NOATIME)
+ di_flags |= XFS_DIFLAG_NOATIME;
+ if (xflags & FS_XFLAG_NODUMP)
+ di_flags |= XFS_DIFLAG_NODUMP;
+ if (xflags & FS_XFLAG_NODEFRAG)
+ di_flags |= XFS_DIFLAG_NODEFRAG;
+ if (xflags & FS_XFLAG_FILESTREAM)
+ di_flags |= XFS_DIFLAG_FILESTREAM;
+ if (S_ISDIR(VFS_I(ip)->i_mode)) {
+ if (xflags & FS_XFLAG_RTINHERIT)
+ di_flags |= XFS_DIFLAG_RTINHERIT;
+ if (xflags & FS_XFLAG_NOSYMLINKS)
+ di_flags |= XFS_DIFLAG_NOSYMLINKS;
+ if (xflags & FS_XFLAG_EXTSZINHERIT)
+ di_flags |= XFS_DIFLAG_EXTSZINHERIT;
+ if (xflags & FS_XFLAG_PROJINHERIT)
+ di_flags |= XFS_DIFLAG_PROJINHERIT;
+ } else if (S_ISREG(VFS_I(ip)->i_mode)) {
+ if (xflags & FS_XFLAG_REALTIME)
+ di_flags |= XFS_DIFLAG_REALTIME;
+ if (xflags & FS_XFLAG_EXTSIZE)
+ di_flags |= XFS_DIFLAG_EXTSIZE;
+ }
+
+ return di_flags;
+}
+
+uint64_t
+xfs_flags2diflags2(
+ struct xfs_inode *ip,
+ unsigned int xflags)
+{
+ uint64_t di_flags2 =
+ (ip->i_diflags2 & (XFS_DIFLAG2_REFLINK |
+ XFS_DIFLAG2_BIGTIME |
+ XFS_DIFLAG2_NREXT64));
+
+ if (xflags & FS_XFLAG_DAX)
+ di_flags2 |= XFS_DIFLAG2_DAX;
+ if (xflags & FS_XFLAG_COWEXTSIZE)
+ di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
+
+ return di_flags2;
+}
+
+uint32_t
+xfs_ip2xflags(
+ struct xfs_inode *ip)
+{
+ uint32_t flags = 0;
+
+ if (ip->i_diflags & XFS_DIFLAG_ANY) {
+ if (ip->i_diflags & XFS_DIFLAG_REALTIME)
+ flags |= FS_XFLAG_REALTIME;
+ if (ip->i_diflags & XFS_DIFLAG_PREALLOC)
+ flags |= FS_XFLAG_PREALLOC;
+ if (ip->i_diflags & XFS_DIFLAG_IMMUTABLE)
+ flags |= FS_XFLAG_IMMUTABLE;
+ if (ip->i_diflags & XFS_DIFLAG_APPEND)
+ flags |= FS_XFLAG_APPEND;
+ if (ip->i_diflags & XFS_DIFLAG_SYNC)
+ flags |= FS_XFLAG_SYNC;
+ if (ip->i_diflags & XFS_DIFLAG_NOATIME)
+ flags |= FS_XFLAG_NOATIME;
+ if (ip->i_diflags & XFS_DIFLAG_NODUMP)
+ flags |= FS_XFLAG_NODUMP;
+ if (ip->i_diflags & XFS_DIFLAG_RTINHERIT)
+ flags |= FS_XFLAG_RTINHERIT;
+ if (ip->i_diflags & XFS_DIFLAG_PROJINHERIT)
+ flags |= FS_XFLAG_PROJINHERIT;
+ if (ip->i_diflags & XFS_DIFLAG_NOSYMLINKS)
+ flags |= FS_XFLAG_NOSYMLINKS;
+ if (ip->i_diflags & XFS_DIFLAG_EXTSIZE)
+ flags |= FS_XFLAG_EXTSIZE;
+ if (ip->i_diflags & XFS_DIFLAG_EXTSZINHERIT)
+ flags |= FS_XFLAG_EXTSZINHERIT;
+ if (ip->i_diflags & XFS_DIFLAG_NODEFRAG)
+ flags |= FS_XFLAG_NODEFRAG;
+ if (ip->i_diflags & XFS_DIFLAG_FILESTREAM)
+ flags |= FS_XFLAG_FILESTREAM;
+ }
+
+ if (ip->i_diflags2 & XFS_DIFLAG2_ANY) {
+ if (ip->i_diflags2 & XFS_DIFLAG2_DAX)
+ flags |= FS_XFLAG_DAX;
+ if (ip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE)
+ flags |= FS_XFLAG_COWEXTSIZE;
+ }
+
+ if (xfs_inode_has_attr_fork(ip))
+ flags |= FS_XFLAG_HASATTR;
+ return flags;
+}
+
+prid_t
+xfs_get_initial_prid(struct xfs_inode *dp)
+{
+ if (dp->i_diflags & XFS_DIFLAG_PROJINHERIT)
+ return dp->i_projid;
+
+ /* Assign to the root project by default. */
+ return 0;
+}
+
+/* Propagate di_flags from a parent inode to a child inode. */
+static inline void
+xfs_inode_inherit_flags(
+ struct xfs_inode *ip,
+ const struct xfs_inode *pip)
+{
+ unsigned int di_flags = 0;
+ xfs_failaddr_t failaddr;
+ umode_t mode = VFS_I(ip)->i_mode;
+
+ if (S_ISDIR(mode)) {
+ if (pip->i_diflags & XFS_DIFLAG_RTINHERIT)
+ di_flags |= XFS_DIFLAG_RTINHERIT;
+ if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
+ di_flags |= XFS_DIFLAG_EXTSZINHERIT;
+ ip->i_extsize = pip->i_extsize;
+ }
+ if (pip->i_diflags & XFS_DIFLAG_PROJINHERIT)
+ di_flags |= XFS_DIFLAG_PROJINHERIT;
+ } else if (S_ISREG(mode)) {
+ if ((pip->i_diflags & XFS_DIFLAG_RTINHERIT) &&
+ xfs_has_realtime(ip->i_mount))
+ di_flags |= XFS_DIFLAG_REALTIME;
+ if (pip->i_diflags & XFS_DIFLAG_EXTSZINHERIT) {
+ di_flags |= XFS_DIFLAG_EXTSIZE;
+ ip->i_extsize = pip->i_extsize;
+ }
+ }
+ if ((pip->i_diflags & XFS_DIFLAG_NOATIME) &&
+ xfs_inherit_noatime)
+ di_flags |= XFS_DIFLAG_NOATIME;
+ if ((pip->i_diflags & XFS_DIFLAG_NODUMP) &&
+ xfs_inherit_nodump)
+ di_flags |= XFS_DIFLAG_NODUMP;
+ if ((pip->i_diflags & XFS_DIFLAG_SYNC) &&
+ xfs_inherit_sync)
+ di_flags |= XFS_DIFLAG_SYNC;
+ if ((pip->i_diflags & XFS_DIFLAG_NOSYMLINKS) &&
+ xfs_inherit_nosymlinks)
+ di_flags |= XFS_DIFLAG_NOSYMLINKS;
+ if ((pip->i_diflags & XFS_DIFLAG_NODEFRAG) &&
+ xfs_inherit_nodefrag)
+ di_flags |= XFS_DIFLAG_NODEFRAG;
+ if (pip->i_diflags & XFS_DIFLAG_FILESTREAM)
+ di_flags |= XFS_DIFLAG_FILESTREAM;
+
+ ip->i_diflags |= di_flags;
+
+ /*
+ * Inode verifiers on older kernels only check that the extent size
+ * hint is an integer multiple of the rt extent size on realtime files.
+ * They did not check the hint alignment on a directory with both
+ * rtinherit and extszinherit flags set. If the misaligned hint is
+ * propagated from a directory into a new realtime file, new file
+ * allocations will fail due to math errors in the rt allocator and/or
+ * trip the verifiers. Validate the hint settings in the new file so
+ * that we don't let broken hints propagate.
+ */
+ failaddr = xfs_inode_validate_extsize(ip->i_mount, ip->i_extsize,
+ VFS_I(ip)->i_mode, ip->i_diflags);
+ if (failaddr) {
+ ip->i_diflags &= ~(XFS_DIFLAG_EXTSIZE |
+ XFS_DIFLAG_EXTSZINHERIT);
+ ip->i_extsize = 0;
+ }
+}
+
+/* Propagate di_flags2 from a parent inode to a child inode. */
+static inline void
+xfs_inode_inherit_flags2(
+ struct xfs_inode *ip,
+ const struct xfs_inode *pip)
+{
+ xfs_failaddr_t failaddr;
+
+ if (pip->i_diflags2 & XFS_DIFLAG2_COWEXTSIZE) {
+ ip->i_diflags2 |= XFS_DIFLAG2_COWEXTSIZE;
+ ip->i_cowextsize = pip->i_cowextsize;
+ }
+ if (pip->i_diflags2 & XFS_DIFLAG2_DAX)
+ ip->i_diflags2 |= XFS_DIFLAG2_DAX;
+
+ /* Don't let invalid cowextsize hints propagate. */
+ failaddr = xfs_inode_validate_cowextsize(ip->i_mount, ip->i_cowextsize,
+ VFS_I(ip)->i_mode, ip->i_diflags, ip->i_diflags2);
+ if (failaddr) {
+ ip->i_diflags2 &= ~XFS_DIFLAG2_COWEXTSIZE;
+ ip->i_cowextsize = 0;
+ }
+}
+
+/*
+ * If we need to create attributes immediately after allocating the inode,
+ * initialise an empty attribute fork right now. We use the default fork offset
+ * for attributes here as we don't know exactly what size or how many
+ * attributes we might be adding. We can do this safely here because we know
+ * the data fork is completely empty and this saves us from needing to run a
+ * separate transaction to set the fork offset in the immediate future.
+ *
+ * If we have parent pointers and the caller hasn't told us that the file will
+ * never be linked into a directory tree, we /must/ create the attr fork.
+ */
+static inline bool
+xfs_icreate_want_attrfork(
+ struct xfs_mount *mp,
+ const struct xfs_icreate_args *args)
+{
+ if (args->flags & XFS_ICREATE_INIT_XATTRS)
+ return true;
+
+ if (!(args->flags & XFS_ICREATE_UNLINKABLE) && xfs_has_parent(mp))
+ return true;
+
+ return false;
+}
+
+/* Initialise an inode's attributes. */
+void
+xfs_inode_init(
+ struct xfs_trans *tp,
+ const struct xfs_icreate_args *args,
+ struct xfs_inode *ip)
+{
+ struct xfs_inode *pip = args->pip;
+ struct inode *dir = pip ? VFS_I(pip) : NULL;
+ struct xfs_mount *mp = tp->t_mountp;
+ struct inode *inode = VFS_I(ip);
+ unsigned int flags;
+ int times = XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG |
+ XFS_ICHGTIME_ACCESS;
+
+ if (args->flags & XFS_ICREATE_TMPFILE)
+ set_nlink(inode, 0);
+ else if (S_ISDIR(args->mode))
+ set_nlink(inode, 2);
+ else
+ set_nlink(inode, 1);
+ inode->i_rdev = args->rdev;
+
+ if (!args->idmap || pip == NULL) {
+ /* creating a tree root, sb rooted, or detached file */
+ inode->i_uid = GLOBAL_ROOT_UID;
+ inode->i_gid = GLOBAL_ROOT_GID;
+ ip->i_projid = 0;
+ inode->i_mode = args->mode;
+ } else {
+ /* creating a child in the directory tree */
+ if (dir && !(dir->i_mode & S_ISGID) && xfs_has_grpid(mp)) {
+ inode_fsuid_set(inode, args->idmap);
+ inode->i_gid = dir->i_gid;
+ inode->i_mode = args->mode;
+ } else {
+ inode_init_owner(args->idmap, inode, dir, args->mode);
+ }
+
+ /*
+ * If the group ID of the new file does not match the effective
+ * group ID or one of the supplementary group IDs, the S_ISGID
+ * bit is cleared (and only if the irix_sgid_inherit
+ * compatibility variable is set).
+ */
+ if (irix_sgid_inherit && (inode->i_mode & S_ISGID) &&
+ !vfsgid_in_group_p(i_gid_into_vfsgid(args->idmap, inode)))
+ inode->i_mode &= ~S_ISGID;
+
+ ip->i_projid = pip ? xfs_get_initial_prid(pip) : 0;
+ }
+
+ ip->i_disk_size = 0;
+ ip->i_df.if_nextents = 0;
+ ASSERT(ip->i_nblocks == 0);
+
+ ip->i_extsize = 0;
+ ip->i_diflags = 0;
+
+ if (xfs_has_v3inodes(mp)) {
+ inode_set_iversion(inode, 1);
+ ip->i_cowextsize = 0;
+ times |= XFS_ICHGTIME_CREATE;
+ }
+
+ xfs_trans_ichgtime(tp, ip, times);
+
+ flags = XFS_ILOG_CORE;
+ switch (args->mode & S_IFMT) {
+ case S_IFIFO:
+ case S_IFCHR:
+ case S_IFBLK:
+ case S_IFSOCK:
+ ip->i_df.if_format = XFS_DINODE_FMT_DEV;
+ flags |= XFS_ILOG_DEV;
+ break;
+ case S_IFREG:
+ case S_IFDIR:
+ if (pip && (pip->i_diflags & XFS_DIFLAG_ANY))
+ xfs_inode_inherit_flags(ip, pip);
+ if (pip && (pip->i_diflags2 & XFS_DIFLAG2_ANY))
+ xfs_inode_inherit_flags2(ip, pip);
+ fallthrough;
+ case S_IFLNK:
+ ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
+ ip->i_df.if_bytes = 0;
+ ip->i_df.if_data = NULL;
+ break;
+ default:
+ ASSERT(0);
+ }
+
+ if (xfs_icreate_want_attrfork(mp, args)) {
+ ip->i_forkoff = xfs_default_attroffset(ip) >> 3;
+ xfs_ifork_init_attr(ip, XFS_DINODE_FMT_EXTENTS, 0);
+
+ if (!xfs_has_attr(mp)) {
+ spin_lock(&mp->m_sb_lock);
+ xfs_add_attr(mp);
+ spin_unlock(&mp->m_sb_lock);
+ xfs_log_sb(tp);
+ }
+ }
+
+ xfs_trans_log_inode(tp, ip, flags);
+}
+
+/*
+ * In-Core Unlinked List Lookups
+ * =============================
+ *
+ * Every inode is supposed to be reachable from some other piece of metadata
+ * with the exception of the root directory. Inodes with a connection to a
+ * file descriptor but not linked from anywhere in the on-disk directory tree
+ * are collectively known as unlinked inodes, though the filesystem itself
+ * maintains links to these inodes so that on-disk metadata are consistent.
+ *
+ * XFS implements a per-AG on-disk hash table of unlinked inodes. The AGI
+ * header contains a number of buckets that point to an inode, and each inode
+ * record has a pointer to the next inode in the hash chain. This
+ * singly-linked list causes scaling problems in the iunlink remove function
+ * because we must walk that list to find the inode that points to the inode
+ * being removed from the unlinked hash bucket list.
+ *
+ * Hence we keep an in-memory double linked list to link each inode on an
+ * unlinked list. Because there are 64 unlinked lists per AGI, keeping pointer
+ * based lists would require having 64 list heads in the perag, one for each
+ * list. This is expensive in terms of memory (think millions of AGs) and cache
+ * misses on lookups. Instead, use the fact that inodes on the unlinked list
+ * must be referenced at the VFS level to keep them on the list and hence we
+ * have an existence guarantee for inodes on the unlinked list.
+ *
+ * Given we have an existence guarantee, we can use lockless inode cache lookups
+ * to resolve aginos to xfs inodes. This means we only need 8 bytes per inode
+ * for the double linked unlinked list, and we don't need any extra locking to
+ * keep the list safe as all manipulations are done under the AGI buffer lock.
+ * Keeping the list up to date does not require memory allocation, just finding
+ * the XFS inode and updating the next/prev unlinked list aginos.
+ */
+
+/*
+ * Update the prev pointer of the next agino. Returns -ENOLINK if the inode
+ * is not in cache.
+ */
+static int
+xfs_iunlink_update_backref(
+ struct xfs_perag *pag,
+ xfs_agino_t prev_agino,
+ xfs_agino_t next_agino)
+{
+ struct xfs_inode *ip;
+
+ /* No update necessary if we are at the end of the list. */
+ if (next_agino == NULLAGINO)
+ return 0;
+
+ ip = xfs_iunlink_lookup(pag, next_agino);
+ if (!ip)
+ return -ENOLINK;
+
+ ip->i_prev_unlinked = prev_agino;
+ return 0;
+}
+
+/*
+ * Point the AGI unlinked bucket at an inode and log the results. The caller
+ * is responsible for validating the old value.
+ */
+STATIC int
+xfs_iunlink_update_bucket(
+ struct xfs_trans *tp,
+ struct xfs_perag *pag,
+ struct xfs_buf *agibp,
+ unsigned int bucket_index,
+ xfs_agino_t new_agino)
+{
+ struct xfs_agi *agi = agibp->b_addr;
+ xfs_agino_t old_value;
+ int offset;
+
+ ASSERT(xfs_verify_agino_or_null(pag, new_agino));
+
+ old_value = be32_to_cpu(agi->agi_unlinked[bucket_index]);
+ trace_xfs_iunlink_update_bucket(tp->t_mountp, pag->pag_agno, bucket_index,
+ old_value, new_agino);
+
+ /*
+ * We should never find the head of the list already set to the value
+ * passed in because either we're adding or removing ourselves from the
+ * head of the list.
+ */
+ if (old_value == new_agino) {
+ xfs_buf_mark_corrupt(agibp);
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
+ return -EFSCORRUPTED;
+ }
+
+ agi->agi_unlinked[bucket_index] = cpu_to_be32(new_agino);
+ offset = offsetof(struct xfs_agi, agi_unlinked) +
+ (sizeof(xfs_agino_t) * bucket_index);
+ xfs_trans_log_buf(tp, agibp, offset, offset + sizeof(xfs_agino_t) - 1);
+ return 0;
+}
+
+static int
+xfs_iunlink_insert_inode(
+ struct xfs_trans *tp,
+ struct xfs_perag *pag,
+ struct xfs_buf *agibp,
+ struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_agi *agi = agibp->b_addr;
+ xfs_agino_t next_agino;
+ xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
+ short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
+ int error;
+
+ /*
+ * Get the index into the agi hash table for the list this inode will
+ * go on. Make sure the pointer isn't garbage and that this inode
+ * isn't already on the list.
+ */
+ next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
+ if (next_agino == agino ||
+ !xfs_verify_agino_or_null(pag, next_agino)) {
+ xfs_buf_mark_corrupt(agibp);
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
+ return -EFSCORRUPTED;
+ }
+
+ /*
+ * Update the prev pointer in the next inode to point back to this
+ * inode.
+ */
+ error = xfs_iunlink_update_backref(pag, agino, next_agino);
+ if (error == -ENOLINK)
+ error = xfs_iunlink_reload_next(tp, agibp, agino, next_agino);
+ if (error)
+ return error;
+
+ if (next_agino != NULLAGINO) {
+ /*
+ * There is already another inode in the bucket, so point this
+ * inode to the current head of the list.
+ */
+ error = xfs_iunlink_log_inode(tp, ip, pag, next_agino);
+ if (error)
+ return error;
+ ip->i_next_unlinked = next_agino;
+ }
+
+ /* Point the head of the list to point to this inode. */
+ ip->i_prev_unlinked = NULLAGINO;
+ return xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index, agino);
+}
+
+/*
+ * This is called when the inode's link count has gone to 0 or we are creating
+ * a tmpfile via O_TMPFILE. The inode @ip must have nlink == 0.
+ *
+ * We place the on-disk inode on a list in the AGI. It will be pulled from this
+ * list when the inode is freed.
+ */
+int
+xfs_iunlink(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_perag *pag;
+ struct xfs_buf *agibp;
+ int error;
+
+ ASSERT(VFS_I(ip)->i_nlink == 0);
+ ASSERT(VFS_I(ip)->i_mode != 0);
+ trace_xfs_iunlink(ip);
+
+ pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
+
+ /* Get the agi buffer first. It ensures lock ordering on the list. */
+ error = xfs_read_agi(pag, tp, 0, &agibp);
+ if (error)
+ goto out;
+
+ error = xfs_iunlink_insert_inode(tp, pag, agibp, ip);
+out:
+ xfs_perag_put(pag);
+ return error;
+}
+
+static int
+xfs_iunlink_remove_inode(
+ struct xfs_trans *tp,
+ struct xfs_perag *pag,
+ struct xfs_buf *agibp,
+ struct xfs_inode *ip)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_agi *agi = agibp->b_addr;
+ xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
+ xfs_agino_t head_agino;
+ short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
+ int error;
+
+ trace_xfs_iunlink_remove(ip);
+
+ /*
+ * Get the index into the agi hash table for the list this inode will
+ * go on. Make sure the head pointer isn't garbage.
+ */
+ head_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
+ if (!xfs_verify_agino(pag, head_agino)) {
+ XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
+ agi, sizeof(*agi));
+ xfs_ag_mark_sick(pag, XFS_SICK_AG_AGI);
+ return -EFSCORRUPTED;
+ }
+
+ /*
+ * Set our inode's next_unlinked pointer to NULL and then return
+ * the old pointer value so that we can update whatever was previous
+ * to us in the list to point to whatever was next in the list.
+ */
+ error = xfs_iunlink_log_inode(tp, ip, pag, NULLAGINO);
+ if (error)
+ return error;
+
+ /*
+ * Update the prev pointer in the next inode to point back to previous
+ * inode in the chain.
+ */
+ error = xfs_iunlink_update_backref(pag, ip->i_prev_unlinked,
+ ip->i_next_unlinked);
+ if (error == -ENOLINK)
+ error = xfs_iunlink_reload_next(tp, agibp, ip->i_prev_unlinked,
+ ip->i_next_unlinked);
+ if (error)
+ return error;
+
+ if (head_agino != agino) {
+ struct xfs_inode *prev_ip;
+
+ prev_ip = xfs_iunlink_lookup(pag, ip->i_prev_unlinked);
+ if (!prev_ip) {
+ xfs_inode_mark_sick(ip, XFS_SICK_INO_CORE);
+ return -EFSCORRUPTED;
+ }
+
+ error = xfs_iunlink_log_inode(tp, prev_ip, pag,
+ ip->i_next_unlinked);
+ prev_ip->i_next_unlinked = ip->i_next_unlinked;
+ } else {
+ /* Point the head of the list to the next unlinked inode. */
+ error = xfs_iunlink_update_bucket(tp, pag, agibp, bucket_index,
+ ip->i_next_unlinked);
+ }
+
+ ip->i_next_unlinked = NULLAGINO;
+ ip->i_prev_unlinked = 0;
+ return error;
+}
+
+/*
+ * Pull the on-disk inode from the AGI unlinked list.
+ */
+int
+xfs_iunlink_remove(
+ struct xfs_trans *tp,
+ struct xfs_perag *pag,
+ struct xfs_inode *ip)
+{
+ struct xfs_buf *agibp;
+ int error;
+
+ trace_xfs_iunlink_remove(ip);
+
+ /* Get the agi buffer first. It ensures lock ordering on the list. */
+ error = xfs_read_agi(pag, tp, 0, &agibp);
+ if (error)
+ return error;
+
+ return xfs_iunlink_remove_inode(tp, pag, agibp, ip);
+}
+
+/*
+ * Decrement the link count on an inode & log the change. If this causes the
+ * link count to go to zero, move the inode to AGI unlinked list so that it can
+ * be freed when the last active reference goes away via xfs_inactive().
+ */
+int
+xfs_droplink(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
+{
+ struct inode *inode = VFS_I(ip);
+
+ xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
+
+ if (inode->i_nlink == 0) {
+ xfs_info_ratelimited(tp->t_mountp,
+ "Inode 0x%llx link count dropped below zero. Pinning link count.",
+ ip->i_ino);
+ set_nlink(inode, XFS_NLINK_PINNED);
+ }
+ if (inode->i_nlink != XFS_NLINK_PINNED)
+ drop_nlink(inode);
+
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+ if (inode->i_nlink)
+ return 0;
+
+ return xfs_iunlink(tp, ip);
+}
+
+/*
+ * Increment the link count on an inode & log the change.
+ */
+void
+xfs_bumplink(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
+{
+ struct inode *inode = VFS_I(ip);
+
+ xfs_trans_ichgtime(tp, ip, XFS_ICHGTIME_CHG);
+
+ if (inode->i_nlink == XFS_NLINK_PINNED - 1)
+ xfs_info_ratelimited(tp->t_mountp,
+ "Inode 0x%llx link count exceeded maximum. Pinning link count.",
+ ip->i_ino);
+ if (inode->i_nlink != XFS_NLINK_PINNED)
+ inc_nlink(inode);
+
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+/* Free an inode in the ondisk index and zero it out. */
+int
+xfs_inode_uninit(
+ struct xfs_trans *tp,
+ struct xfs_perag *pag,
+ struct xfs_inode *ip,
+ struct xfs_icluster *xic)
+{
+ struct xfs_mount *mp = ip->i_mount;
+ int error;
+
+ /*
+ * Free the inode first so that we guarantee that the AGI lock is going
+ * to be taken before we remove the inode from the unlinked list. This
+ * makes the AGI lock -> unlinked list modification order the same as
+ * used in O_TMPFILE creation.
+ */
+ error = xfs_difree(tp, pag, ip->i_ino, xic);
+ if (error)
+ return error;
+
+ error = xfs_iunlink_remove(tp, pag, ip);
+ if (error)
+ return error;
+
+ /*
+ * Free any local-format data sitting around before we reset the
+ * data fork to extents format. Note that the attr fork data has
+ * already been freed by xfs_attr_inactive.
+ */
+ if (ip->i_df.if_format == XFS_DINODE_FMT_LOCAL) {
+ kfree(ip->i_df.if_data);
+ ip->i_df.if_data = NULL;
+ ip->i_df.if_bytes = 0;
+ }
+
+ VFS_I(ip)->i_mode = 0; /* mark incore inode as free */
+ ip->i_diflags = 0;
+ ip->i_diflags2 = mp->m_ino_geo.new_diflags2;
+ ip->i_forkoff = 0; /* mark the attr fork not in use */
+ ip->i_df.if_format = XFS_DINODE_FMT_EXTENTS;
+
+ /*
+ * Bump the generation count so no one will be confused
+ * by reincarnations of this inode.
+ */
+ VFS_I(ip)->i_generation++;
+ xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+ return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_inode_util.h b/fs/xfs/libxfs/xfs_inode_util.h
new file mode 100644
index 000000000000..060242998a23
--- /dev/null
+++ b/fs/xfs/libxfs/xfs_inode_util.h
@@ -0,0 +1,62 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
+ * All Rights Reserved.
+ */
+#ifndef __XFS_INODE_UTIL_H__
+#define __XFS_INODE_UTIL_H__
+
+struct xfs_icluster;
+
+uint16_t xfs_flags2diflags(struct xfs_inode *ip, unsigned int xflags);
+uint64_t xfs_flags2diflags2(struct xfs_inode *ip, unsigned int xflags);
+uint32_t xfs_dic2xflags(struct xfs_inode *ip);
+uint32_t xfs_ip2xflags(struct xfs_inode *ip);
+
+prid_t xfs_get_initial_prid(struct xfs_inode *dp);
+
+/*
+ * File creation context.
+ *
+ * Due to our only partial reliance on the VFS to propagate uid and gid values
+ * according to accepted Unix behaviors, callers must initialize idmap to the
+ * correct idmapping structure to get the correct inheritance behaviors when
+ * XFS_MOUNT_GRPID is set.
+ *
+ * To create files detached from the directory tree (e.g. quota inodes), set
+ * idmap to NULL. To create a tree root, set pip to NULL.
+ */
+struct xfs_icreate_args {
+ struct mnt_idmap *idmap;
+ struct xfs_inode *pip; /* parent inode or null */
+ dev_t rdev;
+ umode_t mode;
+
+#define XFS_ICREATE_TMPFILE (1U << 0) /* create an unlinked file */
+#define XFS_ICREATE_INIT_XATTRS (1U << 1) /* will set xattrs immediately */
+#define XFS_ICREATE_UNLINKABLE (1U << 2) /* cannot link into dir tree */
+ uint16_t flags;
+};
+
+/*
+ * Flags for xfs_trans_ichgtime().
+ */
+#define XFS_ICHGTIME_MOD 0x1 /* data fork modification timestamp */
+#define XFS_ICHGTIME_CHG 0x2 /* inode field change timestamp */
+#define XFS_ICHGTIME_CREATE 0x4 /* inode create timestamp */
+#define XFS_ICHGTIME_ACCESS 0x8 /* last access timestamp */
+void xfs_trans_ichgtime(struct xfs_trans *tp, struct xfs_inode *ip, int flags);
+
+void xfs_inode_init(struct xfs_trans *tp, const struct xfs_icreate_args *args,
+ struct xfs_inode *ip);
+
+int xfs_inode_uninit(struct xfs_trans *tp, struct xfs_perag *pag,
+ struct xfs_inode *ip, struct xfs_icluster *xic);
+
+int xfs_iunlink(struct xfs_trans *tp, struct xfs_inode *ip);
+int xfs_iunlink_remove(struct xfs_trans *tp, struct xfs_perag *pag,
+ struct xfs_inode *ip);
+int xfs_droplink(struct xfs_trans *tp, struct xfs_inode *ip);
+void xfs_bumplink(struct xfs_trans *tp, struct xfs_inode *ip);
+
+#endif /* __XFS_INODE_UTIL_H__ */
diff --git a/fs/xfs/libxfs/xfs_ondisk.h b/fs/xfs/libxfs/xfs_ondisk.h
index e8cdd77d03fa..23c133fd36f5 100644
--- a/fs/xfs/libxfs/xfs_ondisk.h
+++ b/fs/xfs/libxfs/xfs_ondisk.h
@@ -85,6 +85,7 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_STRUCT_SIZE(xfs_attr_leaf_name_remote_t, 12);
*/
+ XFS_CHECK_OFFSET(struct xfs_dsb, sb_crc, 224);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, valuelen, 0);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, namelen, 2);
XFS_CHECK_OFFSET(xfs_attr_leaf_name_local_t, nameval, 3);
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index 511c912d515c..198b84117df1 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -24,6 +24,7 @@
#include "xfs_rmap.h"
#include "xfs_ag.h"
#include "xfs_health.h"
+#include "xfs_refcount_item.h"
struct kmem_cache *xfs_refcount_intent_cache;
@@ -51,7 +52,7 @@ xfs_refcount_lookup_le(
xfs_agblock_t bno,
int *stat)
{
- trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+ trace_xfs_refcount_lookup(cur,
xfs_refcount_encode_startblock(bno, domain),
XFS_LOOKUP_LE);
cur->bc_rec.rc.rc_startblock = bno;
@@ -71,7 +72,7 @@ xfs_refcount_lookup_ge(
xfs_agblock_t bno,
int *stat)
{
- trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+ trace_xfs_refcount_lookup(cur,
xfs_refcount_encode_startblock(bno, domain),
XFS_LOOKUP_GE);
cur->bc_rec.rc.rc_startblock = bno;
@@ -91,7 +92,7 @@ xfs_refcount_lookup_eq(
xfs_agblock_t bno,
int *stat)
{
- trace_xfs_refcount_lookup(cur->bc_mp, cur->bc_ag.pag->pag_agno,
+ trace_xfs_refcount_lookup(cur,
xfs_refcount_encode_startblock(bno, domain),
XFS_LOOKUP_LE);
cur->bc_rec.rc.rc_startblock = bno;
@@ -183,7 +184,7 @@ xfs_refcount_get_rec(
if (fa)
return xfs_refcount_complain_bad_rec(cur, fa, irec);
- trace_xfs_refcount_get(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec);
+ trace_xfs_refcount_get(cur, irec);
return 0;
}
@@ -201,7 +202,7 @@ xfs_refcount_update(
uint32_t start;
int error;
- trace_xfs_refcount_update(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec);
+ trace_xfs_refcount_update(cur, irec);
start = xfs_refcount_encode_startblock(irec->rc_startblock,
irec->rc_domain);
@@ -211,8 +212,7 @@ xfs_refcount_update(
error = xfs_btree_update(cur, &rec);
if (error)
- trace_xfs_refcount_update_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_refcount_update_error(cur, error, _RET_IP_);
return error;
}
@@ -229,7 +229,7 @@ xfs_refcount_insert(
{
int error;
- trace_xfs_refcount_insert(cur->bc_mp, cur->bc_ag.pag->pag_agno, irec);
+ trace_xfs_refcount_insert(cur, irec);
cur->bc_rec.rc.rc_startblock = irec->rc_startblock;
cur->bc_rec.rc.rc_blockcount = irec->rc_blockcount;
@@ -247,8 +247,7 @@ xfs_refcount_insert(
out_error:
if (error)
- trace_xfs_refcount_insert_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_refcount_insert_error(cur, error, _RET_IP_);
return error;
}
@@ -275,7 +274,7 @@ xfs_refcount_delete(
error = -EFSCORRUPTED;
goto out_error;
}
- trace_xfs_refcount_delete(cur->bc_mp, cur->bc_ag.pag->pag_agno, &irec);
+ trace_xfs_refcount_delete(cur, &irec);
error = xfs_btree_delete(cur, i);
if (XFS_IS_CORRUPT(cur->bc_mp, *i != 1)) {
xfs_btree_mark_sick(cur);
@@ -288,8 +287,7 @@ xfs_refcount_delete(
&found_rec);
out_error:
if (error)
- trace_xfs_refcount_delete_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_refcount_delete_error(cur, error, _RET_IP_);
return error;
}
@@ -413,8 +411,7 @@ xfs_refcount_split_extent(
return 0;
*shape_changed = true;
- trace_xfs_refcount_split_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- &rcext, agbno);
+ trace_xfs_refcount_split_extent(cur, &rcext, agbno);
/* Establish the right extent. */
tmp = rcext;
@@ -438,8 +435,7 @@ xfs_refcount_split_extent(
return error;
out_error:
- trace_xfs_refcount_split_extent_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_refcount_split_extent_error(cur, error, _RET_IP_);
return error;
}
@@ -458,8 +454,7 @@ xfs_refcount_merge_center_extents(
int error;
int found_rec;
- trace_xfs_refcount_merge_center_extents(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, left, center, right);
+ trace_xfs_refcount_merge_center_extents(cur, left, center, right);
ASSERT(left->rc_domain == center->rc_domain);
ASSERT(right->rc_domain == center->rc_domain);
@@ -522,8 +517,7 @@ xfs_refcount_merge_center_extents(
return error;
out_error:
- trace_xfs_refcount_merge_center_extents_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_refcount_merge_center_extents_error(cur, error, _RET_IP_);
return error;
}
@@ -541,8 +535,7 @@ xfs_refcount_merge_left_extent(
int error;
int found_rec;
- trace_xfs_refcount_merge_left_extent(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, left, cleft);
+ trace_xfs_refcount_merge_left_extent(cur, left, cleft);
ASSERT(left->rc_domain == cleft->rc_domain);
@@ -589,8 +582,7 @@ xfs_refcount_merge_left_extent(
return error;
out_error:
- trace_xfs_refcount_merge_left_extent_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_refcount_merge_left_extent_error(cur, error, _RET_IP_);
return error;
}
@@ -607,8 +599,7 @@ xfs_refcount_merge_right_extent(
int error;
int found_rec;
- trace_xfs_refcount_merge_right_extent(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, cright, right);
+ trace_xfs_refcount_merge_right_extent(cur, cright, right);
ASSERT(right->rc_domain == cright->rc_domain);
@@ -658,8 +649,7 @@ xfs_refcount_merge_right_extent(
return error;
out_error:
- trace_xfs_refcount_merge_right_extent_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_refcount_merge_right_extent_error(cur, error, _RET_IP_);
return error;
}
@@ -748,13 +738,11 @@ not_found:
cleft->rc_refcount = 1;
cleft->rc_domain = domain;
}
- trace_xfs_refcount_find_left_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- left, cleft, agbno);
+ trace_xfs_refcount_find_left_extent(cur, left, cleft, agbno);
return error;
out_error:
- trace_xfs_refcount_find_left_extent_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_refcount_find_left_extent_error(cur, error, _RET_IP_);
return error;
}
@@ -843,13 +831,12 @@ not_found:
cright->rc_refcount = 1;
cright->rc_domain = domain;
}
- trace_xfs_refcount_find_right_extent(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- cright, right, agbno + aglen);
+ trace_xfs_refcount_find_right_extent(cur, cright, right,
+ agbno + aglen);
return error;
out_error:
- trace_xfs_refcount_find_right_extent_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_refcount_find_right_extent_error(cur, error, _RET_IP_);
return error;
}
@@ -1148,8 +1135,7 @@ xfs_refcount_adjust_extents(
tmp.rc_refcount = 1 + adj;
tmp.rc_domain = XFS_REFC_DOMAIN_SHARED;
- trace_xfs_refcount_modify_extent(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, &tmp);
+ trace_xfs_refcount_modify_extent(cur, &tmp);
/*
* Either cover the hole (increment) or
@@ -1173,7 +1159,7 @@ xfs_refcount_adjust_extents(
tmp.rc_startblock);
error = xfs_free_extent_later(cur->bc_tp, fsbno,
tmp.rc_blockcount, NULL,
- XFS_AG_RESV_NONE, false);
+ XFS_AG_RESV_NONE, 0);
if (error)
goto out_error;
}
@@ -1214,8 +1200,7 @@ xfs_refcount_adjust_extents(
if (ext.rc_refcount == MAXREFCOUNT)
goto skip;
ext.rc_refcount += adj;
- trace_xfs_refcount_modify_extent(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, &ext);
+ trace_xfs_refcount_modify_extent(cur, &ext);
cur->bc_refc.nr_ops++;
if (ext.rc_refcount > 1) {
error = xfs_refcount_update(cur, &ext);
@@ -1237,7 +1222,7 @@ xfs_refcount_adjust_extents(
ext.rc_startblock);
error = xfs_free_extent_later(cur->bc_tp, fsbno,
ext.rc_blockcount, NULL,
- XFS_AG_RESV_NONE, false);
+ XFS_AG_RESV_NONE, 0);
if (error)
goto out_error;
}
@@ -1254,8 +1239,7 @@ advloop:
return error;
out_error:
- trace_xfs_refcount_modify_extent_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_refcount_modify_extent_error(cur, error, _RET_IP_);
return error;
}
@@ -1272,11 +1256,9 @@ xfs_refcount_adjust(
int error;
if (adj == XFS_REFCOUNT_ADJUST_INCREASE)
- trace_xfs_refcount_increase(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, *agbno, *aglen);
+ trace_xfs_refcount_increase(cur, *agbno, *aglen);
else
- trace_xfs_refcount_decrease(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, *agbno, *aglen);
+ trace_xfs_refcount_decrease(cur, *agbno, *aglen);
/*
* Ensure that no rcextents cross the boundary of the adjustment range.
@@ -1315,28 +1297,10 @@ xfs_refcount_adjust(
return 0;
out_error:
- trace_xfs_refcount_adjust_error(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- error, _RET_IP_);
+ trace_xfs_refcount_adjust_error(cur, error, _RET_IP_);
return error;
}
-/* Clean up after calling xfs_refcount_finish_one. */
-void
-xfs_refcount_finish_one_cleanup(
- struct xfs_trans *tp,
- struct xfs_btree_cur *rcur,
- int error)
-{
- struct xfs_buf *agbp;
-
- if (rcur == NULL)
- return;
- agbp = rcur->bc_ag.agbp;
- xfs_btree_del_cursor(rcur, error);
- if (error)
- xfs_trans_brelse(tp, agbp);
-}
-
/*
* Set up a continuation a deferred refcount operation by updating the intent.
* Checks to make sure we're not going to run off the end of the AG.
@@ -1378,7 +1342,7 @@ xfs_refcount_finish_one(
struct xfs_btree_cur **pcur)
{
struct xfs_mount *mp = tp->t_mountp;
- struct xfs_btree_cur *rcur;
+ struct xfs_btree_cur *rcur = *pcur;
struct xfs_buf *agbp = NULL;
int error = 0;
xfs_agblock_t bno;
@@ -1387,9 +1351,7 @@ xfs_refcount_finish_one(
bno = XFS_FSB_TO_AGBNO(mp, ri->ri_startblock);
- trace_xfs_refcount_deferred(mp, XFS_FSB_TO_AGNO(mp, ri->ri_startblock),
- ri->ri_type, XFS_FSB_TO_AGBNO(mp, ri->ri_startblock),
- ri->ri_blockcount);
+ trace_xfs_refcount_deferred(mp, ri);
if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_REFCOUNT_FINISH_ONE))
return -EIO;
@@ -1398,11 +1360,10 @@ xfs_refcount_finish_one(
* If we haven't gotten a cursor or the cursor AG doesn't match
* the startblock, get one now.
*/
- rcur = *pcur;
if (rcur != NULL && rcur->bc_ag.pag != ri->ri_pag) {
nr_ops = rcur->bc_refc.nr_ops;
shape_changes = rcur->bc_refc.shape_changes;
- xfs_refcount_finish_one_cleanup(tp, rcur, 0);
+ xfs_btree_del_cursor(rcur, 0);
rcur = NULL;
*pcur = NULL;
}
@@ -1412,11 +1373,11 @@ xfs_refcount_finish_one(
if (error)
return error;
- rcur = xfs_refcountbt_init_cursor(mp, tp, agbp, ri->ri_pag);
+ *pcur = rcur = xfs_refcountbt_init_cursor(mp, tp, agbp,
+ ri->ri_pag);
rcur->bc_refc.nr_ops = nr_ops;
rcur->bc_refc.shape_changes = shape_changes;
}
- *pcur = rcur;
switch (ri->ri_type) {
case XFS_REFCOUNT_INCREASE:
@@ -1452,8 +1413,7 @@ xfs_refcount_finish_one(
return -EFSCORRUPTED;
}
if (!error && ri->ri_blockcount > 0)
- trace_xfs_refcount_finish_one_leftover(mp, ri->ri_pag->pag_agno,
- ri->ri_type, bno, ri->ri_blockcount);
+ trace_xfs_refcount_finish_one_leftover(mp, ri);
return error;
}
@@ -1469,11 +1429,6 @@ __xfs_refcount_add(
{
struct xfs_refcount_intent *ri;
- trace_xfs_refcount_defer(tp->t_mountp,
- XFS_FSB_TO_AGNO(tp->t_mountp, startblock),
- type, XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
- blockcount);
-
ri = kmem_cache_alloc(xfs_refcount_intent_cache,
GFP_KERNEL | __GFP_NOFAIL);
INIT_LIST_HEAD(&ri->ri_list);
@@ -1481,8 +1436,7 @@ __xfs_refcount_add(
ri->ri_startblock = startblock;
ri->ri_blockcount = blockcount;
- xfs_refcount_update_get_group(tp->t_mountp, ri);
- xfs_defer_add(tp, &ri->ri_list, &xfs_refcount_update_defer_type);
+ xfs_refcount_defer_add(tp, ri);
}
/*
@@ -1537,8 +1491,7 @@ xfs_refcount_find_shared(
int have;
int error;
- trace_xfs_refcount_find_shared(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- agbno, aglen);
+ trace_xfs_refcount_find_shared(cur, agbno, aglen);
/* By default, skip the whole range */
*fbno = NULLAGBLOCK;
@@ -1625,13 +1578,11 @@ xfs_refcount_find_shared(
}
done:
- trace_xfs_refcount_find_shared_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, *fbno, *flen);
+ trace_xfs_refcount_find_shared_result(cur, *fbno, *flen);
out_error:
if (error)
- trace_xfs_refcount_find_shared_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_refcount_find_shared_error(cur, error, _RET_IP_);
return error;
}
@@ -1737,8 +1688,7 @@ xfs_refcount_adjust_cow_extents(
tmp.rc_refcount = 1;
tmp.rc_domain = XFS_REFC_DOMAIN_COW;
- trace_xfs_refcount_modify_extent(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, &tmp);
+ trace_xfs_refcount_modify_extent(cur, &tmp);
error = xfs_refcount_insert(cur, &tmp,
&found_tmp);
@@ -1769,8 +1719,7 @@ xfs_refcount_adjust_cow_extents(
}
ext.rc_refcount = 0;
- trace_xfs_refcount_modify_extent(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, &ext);
+ trace_xfs_refcount_modify_extent(cur, &ext);
error = xfs_refcount_delete(cur, &found_rec);
if (error)
goto out_error;
@@ -1786,8 +1735,7 @@ xfs_refcount_adjust_cow_extents(
return error;
out_error:
- trace_xfs_refcount_modify_extent_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_refcount_modify_extent_error(cur, error, _RET_IP_);
return error;
}
@@ -1833,8 +1781,7 @@ xfs_refcount_adjust_cow(
return 0;
out_error:
- trace_xfs_refcount_adjust_cow_error(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- error, _RET_IP_);
+ trace_xfs_refcount_adjust_cow_error(cur, error, _RET_IP_);
return error;
}
@@ -1847,8 +1794,7 @@ __xfs_refcount_cow_alloc(
xfs_agblock_t agbno,
xfs_extlen_t aglen)
{
- trace_xfs_refcount_cow_increase(rcur->bc_mp, rcur->bc_ag.pag->pag_agno,
- agbno, aglen);
+ trace_xfs_refcount_cow_increase(rcur, agbno, aglen);
/* Add refcount btree reservation */
return xfs_refcount_adjust_cow(rcur, agbno, aglen,
@@ -1864,8 +1810,7 @@ __xfs_refcount_cow_free(
xfs_agblock_t agbno,
xfs_extlen_t aglen)
{
- trace_xfs_refcount_cow_decrease(rcur->bc_mp, rcur->bc_ag.pag->pag_agno,
- agbno, aglen);
+ trace_xfs_refcount_cow_decrease(rcur, agbno, aglen);
/* Remove refcount btree reservation */
return xfs_refcount_adjust_cow(rcur, agbno, aglen,
@@ -2010,9 +1955,6 @@ xfs_refcount_recover_cow_leftovers(
if (error)
goto out_free;
- trace_xfs_refcount_recover_extent(mp, pag->pag_agno,
- &rr->rr_rrec);
-
/* Free the orphan record */
fsb = XFS_AGB_TO_FSB(mp, pag->pag_agno,
rr->rr_rrec.rc_startblock);
@@ -2022,7 +1964,7 @@ xfs_refcount_recover_cow_leftovers(
/* Free the block. */
error = xfs_free_extent_later(tp, fsb,
rr->rr_rrec.rc_blockcount, NULL,
- XFS_AG_RESV_NONE, false);
+ XFS_AG_RESV_NONE, 0);
if (error)
goto out_trans;
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 9b56768a590c..68acb0b1b4a8 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -48,6 +48,12 @@ enum xfs_refcount_intent_type {
XFS_REFCOUNT_FREE_COW,
};
+#define XFS_REFCOUNT_INTENT_STRINGS \
+ { XFS_REFCOUNT_INCREASE, "incr" }, \
+ { XFS_REFCOUNT_DECREASE, "decr" }, \
+ { XFS_REFCOUNT_ALLOC_COW, "alloc_cow" }, \
+ { XFS_REFCOUNT_FREE_COW, "free_cow" }
+
struct xfs_refcount_intent {
struct list_head ri_list;
struct xfs_perag *ri_pag;
@@ -68,16 +74,11 @@ xfs_refcount_check_domain(
return true;
}
-void xfs_refcount_update_get_group(struct xfs_mount *mp,
- struct xfs_refcount_intent *ri);
-
void xfs_refcount_increase_extent(struct xfs_trans *tp,
struct xfs_bmbt_irec *irec);
void xfs_refcount_decrease_extent(struct xfs_trans *tp,
struct xfs_bmbt_irec *irec);
-extern void xfs_refcount_finish_one_cleanup(struct xfs_trans *tp,
- struct xfs_btree_cur *rcur, int error);
extern int xfs_refcount_finish_one(struct xfs_trans *tp,
struct xfs_refcount_intent *ri, struct xfs_btree_cur **pcur);
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index ca59f6c89f3e..cb3b1d42ae9a 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -109,7 +109,7 @@ xfs_refcountbt_free_block(
be32_add_cpu(&agf->agf_refcount_blocks, -1);
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_REFCOUNT_BLOCKS);
return xfs_free_extent_later(cur->bc_tp, fsbno, 1,
- &XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA, false);
+ &XFS_RMAP_OINFO_REFC, XFS_AG_RESV_METADATA, 0);
}
STATIC int
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index ef16f6f9cef6..6ef4687b3aba 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -24,6 +24,7 @@
#include "xfs_inode.h"
#include "xfs_ag.h"
#include "xfs_health.h"
+#include "xfs_rmap_item.h"
struct kmem_cache *xfs_rmap_intent_cache;
@@ -100,8 +101,7 @@ xfs_rmap_update(
union xfs_btree_rec rec;
int error;
- trace_xfs_rmap_update(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- irec->rm_startblock, irec->rm_blockcount,
+ trace_xfs_rmap_update(cur, irec->rm_startblock, irec->rm_blockcount,
irec->rm_owner, irec->rm_offset, irec->rm_flags);
rec.rmap.rm_startblock = cpu_to_be32(irec->rm_startblock);
@@ -111,8 +111,7 @@ xfs_rmap_update(
xfs_rmap_irec_offset_pack(irec));
error = xfs_btree_update(cur, &rec);
if (error)
- trace_xfs_rmap_update_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_rmap_update_error(cur, error, _RET_IP_);
return error;
}
@@ -128,8 +127,7 @@ xfs_rmap_insert(
int i;
int error;
- trace_xfs_rmap_insert(rcur->bc_mp, rcur->bc_ag.pag->pag_agno, agbno,
- len, owner, offset, flags);
+ trace_xfs_rmap_insert(rcur, agbno, len, owner, offset, flags);
error = xfs_rmap_lookup_eq(rcur, agbno, len, owner, offset, flags, &i);
if (error)
@@ -155,8 +153,7 @@ xfs_rmap_insert(
}
done:
if (error)
- trace_xfs_rmap_insert_error(rcur->bc_mp,
- rcur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_rmap_insert_error(rcur, error, _RET_IP_);
return error;
}
@@ -172,8 +169,7 @@ xfs_rmap_delete(
int i;
int error;
- trace_xfs_rmap_delete(rcur->bc_mp, rcur->bc_ag.pag->pag_agno, agbno,
- len, owner, offset, flags);
+ trace_xfs_rmap_delete(rcur, agbno, len, owner, offset, flags);
error = xfs_rmap_lookup_eq(rcur, agbno, len, owner, offset, flags, &i);
if (error)
@@ -194,8 +190,7 @@ xfs_rmap_delete(
}
done:
if (error)
- trace_xfs_rmap_delete_error(rcur->bc_mp,
- rcur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_rmap_delete_error(rcur, error, _RET_IP_);
return error;
}
@@ -342,8 +337,7 @@ xfs_rmap_find_left_neighbor_helper(
{
struct xfs_find_left_neighbor_info *info = priv;
- trace_xfs_rmap_find_left_neighbor_candidate(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, rec->rm_startblock,
+ trace_xfs_rmap_find_left_neighbor_candidate(cur, rec->rm_startblock,
rec->rm_blockcount, rec->rm_owner, rec->rm_offset,
rec->rm_flags);
@@ -393,8 +387,8 @@ xfs_rmap_find_left_neighbor(
info.high.rm_blockcount = 0;
info.irec = irec;
- trace_xfs_rmap_find_left_neighbor_query(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, bno, 0, owner, offset, flags);
+ trace_xfs_rmap_find_left_neighbor_query(cur, bno, 0, owner, offset,
+ flags);
/*
* Historically, we always used the range query to walk every reverse
@@ -425,8 +419,7 @@ xfs_rmap_find_left_neighbor(
return error;
*stat = 1;
- trace_xfs_rmap_find_left_neighbor_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, irec->rm_startblock,
+ trace_xfs_rmap_find_left_neighbor_result(cur, irec->rm_startblock,
irec->rm_blockcount, irec->rm_owner, irec->rm_offset,
irec->rm_flags);
return 0;
@@ -441,8 +434,7 @@ xfs_rmap_lookup_le_range_helper(
{
struct xfs_find_left_neighbor_info *info = priv;
- trace_xfs_rmap_lookup_le_range_candidate(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, rec->rm_startblock,
+ trace_xfs_rmap_lookup_le_range_candidate(cur, rec->rm_startblock,
rec->rm_blockcount, rec->rm_owner, rec->rm_offset,
rec->rm_flags);
@@ -489,8 +481,7 @@ xfs_rmap_lookup_le_range(
*stat = 0;
info.irec = irec;
- trace_xfs_rmap_lookup_le_range(cur->bc_mp, cur->bc_ag.pag->pag_agno,
- bno, 0, owner, offset, flags);
+ trace_xfs_rmap_lookup_le_range(cur, bno, 0, owner, offset, flags);
/*
* Historically, we always used the range query to walk every reverse
@@ -521,8 +512,7 @@ xfs_rmap_lookup_le_range(
return error;
*stat = 1;
- trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, irec->rm_startblock,
+ trace_xfs_rmap_lookup_le_range_result(cur, irec->rm_startblock,
irec->rm_blockcount, irec->rm_owner, irec->rm_offset,
irec->rm_flags);
return 0;
@@ -634,8 +624,7 @@ xfs_rmap_unmap(
(flags & XFS_RMAP_BMBT_BLOCK);
if (unwritten)
flags |= XFS_RMAP_UNWRITTEN;
- trace_xfs_rmap_unmap(mp, cur->bc_ag.pag->pag_agno, bno, len,
- unwritten, oinfo);
+ trace_xfs_rmap_unmap(cur, bno, len, unwritten, oinfo);
/*
* We should always have a left record because there's a static record
@@ -651,10 +640,9 @@ xfs_rmap_unmap(
goto out_error;
}
- trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, ltrec.rm_startblock,
- ltrec.rm_blockcount, ltrec.rm_owner,
- ltrec.rm_offset, ltrec.rm_flags);
+ trace_xfs_rmap_lookup_le_range_result(cur, ltrec.rm_startblock,
+ ltrec.rm_blockcount, ltrec.rm_owner, ltrec.rm_offset,
+ ltrec.rm_flags);
ltoff = ltrec.rm_offset;
/*
@@ -721,10 +709,9 @@ xfs_rmap_unmap(
if (ltrec.rm_startblock == bno && ltrec.rm_blockcount == len) {
/* exact match, simply remove the record from rmap tree */
- trace_xfs_rmap_delete(mp, cur->bc_ag.pag->pag_agno,
- ltrec.rm_startblock, ltrec.rm_blockcount,
- ltrec.rm_owner, ltrec.rm_offset,
- ltrec.rm_flags);
+ trace_xfs_rmap_delete(cur, ltrec.rm_startblock,
+ ltrec.rm_blockcount, ltrec.rm_owner,
+ ltrec.rm_offset, ltrec.rm_flags);
error = xfs_btree_delete(cur, &i);
if (error)
goto out_error;
@@ -800,8 +787,7 @@ xfs_rmap_unmap(
else
cur->bc_rec.r.rm_offset = offset + len;
cur->bc_rec.r.rm_flags = flags;
- trace_xfs_rmap_insert(mp, cur->bc_ag.pag->pag_agno,
- cur->bc_rec.r.rm_startblock,
+ trace_xfs_rmap_insert(cur, cur->bc_rec.r.rm_startblock,
cur->bc_rec.r.rm_blockcount,
cur->bc_rec.r.rm_owner,
cur->bc_rec.r.rm_offset,
@@ -812,12 +798,10 @@ xfs_rmap_unmap(
}
out_done:
- trace_xfs_rmap_unmap_done(mp, cur->bc_ag.pag->pag_agno, bno, len,
- unwritten, oinfo);
+ trace_xfs_rmap_unmap_done(cur, bno, len, unwritten, oinfo);
out_error:
if (error)
- trace_xfs_rmap_unmap_error(mp, cur->bc_ag.pag->pag_agno,
- error, _RET_IP_);
+ trace_xfs_rmap_unmap_error(cur, error, _RET_IP_);
return error;
}
@@ -987,8 +971,7 @@ xfs_rmap_map(
(flags & XFS_RMAP_BMBT_BLOCK);
if (unwritten)
flags |= XFS_RMAP_UNWRITTEN;
- trace_xfs_rmap_map(mp, cur->bc_ag.pag->pag_agno, bno, len,
- unwritten, oinfo);
+ trace_xfs_rmap_map(cur, bno, len, unwritten, oinfo);
ASSERT(!xfs_rmap_should_skip_owner_update(oinfo));
/*
@@ -1001,8 +984,7 @@ xfs_rmap_map(
if (error)
goto out_error;
if (have_lt) {
- trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, ltrec.rm_startblock,
+ trace_xfs_rmap_lookup_le_range_result(cur, ltrec.rm_startblock,
ltrec.rm_blockcount, ltrec.rm_owner,
ltrec.rm_offset, ltrec.rm_flags);
@@ -1040,10 +1022,10 @@ xfs_rmap_map(
error = -EFSCORRUPTED;
goto out_error;
}
- trace_xfs_rmap_find_right_neighbor_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, gtrec.rm_startblock,
- gtrec.rm_blockcount, gtrec.rm_owner,
- gtrec.rm_offset, gtrec.rm_flags);
+ trace_xfs_rmap_find_right_neighbor_result(cur,
+ gtrec.rm_startblock, gtrec.rm_blockcount,
+ gtrec.rm_owner, gtrec.rm_offset,
+ gtrec.rm_flags);
if (!xfs_rmap_is_mergeable(&gtrec, owner, flags))
have_gt = 0;
}
@@ -1080,12 +1062,9 @@ xfs_rmap_map(
* result: |rrrrrrrrrrrrrrrrrrrrrrrrrrrrr|
*/
ltrec.rm_blockcount += gtrec.rm_blockcount;
- trace_xfs_rmap_delete(mp, cur->bc_ag.pag->pag_agno,
- gtrec.rm_startblock,
- gtrec.rm_blockcount,
- gtrec.rm_owner,
- gtrec.rm_offset,
- gtrec.rm_flags);
+ trace_xfs_rmap_delete(cur, gtrec.rm_startblock,
+ gtrec.rm_blockcount, gtrec.rm_owner,
+ gtrec.rm_offset, gtrec.rm_flags);
error = xfs_btree_delete(cur, &i);
if (error)
goto out_error;
@@ -1132,8 +1111,7 @@ xfs_rmap_map(
cur->bc_rec.r.rm_owner = owner;
cur->bc_rec.r.rm_offset = offset;
cur->bc_rec.r.rm_flags = flags;
- trace_xfs_rmap_insert(mp, cur->bc_ag.pag->pag_agno, bno, len,
- owner, offset, flags);
+ trace_xfs_rmap_insert(cur, bno, len, owner, offset, flags);
error = xfs_btree_insert(cur, &i);
if (error)
goto out_error;
@@ -1144,12 +1122,10 @@ xfs_rmap_map(
}
}
- trace_xfs_rmap_map_done(mp, cur->bc_ag.pag->pag_agno, bno, len,
- unwritten, oinfo);
+ trace_xfs_rmap_map_done(cur, bno, len, unwritten, oinfo);
out_error:
if (error)
- trace_xfs_rmap_map_error(mp, cur->bc_ag.pag->pag_agno,
- error, _RET_IP_);
+ trace_xfs_rmap_map_error(cur, error, _RET_IP_);
return error;
}
@@ -1223,8 +1199,7 @@ xfs_rmap_convert(
(flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))));
oldext = unwritten ? XFS_RMAP_UNWRITTEN : 0;
new_endoff = offset + len;
- trace_xfs_rmap_convert(mp, cur->bc_ag.pag->pag_agno, bno, len,
- unwritten, oinfo);
+ trace_xfs_rmap_convert(cur, bno, len, unwritten, oinfo);
/*
* For the initial lookup, look for an exact match or the left-adjacent
@@ -1240,10 +1215,9 @@ xfs_rmap_convert(
goto done;
}
- trace_xfs_rmap_lookup_le_range_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, PREV.rm_startblock,
- PREV.rm_blockcount, PREV.rm_owner,
- PREV.rm_offset, PREV.rm_flags);
+ trace_xfs_rmap_lookup_le_range_result(cur, PREV.rm_startblock,
+ PREV.rm_blockcount, PREV.rm_owner, PREV.rm_offset,
+ PREV.rm_flags);
ASSERT(PREV.rm_offset <= offset);
ASSERT(PREV.rm_offset + PREV.rm_blockcount >= new_endoff);
@@ -1284,10 +1258,9 @@ xfs_rmap_convert(
error = -EFSCORRUPTED;
goto done;
}
- trace_xfs_rmap_find_left_neighbor_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, LEFT.rm_startblock,
- LEFT.rm_blockcount, LEFT.rm_owner,
- LEFT.rm_offset, LEFT.rm_flags);
+ trace_xfs_rmap_find_left_neighbor_result(cur,
+ LEFT.rm_startblock, LEFT.rm_blockcount,
+ LEFT.rm_owner, LEFT.rm_offset, LEFT.rm_flags);
if (LEFT.rm_startblock + LEFT.rm_blockcount == bno &&
LEFT.rm_offset + LEFT.rm_blockcount == offset &&
xfs_rmap_is_mergeable(&LEFT, owner, newext))
@@ -1325,10 +1298,10 @@ xfs_rmap_convert(
error = -EFSCORRUPTED;
goto done;
}
- trace_xfs_rmap_find_right_neighbor_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, RIGHT.rm_startblock,
- RIGHT.rm_blockcount, RIGHT.rm_owner,
- RIGHT.rm_offset, RIGHT.rm_flags);
+ trace_xfs_rmap_find_right_neighbor_result(cur,
+ RIGHT.rm_startblock, RIGHT.rm_blockcount,
+ RIGHT.rm_owner, RIGHT.rm_offset,
+ RIGHT.rm_flags);
if (bno + len == RIGHT.rm_startblock &&
offset + len == RIGHT.rm_offset &&
xfs_rmap_is_mergeable(&RIGHT, owner, newext))
@@ -1344,8 +1317,7 @@ xfs_rmap_convert(
RIGHT.rm_blockcount > XFS_RMAP_LEN_MAX)
state &= ~RMAP_RIGHT_CONTIG;
- trace_xfs_rmap_convert_state(mp, cur->bc_ag.pag->pag_agno, state,
- _RET_IP_);
+ trace_xfs_rmap_convert_state(cur, state, _RET_IP_);
/* reset the cursor back to PREV */
error = xfs_rmap_lookup_le(cur, bno, owner, offset, oldext, NULL, &i);
@@ -1376,10 +1348,9 @@ xfs_rmap_convert(
error = -EFSCORRUPTED;
goto done;
}
- trace_xfs_rmap_delete(mp, cur->bc_ag.pag->pag_agno,
- RIGHT.rm_startblock, RIGHT.rm_blockcount,
- RIGHT.rm_owner, RIGHT.rm_offset,
- RIGHT.rm_flags);
+ trace_xfs_rmap_delete(cur, RIGHT.rm_startblock,
+ RIGHT.rm_blockcount, RIGHT.rm_owner,
+ RIGHT.rm_offset, RIGHT.rm_flags);
error = xfs_btree_delete(cur, &i);
if (error)
goto done;
@@ -1396,10 +1367,9 @@ xfs_rmap_convert(
error = -EFSCORRUPTED;
goto done;
}
- trace_xfs_rmap_delete(mp, cur->bc_ag.pag->pag_agno,
- PREV.rm_startblock, PREV.rm_blockcount,
- PREV.rm_owner, PREV.rm_offset,
- PREV.rm_flags);
+ trace_xfs_rmap_delete(cur, PREV.rm_startblock,
+ PREV.rm_blockcount, PREV.rm_owner,
+ PREV.rm_offset, PREV.rm_flags);
error = xfs_btree_delete(cur, &i);
if (error)
goto done;
@@ -1428,10 +1398,9 @@ xfs_rmap_convert(
* Setting all of a previous oldext extent to newext.
* The left neighbor is contiguous, the right is not.
*/
- trace_xfs_rmap_delete(mp, cur->bc_ag.pag->pag_agno,
- PREV.rm_startblock, PREV.rm_blockcount,
- PREV.rm_owner, PREV.rm_offset,
- PREV.rm_flags);
+ trace_xfs_rmap_delete(cur, PREV.rm_startblock,
+ PREV.rm_blockcount, PREV.rm_owner,
+ PREV.rm_offset, PREV.rm_flags);
error = xfs_btree_delete(cur, &i);
if (error)
goto done;
@@ -1468,10 +1437,9 @@ xfs_rmap_convert(
error = -EFSCORRUPTED;
goto done;
}
- trace_xfs_rmap_delete(mp, cur->bc_ag.pag->pag_agno,
- RIGHT.rm_startblock, RIGHT.rm_blockcount,
- RIGHT.rm_owner, RIGHT.rm_offset,
- RIGHT.rm_flags);
+ trace_xfs_rmap_delete(cur, RIGHT.rm_startblock,
+ RIGHT.rm_blockcount, RIGHT.rm_owner,
+ RIGHT.rm_offset, RIGHT.rm_flags);
error = xfs_btree_delete(cur, &i);
if (error)
goto done;
@@ -1549,8 +1517,7 @@ xfs_rmap_convert(
NEW.rm_blockcount = len;
NEW.rm_flags = newext;
cur->bc_rec.r = NEW;
- trace_xfs_rmap_insert(mp, cur->bc_ag.pag->pag_agno, bno,
- len, owner, offset, newext);
+ trace_xfs_rmap_insert(cur, bno, len, owner, offset, newext);
error = xfs_btree_insert(cur, &i);
if (error)
goto done;
@@ -1608,8 +1575,7 @@ xfs_rmap_convert(
NEW.rm_blockcount = len;
NEW.rm_flags = newext;
cur->bc_rec.r = NEW;
- trace_xfs_rmap_insert(mp, cur->bc_ag.pag->pag_agno, bno,
- len, owner, offset, newext);
+ trace_xfs_rmap_insert(cur, bno, len, owner, offset, newext);
error = xfs_btree_insert(cur, &i);
if (error)
goto done;
@@ -1640,9 +1606,8 @@ xfs_rmap_convert(
NEW = PREV;
NEW.rm_blockcount = offset - PREV.rm_offset;
cur->bc_rec.r = NEW;
- trace_xfs_rmap_insert(mp, cur->bc_ag.pag->pag_agno,
- NEW.rm_startblock, NEW.rm_blockcount,
- NEW.rm_owner, NEW.rm_offset,
+ trace_xfs_rmap_insert(cur, NEW.rm_startblock,
+ NEW.rm_blockcount, NEW.rm_owner, NEW.rm_offset,
NEW.rm_flags);
error = xfs_btree_insert(cur, &i);
if (error)
@@ -1669,8 +1634,7 @@ xfs_rmap_convert(
/* new middle extent - newext */
cur->bc_rec.r.rm_flags &= ~XFS_RMAP_UNWRITTEN;
cur->bc_rec.r.rm_flags |= newext;
- trace_xfs_rmap_insert(mp, cur->bc_ag.pag->pag_agno, bno, len,
- owner, offset, newext);
+ trace_xfs_rmap_insert(cur, bno, len, owner, offset, newext);
error = xfs_btree_insert(cur, &i);
if (error)
goto done;
@@ -1694,12 +1658,10 @@ xfs_rmap_convert(
ASSERT(0);
}
- trace_xfs_rmap_convert_done(mp, cur->bc_ag.pag->pag_agno, bno, len,
- unwritten, oinfo);
+ trace_xfs_rmap_convert_done(cur, bno, len, unwritten, oinfo);
done:
if (error)
- trace_xfs_rmap_convert_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_rmap_convert_error(cur, error, _RET_IP_);
return error;
}
@@ -1735,8 +1697,7 @@ xfs_rmap_convert_shared(
(flags & (XFS_RMAP_ATTR_FORK | XFS_RMAP_BMBT_BLOCK))));
oldext = unwritten ? XFS_RMAP_UNWRITTEN : 0;
new_endoff = offset + len;
- trace_xfs_rmap_convert(mp, cur->bc_ag.pag->pag_agno, bno, len,
- unwritten, oinfo);
+ trace_xfs_rmap_convert(cur, bno, len, unwritten, oinfo);
/*
* For the initial lookup, look for and exact match or the left-adjacent
@@ -1805,10 +1766,10 @@ xfs_rmap_convert_shared(
error = -EFSCORRUPTED;
goto done;
}
- trace_xfs_rmap_find_right_neighbor_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, RIGHT.rm_startblock,
- RIGHT.rm_blockcount, RIGHT.rm_owner,
- RIGHT.rm_offset, RIGHT.rm_flags);
+ trace_xfs_rmap_find_right_neighbor_result(cur,
+ RIGHT.rm_startblock, RIGHT.rm_blockcount,
+ RIGHT.rm_owner, RIGHT.rm_offset,
+ RIGHT.rm_flags);
if (xfs_rmap_is_mergeable(&RIGHT, owner, newext))
state |= RMAP_RIGHT_CONTIG;
}
@@ -1822,8 +1783,7 @@ xfs_rmap_convert_shared(
RIGHT.rm_blockcount > XFS_RMAP_LEN_MAX)
state &= ~RMAP_RIGHT_CONTIG;
- trace_xfs_rmap_convert_state(mp, cur->bc_ag.pag->pag_agno, state,
- _RET_IP_);
+ trace_xfs_rmap_convert_state(cur, state, _RET_IP_);
/*
* Switch out based on the FILLING and CONTIG state bits.
*/
@@ -2121,12 +2081,10 @@ xfs_rmap_convert_shared(
ASSERT(0);
}
- trace_xfs_rmap_convert_done(mp, cur->bc_ag.pag->pag_agno, bno, len,
- unwritten, oinfo);
+ trace_xfs_rmap_convert_done(cur, bno, len, unwritten, oinfo);
done:
if (error)
- trace_xfs_rmap_convert_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_rmap_convert_error(cur, error, _RET_IP_);
return error;
}
@@ -2164,8 +2122,7 @@ xfs_rmap_unmap_shared(
xfs_owner_info_unpack(oinfo, &owner, &offset, &flags);
if (unwritten)
flags |= XFS_RMAP_UNWRITTEN;
- trace_xfs_rmap_unmap(mp, cur->bc_ag.pag->pag_agno, bno, len,
- unwritten, oinfo);
+ trace_xfs_rmap_unmap(cur, bno, len, unwritten, oinfo);
/*
* We should always have a left record because there's a static record
@@ -2321,12 +2278,10 @@ xfs_rmap_unmap_shared(
goto out_error;
}
- trace_xfs_rmap_unmap_done(mp, cur->bc_ag.pag->pag_agno, bno, len,
- unwritten, oinfo);
+ trace_xfs_rmap_unmap_done(cur, bno, len, unwritten, oinfo);
out_error:
if (error)
- trace_xfs_rmap_unmap_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_rmap_unmap_error(cur, error, _RET_IP_);
return error;
}
@@ -2361,8 +2316,7 @@ xfs_rmap_map_shared(
xfs_owner_info_unpack(oinfo, &owner, &offset, &flags);
if (unwritten)
flags |= XFS_RMAP_UNWRITTEN;
- trace_xfs_rmap_map(mp, cur->bc_ag.pag->pag_agno, bno, len,
- unwritten, oinfo);
+ trace_xfs_rmap_map(cur, bno, len, unwritten, oinfo);
/* Is there a left record that abuts our range? */
error = xfs_rmap_find_left_neighbor(cur, bno, owner, offset, flags,
@@ -2387,10 +2341,10 @@ xfs_rmap_map_shared(
error = -EFSCORRUPTED;
goto out_error;
}
- trace_xfs_rmap_find_right_neighbor_result(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, gtrec.rm_startblock,
- gtrec.rm_blockcount, gtrec.rm_owner,
- gtrec.rm_offset, gtrec.rm_flags);
+ trace_xfs_rmap_find_right_neighbor_result(cur,
+ gtrec.rm_startblock, gtrec.rm_blockcount,
+ gtrec.rm_owner, gtrec.rm_offset,
+ gtrec.rm_flags);
if (!xfs_rmap_is_mergeable(&gtrec, owner, flags))
have_gt = 0;
@@ -2482,12 +2436,10 @@ xfs_rmap_map_shared(
goto out_error;
}
- trace_xfs_rmap_map_done(mp, cur->bc_ag.pag->pag_agno, bno, len,
- unwritten, oinfo);
+ trace_xfs_rmap_map_done(cur, bno, len, unwritten, oinfo);
out_error:
if (error)
- trace_xfs_rmap_map_error(cur->bc_mp,
- cur->bc_ag.pag->pag_agno, error, _RET_IP_);
+ trace_xfs_rmap_map_error(cur, error, _RET_IP_);
return error;
}
@@ -2572,23 +2524,6 @@ xfs_rmap_query_all(
return xfs_btree_query_all(cur, xfs_rmap_query_range_helper, &query);
}
-/* Clean up after calling xfs_rmap_finish_one. */
-void
-xfs_rmap_finish_one_cleanup(
- struct xfs_trans *tp,
- struct xfs_btree_cur *rcur,
- int error)
-{
- struct xfs_buf *agbp;
-
- if (rcur == NULL)
- return;
- agbp = rcur->bc_ag.agbp;
- xfs_btree_del_cursor(rcur, error);
- if (error)
- xfs_trans_brelse(tp, agbp);
-}
-
/* Commit an rmap operation into the ondisk tree. */
int
__xfs_rmap_finish_intent(
@@ -2634,20 +2569,15 @@ xfs_rmap_finish_one(
struct xfs_rmap_intent *ri,
struct xfs_btree_cur **pcur)
{
+ struct xfs_owner_info oinfo;
struct xfs_mount *mp = tp->t_mountp;
- struct xfs_btree_cur *rcur;
+ struct xfs_btree_cur *rcur = *pcur;
struct xfs_buf *agbp = NULL;
- int error = 0;
- struct xfs_owner_info oinfo;
xfs_agblock_t bno;
bool unwritten;
+ int error = 0;
- bno = XFS_FSB_TO_AGBNO(mp, ri->ri_bmap.br_startblock);
-
- trace_xfs_rmap_deferred(mp, ri->ri_pag->pag_agno, ri->ri_type, bno,
- ri->ri_owner, ri->ri_whichfork,
- ri->ri_bmap.br_startoff, ri->ri_bmap.br_blockcount,
- ri->ri_bmap.br_state);
+ trace_xfs_rmap_deferred(mp, ri);
if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_RMAP_FINISH_ONE))
return -EIO;
@@ -2656,9 +2586,8 @@ xfs_rmap_finish_one(
* If we haven't gotten a cursor or the cursor AG doesn't match
* the startblock, get one now.
*/
- rcur = *pcur;
if (rcur != NULL && rcur->bc_ag.pag != ri->ri_pag) {
- xfs_rmap_finish_one_cleanup(tp, rcur, 0);
+ xfs_btree_del_cursor(rcur, 0);
rcur = NULL;
*pcur = NULL;
}
@@ -2678,9 +2607,8 @@ xfs_rmap_finish_one(
return -EFSCORRUPTED;
}
- rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, ri->ri_pag);
+ *pcur = rcur = xfs_rmapbt_init_cursor(mp, tp, agbp, ri->ri_pag);
}
- *pcur = rcur;
xfs_rmap_ino_owner(&oinfo, ri->ri_owner, ri->ri_whichfork,
ri->ri_bmap.br_startoff);
@@ -2722,15 +2650,6 @@ __xfs_rmap_add(
{
struct xfs_rmap_intent *ri;
- trace_xfs_rmap_defer(tp->t_mountp,
- XFS_FSB_TO_AGNO(tp->t_mountp, bmap->br_startblock),
- type,
- XFS_FSB_TO_AGBNO(tp->t_mountp, bmap->br_startblock),
- owner, whichfork,
- bmap->br_startoff,
- bmap->br_blockcount,
- bmap->br_state);
-
ri = kmem_cache_alloc(xfs_rmap_intent_cache, GFP_KERNEL | __GFP_NOFAIL);
INIT_LIST_HEAD(&ri->ri_list);
ri->ri_type = type;
@@ -2738,8 +2657,7 @@ __xfs_rmap_add(
ri->ri_whichfork = whichfork;
ri->ri_bmap = *bmap;
- xfs_rmap_update_get_group(tp->t_mountp, ri);
- xfs_defer_add(tp, &ri->ri_list, &xfs_rmap_update_defer_type);
+ xfs_rmap_defer_add(tp, ri);
}
/* Map an extent into a file. */
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 9d01fe689497..b783dd4dd95d 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -157,6 +157,16 @@ enum xfs_rmap_intent_type {
XFS_RMAP_FREE,
};
+#define XFS_RMAP_INTENT_STRINGS \
+ { XFS_RMAP_MAP, "map" }, \
+ { XFS_RMAP_MAP_SHARED, "map_shared" }, \
+ { XFS_RMAP_UNMAP, "unmap" }, \
+ { XFS_RMAP_UNMAP_SHARED, "unmap_shared" }, \
+ { XFS_RMAP_CONVERT, "cvt" }, \
+ { XFS_RMAP_CONVERT_SHARED, "cvt_shared" }, \
+ { XFS_RMAP_ALLOC, "alloc" }, \
+ { XFS_RMAP_FREE, "free" }
+
struct xfs_rmap_intent {
struct list_head ri_list;
enum xfs_rmap_intent_type ri_type;
@@ -166,9 +176,6 @@ struct xfs_rmap_intent {
struct xfs_perag *ri_pag;
};
-void xfs_rmap_update_get_group(struct xfs_mount *mp,
- struct xfs_rmap_intent *ri);
-
/* functions for updating the rmapbt based on bmbt map/unmap operations */
void xfs_rmap_map_extent(struct xfs_trans *tp, struct xfs_inode *ip,
int whichfork, struct xfs_bmbt_irec *imap);
@@ -182,8 +189,6 @@ void xfs_rmap_alloc_extent(struct xfs_trans *tp, xfs_agnumber_t agno,
void xfs_rmap_free_extent(struct xfs_trans *tp, xfs_agnumber_t agno,
xfs_agblock_t bno, xfs_extlen_t len, uint64_t owner);
-void xfs_rmap_finish_one_cleanup(struct xfs_trans *tp,
- struct xfs_btree_cur *rcur, int error);
int xfs_rmap_finish_one(struct xfs_trans *tp, struct xfs_rmap_intent *ri,
struct xfs_btree_cur **pcur);
int __xfs_rmap_finish_intent(struct xfs_btree_cur *rcur,
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 9e759efa81cc..56fd6c4bd8b4 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -88,6 +88,7 @@ xfs_rmapbt_alloc_block(
struct xfs_buf *agbp = cur->bc_ag.agbp;
struct xfs_agf *agf = agbp->b_addr;
struct xfs_perag *pag = cur->bc_ag.pag;
+ struct xfs_alloc_arg args = { .len = 1 };
int error;
xfs_agblock_t bno;
@@ -107,7 +108,11 @@ xfs_rmapbt_alloc_block(
be32_add_cpu(&agf->agf_rmap_blocks, 1);
xfs_alloc_log_agf(cur->bc_tp, agbp, XFS_AGF_RMAP_BLOCKS);
- xfs_ag_resv_rmapbt_alloc(cur->bc_mp, pag->pag_agno);
+ /*
+ * Since rmapbt blocks are sourced from the AGFL, they are allocated one
+ * at a time and the reservation updates don't require a transaction.
+ */
+ xfs_ag_resv_alloc_extent(pag, XFS_AG_RESV_RMAPBT, &args);
*stat = 1;
return 0;
diff --git a/fs/xfs/libxfs/xfs_shared.h b/fs/xfs/libxfs/xfs_shared.h
index 34f104ed372c..2f7413afbf46 100644
--- a/fs/xfs/libxfs/xfs_shared.h
+++ b/fs/xfs/libxfs/xfs_shared.h
@@ -177,13 +177,6 @@ void xfs_log_get_max_trans_res(struct xfs_mount *mp,
#define XFS_REFC_BTREE_REF 1
#define XFS_SSB_REF 0
-/*
- * Flags for xfs_trans_ichgtime().
- */
-#define XFS_ICHGTIME_MOD 0x1 /* data fork modification timestamp */
-#define XFS_ICHGTIME_CHG 0x2 /* inode field change timestamp */
-#define XFS_ICHGTIME_CREATE 0x4 /* inode create timestamp */
-
/* Computed inode geometry for the filesystem. */
struct xfs_ino_geometry {
/* Maximum inode count in this filesystem. */
diff --git a/fs/xfs/libxfs/xfs_trans_inode.c b/fs/xfs/libxfs/xfs_trans_inode.c
index 69fc5b981352..3c40f37e82c7 100644
--- a/fs/xfs/libxfs/xfs_trans_inode.c
+++ b/fs/xfs/libxfs/xfs_trans_inode.c
@@ -68,6 +68,8 @@ xfs_trans_ichgtime(
inode_set_mtime_to_ts(inode, tv);
if (flags & XFS_ICHGTIME_CHG)
inode_set_ctime_to_ts(inode, tv);
+ if (flags & XFS_ICHGTIME_ACCESS)
+ inode_set_atime_to_ts(inode, tv);
if (flags & XFS_ICHGTIME_CREATE)
ip->i_crtime = tv;
}
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index 6dbe6e7251e7..3dc8f785bf29 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -22,7 +22,6 @@
#include "xfs_rtbitmap.h"
#include "xfs_attr_item.h"
#include "xfs_log.h"
-#include "xfs_da_format.h"
#define _ALLOC true
#define _FREE false