Update Linux to v5.4.2
Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 05db954..18f4b26 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -3,7 +3,6 @@
* Copyright (c) 2000-2006 Silicon Graphics, Inc.
* All Rights Reserved.
*/
-#include <linux/log2.h>
#include <linux/iversion.h>
#include "xfs.h"
@@ -16,10 +15,7 @@
#include "xfs_mount.h"
#include "xfs_defer.h"
#include "xfs_inode.h"
-#include "xfs_da_format.h"
-#include "xfs_da_btree.h"
#include "xfs_dir2.h"
-#include "xfs_attr_sf.h"
#include "xfs_attr.h"
#include "xfs_trans_space.h"
#include "xfs_trans.h"
@@ -32,7 +28,6 @@
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_filestream.h"
-#include "xfs_cksum.h"
#include "xfs_trace.h"
#include "xfs_icache.h"
#include "xfs_symlink.h"
@@ -40,7 +35,6 @@
#include "xfs_log.h"
#include "xfs_bmap_btree.h"
#include "xfs_reflink.h"
-#include "xfs_dir2_priv.h"
kmem_zone_t *xfs_inode_zone;
@@ -441,12 +435,12 @@
*/
static void
xfs_lock_inodes(
- xfs_inode_t **ips,
- int inodes,
- uint lock_mode)
+ struct xfs_inode **ips,
+ int inodes,
+ uint lock_mode)
{
- int attempts = 0, i, j, try_lock;
- xfs_log_item_t *lp;
+ int attempts = 0, i, j, try_lock;
+ struct xfs_log_item *lp;
/*
* Currently supports between 2 and 5 inodes with exclusive locking. We
@@ -485,7 +479,7 @@
*/
if (!try_lock) {
for (j = (i - 1); j >= 0 && !try_lock; j--) {
- lp = (xfs_log_item_t *)ips[j]->i_itemp;
+ lp = &ips[j]->i_itemp->ili_item;
if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags))
try_lock++;
}
@@ -551,7 +545,7 @@
struct xfs_inode *temp;
uint mode_temp;
int attempts = 0;
- xfs_log_item_t *lp;
+ struct xfs_log_item *lp;
ASSERT(hweight32(ip0_mode) == 1);
ASSERT(hweight32(ip1_mode) == 1);
@@ -585,7 +579,7 @@
* the second lock. If we can't get it, we must release the first one
* and try again.
*/
- lp = (xfs_log_item_t *)ip0->i_itemp;
+ lp = &ip0->i_itemp->ili_item;
if (lp && test_bit(XFS_LI_IN_AIL, &lp->li_flags)) {
if (!xfs_ilock_nowait(ip1, xfs_lock_inumorder(ip1_mode, 1))) {
xfs_iunlock(ip0, ip0_mode);
@@ -1116,7 +1110,7 @@
/*
* Increment the link count on an inode & log the change.
*/
-static int
+static void
xfs_bumplink(
xfs_trans_t *tp,
xfs_inode_t *ip)
@@ -1126,7 +1120,6 @@
ASSERT(ip->i_d.di_version > 1);
inc_nlink(VFS_I(ip));
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
- return 0;
}
int
@@ -1235,9 +1228,7 @@
if (error)
goto out_trans_cancel;
- error = xfs_bumplink(tp, dp);
- if (error)
- goto out_trans_cancel;
+ xfs_bumplink(tp, dp);
}
/*
@@ -1332,7 +1323,7 @@
if (error)
goto out_trans_cancel;
- error = xfs_dir_ialloc(&tp, dp, mode, 1, 0, prid, &ip);
+ error = xfs_dir_ialloc(&tp, dp, mode, 0, 0, prid, &ip);
if (error)
goto out_trans_cancel;
@@ -1454,9 +1445,7 @@
xfs_trans_ichgtime(tp, tdp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
xfs_trans_log_inode(tp, tdp, XFS_ILOG_CORE);
- error = xfs_bumplink(tp, sip);
- if (error)
- goto error_return;
+ xfs_bumplink(tp, sip);
/*
* If this is a synchronous mount, make sure that the
@@ -1754,7 +1743,7 @@
* now remains allocated and sits on the unlinked list until the fs is
* repaired.
*/
- if (unlikely(mp->m_inotbt_nores)) {
+ if (unlikely(mp->m_finobt_nores)) {
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ifree,
XFS_IFREE_SPACE_RES(mp), 0, XFS_TRANS_RESERVE,
&tp);
@@ -1907,86 +1896,510 @@
}
/*
- * This is called when the inode's link count goes to 0 or we are creating a
- * tmpfile via O_TMPFILE. In the case of a tmpfile, @ignore_linkcount will be
- * set to true as the link count is dropped to zero by the VFS after we've
- * created the file successfully, so we have to add it to the unlinked list
- * while the link count is non-zero.
+ * 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.
+ *
+ * What if we modelled the unlinked list as a collection of records capturing
+ * "X.next_unlinked = Y" relations? If we indexed those records on Y, we'd
+ * have a fast way to look up unlinked list predecessors, which avoids the
+ * slow list walk. That's exactly what we do here (in-core) with a per-AG
+ * rhashtable.
+ *
+ * Because this is a backref cache, we ignore operational failures since the
+ * iunlink code can fall back to the slow bucket walk. The only errors that
+ * should bubble out are for obviously incorrect situations.
+ *
+ * All users of the backref cache MUST hold the AGI buffer lock to serialize
+ * access or have otherwise provided for concurrency control.
+ */
+
+/* Capture a "X.next_unlinked = Y" relationship. */
+struct xfs_iunlink {
+ struct rhash_head iu_rhash_head;
+ xfs_agino_t iu_agino; /* X */
+ xfs_agino_t iu_next_unlinked; /* Y */
+};
+
+/* Unlinked list predecessor lookup hashtable construction */
+static int
+xfs_iunlink_obj_cmpfn(
+ struct rhashtable_compare_arg *arg,
+ const void *obj)
+{
+ const xfs_agino_t *key = arg->key;
+ const struct xfs_iunlink *iu = obj;
+
+ if (iu->iu_next_unlinked != *key)
+ return 1;
+ return 0;
+}
+
+static const struct rhashtable_params xfs_iunlink_hash_params = {
+ .min_size = XFS_AGI_UNLINKED_BUCKETS,
+ .key_len = sizeof(xfs_agino_t),
+ .key_offset = offsetof(struct xfs_iunlink,
+ iu_next_unlinked),
+ .head_offset = offsetof(struct xfs_iunlink, iu_rhash_head),
+ .automatic_shrinking = true,
+ .obj_cmpfn = xfs_iunlink_obj_cmpfn,
+};
+
+/*
+ * Return X, where X.next_unlinked == @agino. Returns NULLAGINO if no such
+ * relation is found.
+ */
+static xfs_agino_t
+xfs_iunlink_lookup_backref(
+ struct xfs_perag *pag,
+ xfs_agino_t agino)
+{
+ struct xfs_iunlink *iu;
+
+ iu = rhashtable_lookup_fast(&pag->pagi_unlinked_hash, &agino,
+ xfs_iunlink_hash_params);
+ return iu ? iu->iu_agino : NULLAGINO;
+}
+
+/*
+ * Take ownership of an iunlink cache entry and insert it into the hash table.
+ * If successful, the entry will be owned by the cache; if not, it is freed.
+ * Either way, the caller does not own @iu after this call.
+ */
+static int
+xfs_iunlink_insert_backref(
+ struct xfs_perag *pag,
+ struct xfs_iunlink *iu)
+{
+ int error;
+
+ error = rhashtable_insert_fast(&pag->pagi_unlinked_hash,
+ &iu->iu_rhash_head, xfs_iunlink_hash_params);
+ /*
+ * Fail loudly if there already was an entry because that's a sign of
+ * corruption of in-memory data. Also fail loudly if we see an error
+ * code we didn't anticipate from the rhashtable code. Currently we
+ * only anticipate ENOMEM.
+ */
+ if (error) {
+ WARN(error != -ENOMEM, "iunlink cache insert error %d", error);
+ kmem_free(iu);
+ }
+ /*
+ * Absorb any runtime errors that aren't a result of corruption because
+ * this is a cache and we can always fall back to bucket list scanning.
+ */
+ if (error != 0 && error != -EEXIST)
+ error = 0;
+ return error;
+}
+
+/* Remember that @prev_agino.next_unlinked = @this_agino. */
+static int
+xfs_iunlink_add_backref(
+ struct xfs_perag *pag,
+ xfs_agino_t prev_agino,
+ xfs_agino_t this_agino)
+{
+ struct xfs_iunlink *iu;
+
+ if (XFS_TEST_ERROR(false, pag->pag_mount, XFS_ERRTAG_IUNLINK_FALLBACK))
+ return 0;
+
+ iu = kmem_zalloc(sizeof(*iu), KM_NOFS);
+ iu->iu_agino = prev_agino;
+ iu->iu_next_unlinked = this_agino;
+
+ return xfs_iunlink_insert_backref(pag, iu);
+}
+
+/*
+ * Replace X.next_unlinked = @agino with X.next_unlinked = @next_unlinked.
+ * If @next_unlinked is NULLAGINO, we drop the backref and exit. If there
+ * wasn't any such entry then we don't bother.
+ */
+static int
+xfs_iunlink_change_backref(
+ struct xfs_perag *pag,
+ xfs_agino_t agino,
+ xfs_agino_t next_unlinked)
+{
+ struct xfs_iunlink *iu;
+ int error;
+
+ /* Look up the old entry; if there wasn't one then exit. */
+ iu = rhashtable_lookup_fast(&pag->pagi_unlinked_hash, &agino,
+ xfs_iunlink_hash_params);
+ if (!iu)
+ return 0;
+
+ /*
+ * Remove the entry. This shouldn't ever return an error, but if we
+ * couldn't remove the old entry we don't want to add it again to the
+ * hash table, and if the entry disappeared on us then someone's
+ * violated the locking rules and we need to fail loudly. Either way
+ * we cannot remove the inode because internal state is or would have
+ * been corrupt.
+ */
+ error = rhashtable_remove_fast(&pag->pagi_unlinked_hash,
+ &iu->iu_rhash_head, xfs_iunlink_hash_params);
+ if (error)
+ return error;
+
+ /* If there is no new next entry just free our item and return. */
+ if (next_unlinked == NULLAGINO) {
+ kmem_free(iu);
+ return 0;
+ }
+
+ /* Update the entry and re-add it to the hash table. */
+ iu->iu_next_unlinked = next_unlinked;
+ return xfs_iunlink_insert_backref(pag, iu);
+}
+
+/* Set up the in-core predecessor structures. */
+int
+xfs_iunlink_init(
+ struct xfs_perag *pag)
+{
+ return rhashtable_init(&pag->pagi_unlinked_hash,
+ &xfs_iunlink_hash_params);
+}
+
+/* Free the in-core predecessor structures. */
+static void
+xfs_iunlink_free_item(
+ void *ptr,
+ void *arg)
+{
+ struct xfs_iunlink *iu = ptr;
+ bool *freed_anything = arg;
+
+ *freed_anything = true;
+ kmem_free(iu);
+}
+
+void
+xfs_iunlink_destroy(
+ struct xfs_perag *pag)
+{
+ bool freed_anything = false;
+
+ rhashtable_free_and_destroy(&pag->pagi_unlinked_hash,
+ xfs_iunlink_free_item, &freed_anything);
+
+ ASSERT(freed_anything == false || XFS_FORCED_SHUTDOWN(pag->pag_mount));
+}
+
+/*
+ * 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,
+ xfs_agnumber_t agno,
+ struct xfs_buf *agibp,
+ unsigned int bucket_index,
+ xfs_agino_t new_agino)
+{
+ struct xfs_agi *agi = XFS_BUF_TO_AGI(agibp);
+ xfs_agino_t old_value;
+ int offset;
+
+ ASSERT(xfs_verify_agino_or_null(tp->t_mountp, agno, new_agino));
+
+ old_value = be32_to_cpu(agi->agi_unlinked[bucket_index]);
+ trace_xfs_iunlink_update_bucket(tp->t_mountp, 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)
+ 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;
+}
+
+/* Set an on-disk inode's next_unlinked pointer. */
+STATIC void
+xfs_iunlink_update_dinode(
+ struct xfs_trans *tp,
+ xfs_agnumber_t agno,
+ xfs_agino_t agino,
+ struct xfs_buf *ibp,
+ struct xfs_dinode *dip,
+ struct xfs_imap *imap,
+ xfs_agino_t next_agino)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ int offset;
+
+ ASSERT(xfs_verify_agino_or_null(mp, agno, next_agino));
+
+ trace_xfs_iunlink_update_dinode(mp, agno, agino,
+ be32_to_cpu(dip->di_next_unlinked), next_agino);
+
+ dip->di_next_unlinked = cpu_to_be32(next_agino);
+ offset = imap->im_boffset +
+ offsetof(struct xfs_dinode, di_next_unlinked);
+
+ /* need to recalc the inode CRC if appropriate */
+ xfs_dinode_calc_crc(mp, dip);
+ xfs_trans_inode_buf(tp, ibp);
+ xfs_trans_log_buf(tp, ibp, offset, offset + sizeof(xfs_agino_t) - 1);
+ xfs_inobp_check(mp, ibp);
+}
+
+/* Set an in-core inode's unlinked pointer and return the old value. */
+STATIC int
+xfs_iunlink_update_inode(
+ struct xfs_trans *tp,
+ struct xfs_inode *ip,
+ xfs_agnumber_t agno,
+ xfs_agino_t next_agino,
+ xfs_agino_t *old_next_agino)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_dinode *dip;
+ struct xfs_buf *ibp;
+ xfs_agino_t old_value;
+ int error;
+
+ ASSERT(xfs_verify_agino_or_null(mp, agno, next_agino));
+
+ error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp, 0, 0);
+ if (error)
+ return error;
+
+ /* Make sure the old pointer isn't garbage. */
+ old_value = be32_to_cpu(dip->di_next_unlinked);
+ if (!xfs_verify_agino_or_null(mp, agno, old_value)) {
+ error = -EFSCORRUPTED;
+ goto out;
+ }
+
+ /*
+ * Since we're updating a linked list, we should never find that the
+ * current pointer is the same as the new value, unless we're
+ * terminating the list.
+ */
+ *old_next_agino = old_value;
+ if (old_value == next_agino) {
+ if (next_agino != NULLAGINO)
+ error = -EFSCORRUPTED;
+ goto out;
+ }
+
+ /* Ok, update the new pointer. */
+ xfs_iunlink_update_dinode(tp, agno, XFS_INO_TO_AGINO(mp, ip->i_ino),
+ ibp, dip, &ip->i_imap, next_agino);
+ return 0;
+out:
+ xfs_trans_brelse(tp, ibp);
+ return error;
+}
+
+/*
+ * 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.
*/
STATIC int
xfs_iunlink(
- struct xfs_trans *tp,
- struct xfs_inode *ip)
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
{
- xfs_mount_t *mp = tp->t_mountp;
- xfs_agi_t *agi;
- xfs_dinode_t *dip;
- xfs_buf_t *agibp;
- xfs_buf_t *ibp;
- xfs_agino_t agino;
- short bucket_index;
- int offset;
- int error;
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_agi *agi;
+ struct xfs_buf *agibp;
+ xfs_agino_t next_agino;
+ xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
+ xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
+ short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
+ int error;
+ ASSERT(VFS_I(ip)->i_nlink == 0);
ASSERT(VFS_I(ip)->i_mode != 0);
+ trace_xfs_iunlink(ip);
- /*
- * Get the agi buffer first. It ensures lock ordering
- * on the list.
- */
- error = xfs_read_agi(mp, tp, XFS_INO_TO_AGNO(mp, ip->i_ino), &agibp);
+ /* Get the agi buffer first. It ensures lock ordering on the list. */
+ error = xfs_read_agi(mp, tp, agno, &agibp);
if (error)
return error;
agi = XFS_BUF_TO_AGI(agibp);
/*
- * Get the index into the agi hash table for the
- * list this inode will go on.
+ * 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.
*/
- agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
- ASSERT(agino != 0);
- bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
- ASSERT(agi->agi_unlinked[bucket_index]);
- ASSERT(be32_to_cpu(agi->agi_unlinked[bucket_index]) != agino);
+ next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
+ if (next_agino == agino ||
+ !xfs_verify_agino_or_null(mp, agno, next_agino))
+ return -EFSCORRUPTED;
- if (agi->agi_unlinked[bucket_index] != cpu_to_be32(NULLAGINO)) {
+ if (next_agino != NULLAGINO) {
+ struct xfs_perag *pag;
+ xfs_agino_t old_agino;
+
/*
- * There is already another inode in the bucket we need
- * to add ourselves to. Add us at the front of the list.
- * Here we put the head pointer into our next pointer,
- * and then we fall through to point the head at us.
+ * There is already another inode in the bucket, so point this
+ * inode to the current head of the list.
*/
- error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
- 0, 0);
+ error = xfs_iunlink_update_inode(tp, ip, agno, next_agino,
+ &old_agino);
+ if (error)
+ return error;
+ ASSERT(old_agino == NULLAGINO);
+
+ /*
+ * agino has been unlinked, add a backref from the next inode
+ * back to agino.
+ */
+ pag = xfs_perag_get(mp, agno);
+ error = xfs_iunlink_add_backref(pag, agino, next_agino);
+ xfs_perag_put(pag);
+ if (error)
+ return error;
+ }
+
+ /* Point the head of the list to point to this inode. */
+ return xfs_iunlink_update_bucket(tp, agno, agibp, bucket_index, agino);
+}
+
+/* Return the imap, dinode pointer, and buffer for an inode. */
+STATIC int
+xfs_iunlink_map_ino(
+ struct xfs_trans *tp,
+ xfs_agnumber_t agno,
+ xfs_agino_t agino,
+ struct xfs_imap *imap,
+ struct xfs_dinode **dipp,
+ struct xfs_buf **bpp)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ int error;
+
+ imap->im_blkno = 0;
+ error = xfs_imap(mp, tp, XFS_AGINO_TO_INO(mp, agno, agino), imap, 0);
+ if (error) {
+ xfs_warn(mp, "%s: xfs_imap returned error %d.",
+ __func__, error);
+ return error;
+ }
+
+ error = xfs_imap_to_bp(mp, tp, imap, dipp, bpp, 0, 0);
+ if (error) {
+ xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.",
+ __func__, error);
+ return error;
+ }
+
+ return 0;
+}
+
+/*
+ * Walk the unlinked chain from @head_agino until we find the inode that
+ * points to @target_agino. Return the inode number, map, dinode pointer,
+ * and inode cluster buffer of that inode as @agino, @imap, @dipp, and @bpp.
+ *
+ * @tp, @pag, @head_agino, and @target_agino are input parameters.
+ * @agino, @imap, @dipp, and @bpp are all output parameters.
+ *
+ * Do not call this function if @target_agino is the head of the list.
+ */
+STATIC int
+xfs_iunlink_map_prev(
+ struct xfs_trans *tp,
+ xfs_agnumber_t agno,
+ xfs_agino_t head_agino,
+ xfs_agino_t target_agino,
+ xfs_agino_t *agino,
+ struct xfs_imap *imap,
+ struct xfs_dinode **dipp,
+ struct xfs_buf **bpp,
+ struct xfs_perag *pag)
+{
+ struct xfs_mount *mp = tp->t_mountp;
+ xfs_agino_t next_agino;
+ int error;
+
+ ASSERT(head_agino != target_agino);
+ *bpp = NULL;
+
+ /* See if our backref cache can find it faster. */
+ *agino = xfs_iunlink_lookup_backref(pag, target_agino);
+ if (*agino != NULLAGINO) {
+ error = xfs_iunlink_map_ino(tp, agno, *agino, imap, dipp, bpp);
if (error)
return error;
- ASSERT(dip->di_next_unlinked == cpu_to_be32(NULLAGINO));
- dip->di_next_unlinked = agi->agi_unlinked[bucket_index];
- offset = ip->i_imap.im_boffset +
- offsetof(xfs_dinode_t, di_next_unlinked);
+ if (be32_to_cpu((*dipp)->di_next_unlinked) == target_agino)
+ return 0;
- /* need to recalc the inode CRC if appropriate */
- xfs_dinode_calc_crc(mp, dip);
-
- xfs_trans_inode_buf(tp, ibp);
- xfs_trans_log_buf(tp, ibp, offset,
- (offset + sizeof(xfs_agino_t) - 1));
- xfs_inobp_check(mp, ibp);
+ /*
+ * If we get here the cache contents were corrupt, so drop the
+ * buffer and fall back to walking the bucket list.
+ */
+ xfs_trans_brelse(tp, *bpp);
+ *bpp = NULL;
+ WARN_ON_ONCE(1);
}
- /*
- * Point the bucket head pointer at the inode being inserted.
- */
- ASSERT(agino != 0);
- agi->agi_unlinked[bucket_index] = cpu_to_be32(agino);
- offset = offsetof(xfs_agi_t, agi_unlinked) +
- (sizeof(xfs_agino_t) * bucket_index);
- xfs_trans_log_buf(tp, agibp, offset,
- (offset + sizeof(xfs_agino_t) - 1));
+ trace_xfs_iunlink_map_prev_fallback(mp, agno);
+
+ /* Otherwise, walk the entire bucket until we find it. */
+ next_agino = head_agino;
+ while (next_agino != target_agino) {
+ xfs_agino_t unlinked_agino;
+
+ if (*bpp)
+ xfs_trans_brelse(tp, *bpp);
+
+ *agino = next_agino;
+ error = xfs_iunlink_map_ino(tp, agno, next_agino, imap, dipp,
+ bpp);
+ if (error)
+ return error;
+
+ unlinked_agino = be32_to_cpu((*dipp)->di_next_unlinked);
+ /*
+ * Make sure this pointer is valid and isn't an obvious
+ * infinite loop.
+ */
+ if (!xfs_verify_agino(mp, agno, unlinked_agino) ||
+ next_agino == unlinked_agino) {
+ XFS_CORRUPTION_ERROR(__func__,
+ XFS_ERRLEVEL_LOW, mp,
+ *dipp, sizeof(**dipp));
+ error = -EFSCORRUPTED;
+ return error;
+ }
+ next_agino = unlinked_agino;
+ }
+
return 0;
}
@@ -1995,181 +2408,106 @@
*/
STATIC int
xfs_iunlink_remove(
- xfs_trans_t *tp,
- xfs_inode_t *ip)
+ struct xfs_trans *tp,
+ struct xfs_inode *ip)
{
- xfs_ino_t next_ino;
- xfs_mount_t *mp;
- xfs_agi_t *agi;
- xfs_dinode_t *dip;
- xfs_buf_t *agibp;
- xfs_buf_t *ibp;
- xfs_agnumber_t agno;
- xfs_agino_t agino;
- xfs_agino_t next_agino;
- xfs_buf_t *last_ibp;
- xfs_dinode_t *last_dip = NULL;
- short bucket_index;
- int offset, last_offset = 0;
- int error;
+ struct xfs_mount *mp = tp->t_mountp;
+ struct xfs_agi *agi;
+ struct xfs_buf *agibp;
+ struct xfs_buf *last_ibp;
+ struct xfs_dinode *last_dip = NULL;
+ struct xfs_perag *pag = NULL;
+ xfs_agnumber_t agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
+ xfs_agino_t agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
+ xfs_agino_t next_agino;
+ xfs_agino_t head_agino;
+ short bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
+ int error;
- mp = tp->t_mountp;
- agno = XFS_INO_TO_AGNO(mp, ip->i_ino);
+ trace_xfs_iunlink_remove(ip);
- /*
- * Get the agi buffer first. It ensures lock ordering
- * on the list.
- */
+ /* Get the agi buffer first. It ensures lock ordering on the list. */
error = xfs_read_agi(mp, tp, agno, &agibp);
if (error)
return error;
-
agi = XFS_BUF_TO_AGI(agibp);
/*
- * Get the index into the agi hash table for the
- * list this inode will go on.
+ * Get the index into the agi hash table for the list this inode will
+ * go on. Make sure the head pointer isn't garbage.
*/
- agino = XFS_INO_TO_AGINO(mp, ip->i_ino);
- if (!xfs_verify_agino(mp, agno, agino))
- return -EFSCORRUPTED;
- bucket_index = agino % XFS_AGI_UNLINKED_BUCKETS;
- if (!xfs_verify_agino(mp, agno,
- be32_to_cpu(agi->agi_unlinked[bucket_index]))) {
+ head_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
+ if (!xfs_verify_agino(mp, agno, head_agino)) {
XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp,
agi, sizeof(*agi));
return -EFSCORRUPTED;
}
- if (be32_to_cpu(agi->agi_unlinked[bucket_index]) == agino) {
- /*
- * We're at the head of the list. Get the inode's on-disk
- * buffer to see if there is anyone after us on the list.
- * Only modify our next pointer if it is not already NULLAGINO.
- * This saves us the overhead of dealing with the buffer when
- * there is no need to change it.
- */
- error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
- 0, 0);
- if (error) {
- xfs_warn(mp, "%s: xfs_imap_to_bp returned error %d.",
- __func__, error);
- return error;
- }
- next_agino = be32_to_cpu(dip->di_next_unlinked);
- ASSERT(next_agino != 0);
- if (next_agino != NULLAGINO) {
- dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
- offset = ip->i_imap.im_boffset +
- offsetof(xfs_dinode_t, di_next_unlinked);
+ /*
+ * 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_update_inode(tp, ip, agno, NULLAGINO, &next_agino);
+ if (error)
+ return error;
- /* need to recalc the inode CRC if appropriate */
- xfs_dinode_calc_crc(mp, dip);
-
- xfs_trans_inode_buf(tp, ibp);
- xfs_trans_log_buf(tp, ibp, offset,
- (offset + sizeof(xfs_agino_t) - 1));
- xfs_inobp_check(mp, ibp);
- } else {
- xfs_trans_brelse(tp, ibp);
- }
- /*
- * Point the bucket head pointer at the next inode.
- */
- ASSERT(next_agino != 0);
- ASSERT(next_agino != agino);
- agi->agi_unlinked[bucket_index] = cpu_to_be32(next_agino);
- offset = offsetof(xfs_agi_t, agi_unlinked) +
- (sizeof(xfs_agino_t) * bucket_index);
- xfs_trans_log_buf(tp, agibp, offset,
- (offset + sizeof(xfs_agino_t) - 1));
- } else {
- /*
- * We need to search the list for the inode being freed.
- */
- next_agino = be32_to_cpu(agi->agi_unlinked[bucket_index]);
- last_ibp = NULL;
- while (next_agino != agino) {
- struct xfs_imap imap;
-
- if (last_ibp)
- xfs_trans_brelse(tp, last_ibp);
-
- imap.im_blkno = 0;
- next_ino = XFS_AGINO_TO_INO(mp, agno, next_agino);
-
- error = xfs_imap(mp, tp, next_ino, &imap, 0);
- if (error) {
- xfs_warn(mp,
- "%s: xfs_imap returned error %d.",
- __func__, error);
- return error;
- }
-
- error = xfs_imap_to_bp(mp, tp, &imap, &last_dip,
- &last_ibp, 0, 0);
- if (error) {
- xfs_warn(mp,
- "%s: xfs_imap_to_bp returned error %d.",
- __func__, error);
- return error;
- }
-
- last_offset = imap.im_boffset;
- next_agino = be32_to_cpu(last_dip->di_next_unlinked);
- if (!xfs_verify_agino(mp, agno, next_agino)) {
- XFS_CORRUPTION_ERROR(__func__,
- XFS_ERRLEVEL_LOW, mp,
- last_dip, sizeof(*last_dip));
- return -EFSCORRUPTED;
- }
- }
-
- /*
- * Now last_ibp points to the buffer previous to us on the
- * unlinked list. Pull us from the list.
- */
- error = xfs_imap_to_bp(mp, tp, &ip->i_imap, &dip, &ibp,
- 0, 0);
- if (error) {
- xfs_warn(mp, "%s: xfs_imap_to_bp(2) returned error %d.",
- __func__, error);
- return error;
- }
- next_agino = be32_to_cpu(dip->di_next_unlinked);
- ASSERT(next_agino != 0);
- ASSERT(next_agino != agino);
- if (next_agino != NULLAGINO) {
- dip->di_next_unlinked = cpu_to_be32(NULLAGINO);
- offset = ip->i_imap.im_boffset +
- offsetof(xfs_dinode_t, di_next_unlinked);
-
- /* need to recalc the inode CRC if appropriate */
- xfs_dinode_calc_crc(mp, dip);
-
- xfs_trans_inode_buf(tp, ibp);
- xfs_trans_log_buf(tp, ibp, offset,
- (offset + sizeof(xfs_agino_t) - 1));
- xfs_inobp_check(mp, ibp);
- } else {
- xfs_trans_brelse(tp, ibp);
- }
- /*
- * Point the previous inode on the list to the next inode.
- */
- last_dip->di_next_unlinked = cpu_to_be32(next_agino);
- ASSERT(next_agino != 0);
- offset = last_offset + offsetof(xfs_dinode_t, di_next_unlinked);
-
- /* need to recalc the inode CRC if appropriate */
- xfs_dinode_calc_crc(mp, last_dip);
-
- xfs_trans_inode_buf(tp, last_ibp);
- xfs_trans_log_buf(tp, last_ibp, offset,
- (offset + sizeof(xfs_agino_t) - 1));
- xfs_inobp_check(mp, last_ibp);
+ /*
+ * If there was a backref pointing from the next inode back to this
+ * one, remove it because we've removed this inode from the list.
+ *
+ * Later, if this inode was in the middle of the list we'll update
+ * this inode's backref to point from the next inode.
+ */
+ if (next_agino != NULLAGINO) {
+ pag = xfs_perag_get(mp, agno);
+ error = xfs_iunlink_change_backref(pag, next_agino,
+ NULLAGINO);
+ if (error)
+ goto out;
}
- return 0;
+
+ if (head_agino == agino) {
+ /* Point the head of the list to the next unlinked inode. */
+ error = xfs_iunlink_update_bucket(tp, agno, agibp, bucket_index,
+ next_agino);
+ if (error)
+ goto out;
+ } else {
+ struct xfs_imap imap;
+ xfs_agino_t prev_agino;
+
+ if (!pag)
+ pag = xfs_perag_get(mp, agno);
+
+ /* We need to search the list for the inode being freed. */
+ error = xfs_iunlink_map_prev(tp, agno, head_agino, agino,
+ &prev_agino, &imap, &last_dip, &last_ibp,
+ pag);
+ if (error)
+ goto out;
+
+ /* Point the previous inode on the list to the next inode. */
+ xfs_iunlink_update_dinode(tp, agno, prev_agino, last_ibp,
+ last_dip, &imap, next_agino);
+
+ /*
+ * Now we deal with the backref for this inode. If this inode
+ * pointed at a real inode, change the backref that pointed to
+ * us to point to our old next. If this inode was the end of
+ * the list, delete the backref that pointed to us. Note that
+ * change_backref takes care of deleting the backref if
+ * next_agino is NULLAGINO.
+ */
+ error = xfs_iunlink_change_backref(pag, agino, next_agino);
+ if (error)
+ goto out;
+ }
+
+out:
+ if (pag)
+ xfs_perag_put(pag);
+ return error;
}
/*
@@ -2184,8 +2522,6 @@
struct xfs_icluster *xic)
{
xfs_mount_t *mp = free_ip->i_mount;
- int blks_per_cluster;
- int inodes_per_cluster;
int nbufs;
int i, j;
int ioffset;
@@ -2195,15 +2531,14 @@
xfs_inode_log_item_t *iip;
struct xfs_log_item *lip;
struct xfs_perag *pag;
+ struct xfs_ino_geometry *igeo = M_IGEO(mp);
xfs_ino_t inum;
inum = xic->first_ino;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, inum));
- blks_per_cluster = xfs_icluster_size_fsb(mp);
- inodes_per_cluster = blks_per_cluster << mp->m_sb.sb_inopblog;
- nbufs = mp->m_ialloc_blks / blks_per_cluster;
+ nbufs = igeo->ialloc_blks / igeo->blocks_per_cluster;
- for (j = 0; j < nbufs; j++, inum += inodes_per_cluster) {
+ for (j = 0; j < nbufs; j++, inum += igeo->inodes_per_cluster) {
/*
* The allocation bitmap tells us which inodes of the chunk were
* physically allocated. Skip the cluster if an inode falls into
@@ -2211,7 +2546,7 @@
*/
ioffset = inum - xic->first_ino;
if ((xic->alloc & XFS_INOBT_MASK(ioffset)) == 0) {
- ASSERT(ioffset % inodes_per_cluster == 0);
+ ASSERT(ioffset % igeo->inodes_per_cluster == 0);
continue;
}
@@ -2227,7 +2562,7 @@
* to mark all the active inodes on the buffer stale.
*/
bp = xfs_trans_get_buf(tp, mp->m_ddev_targp, blkno,
- mp->m_bsize * blks_per_cluster,
+ mp->m_bsize * igeo->blocks_per_cluster,
XBF_UNMAPPED);
if (!bp)
@@ -2242,7 +2577,7 @@
* want it to fail. We can acheive this by adding a write
* verifier to the buffer.
*/
- bp->b_ops = &xfs_inode_buf_ops;
+ bp->b_ops = &xfs_inode_buf_ops;
/*
* Walk the inodes already attached to the buffer and mark them
@@ -2274,7 +2609,7 @@
* transaction stale above, which means there is no point in
* even trying to lock them.
*/
- for (i = 0; i < inodes_per_cluster; i++) {
+ for (i = 0; i < igeo->inodes_per_cluster; i++) {
retry:
rcu_read_lock();
ip = radix_tree_lookup(&pag->pag_ici_root,
@@ -2752,9 +3087,7 @@
error = xfs_droplink(tp, dp2);
if (error)
goto out_trans_abort;
- error = xfs_bumplink(tp, dp1);
- if (error)
- goto out_trans_abort;
+ xfs_bumplink(tp, dp1);
}
/*
@@ -2778,9 +3111,7 @@
error = xfs_droplink(tp, dp1);
if (error)
goto out_trans_abort;
- error = xfs_bumplink(tp, dp2);
- if (error)
- goto out_trans_abort;
+ xfs_bumplink(tp, dp2);
}
/*
@@ -2837,11 +3168,9 @@
/*
* Prepare the tmpfile inode as if it were created through the VFS.
- * Otherwise, the link increment paths will complain about nlink 0->1.
- * Drop the link count as done by d_tmpfile(), complete the inode setup
- * and flag it as linkable.
+ * Complete the inode setup and flag it as linkable. nlink is already
+ * zero, so we can skip the drop_nlink.
*/
- drop_nlink(VFS_I(tmpfile));
xfs_setup_iops(tmpfile);
xfs_finish_inode_setup(tmpfile);
VFS_I(tmpfile)->i_state |= I_LINKABLE;
@@ -2953,7 +3282,8 @@
spaceres);
/*
- * Set up the target.
+ * Check for expected errors before we dirty the transaction
+ * so we can return an error without a transaction abort.
*/
if (target_ip == NULL) {
/*
@@ -2965,6 +3295,46 @@
if (error)
goto out_trans_cancel;
}
+ } 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))) {
+ error = -EEXIST;
+ goto out_trans_cancel;
+ }
+ }
+
+ /*
+ * 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 (wip) {
+ ASSERT(VFS_I(wip)->i_nlink == 0);
+ error = xfs_iunlink_remove(tp, wip);
+ if (error)
+ goto out_trans_cancel;
+
+ xfs_bumplink(tp, wip);
+ xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE);
+ VFS_I(wip)->i_state &= ~I_LINKABLE;
+ }
+
+ /*
+ * Set up the target.
+ */
+ if (target_ip == NULL) {
/*
* If target does not exist and the rename crosses
* directories, adjust the target directory link count
@@ -2979,28 +3349,10 @@
XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
if (new_parent && src_is_directory) {
- error = xfs_bumplink(tp, target_dp);
- if (error)
- goto out_trans_cancel;
+ xfs_bumplink(tp, target_dp);
}
} else { /* target_ip != NULL */
/*
- * If target exists and it's a directory, check that both
- * target and source are directories and that target can be
- * destroyed, or that neither is a directory.
- */
- if (S_ISDIR(VFS_I(target_ip)->i_mode)) {
- /*
- * Make sure target dir is empty.
- */
- if (!(xfs_dir_isempty(target_ip)) ||
- (VFS_I(target_ip)->i_nlink > 2)) {
- error = -EEXIST;
- goto out_trans_cancel;
- }
- }
-
- /*
* 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
@@ -3090,32 +3442,6 @@
if (error)
goto out_trans_cancel;
- /*
- * For whiteouts, we need to bump the link count on the whiteout inode.
- * This means that failures all the way up to this point leave the inode
- * on the unlinked list and so cleanup is a simple matter of dropping
- * the remaining reference to it. If we fail here after bumping the link
- * count, we're shutting down the filesystem so we'll never see the
- * intermediate state on disk.
- */
- if (wip) {
- ASSERT(VFS_I(wip)->i_nlink == 0);
- error = xfs_bumplink(tp, wip);
- if (error)
- goto out_trans_cancel;
- error = xfs_iunlink_remove(tp, wip);
- if (error)
- goto out_trans_cancel;
- xfs_trans_log_inode(tp, wip, XFS_ILOG_CORE);
-
- /*
- * Now we have a real link, clear the "I'm a tmpfile" state
- * flag from the inode so it doesn't accidentally get misused in
- * future.
- */
- VFS_I(wip)->i_state &= ~I_LINKABLE;
- }
-
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)
@@ -3142,28 +3468,27 @@
struct xfs_mount *mp = ip->i_mount;
struct xfs_perag *pag;
unsigned long first_index, mask;
- unsigned long inodes_per_cluster;
int cilist_size;
struct xfs_inode **cilist;
struct xfs_inode *cip;
+ struct xfs_ino_geometry *igeo = M_IGEO(mp);
int nr_found;
int clcount = 0;
int i;
pag = xfs_perag_get(mp, XFS_INO_TO_AGNO(mp, ip->i_ino));
- inodes_per_cluster = mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog;
- cilist_size = inodes_per_cluster * sizeof(xfs_inode_t *);
+ cilist_size = igeo->inodes_per_cluster * sizeof(struct xfs_inode *);
cilist = kmem_alloc(cilist_size, KM_MAYFAIL|KM_NOFS);
if (!cilist)
goto out_put;
- mask = ~(((mp->m_inode_cluster_size >> mp->m_sb.sb_inodelog)) - 1);
+ mask = ~(igeo->inodes_per_cluster - 1);
first_index = XFS_INO_TO_AGINO(mp, ip->i_ino) & mask;
rcu_read_lock();
/* really need a gang lookup range call here */
nr_found = radix_tree_gang_lookup(&pag->pag_ici_root, (void**)cilist,
- first_index, inodes_per_cluster);
+ first_index, igeo->inodes_per_cluster);
if (nr_found == 0)
goto out_free;
@@ -3271,7 +3596,6 @@
* inode buffer and shut down the filesystem.
*/
rcu_read_unlock();
- xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
/*
* We'll always have an inode attached to the buffer for completion
@@ -3281,11 +3605,14 @@
* xfs_buf_submit().
*/
ASSERT(bp->b_iodone);
+ bp->b_flags |= XBF_ASYNC;
bp->b_flags &= ~XBF_DONE;
xfs_buf_stale(bp);
xfs_buf_ioerror(bp, -EIO);
xfs_buf_ioend(bp);
+ xfs_force_shutdown(mp, SHUTDOWN_CORRUPT_INCORE);
+
/* abort the corrupt inode, as it was not attached to the buffer */
xfs_iflush_abort(cip, false);
kmem_free(cilist);