summaryrefslogtreecommitdiff
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/crypto/keyinfo.c5
-rw-r--r--fs/fscache/object-list.c7
-rw-r--r--fs/xfs/libxfs/xfs_ag_resv.c12
-rw-r--r--fs/xfs/libxfs/xfs_alloc.c8
-rw-r--r--fs/xfs/libxfs/xfs_bmap.c11
-rw-r--r--fs/xfs/libxfs/xfs_bmap.h1
-rw-r--r--fs/xfs/libxfs/xfs_log_format.h27
-rw-r--r--fs/xfs/xfs_acl.c22
-rw-r--r--fs/xfs/xfs_aops.c72
-rw-r--r--fs/xfs/xfs_attr_inactive.c2
-rw-r--r--fs/xfs/xfs_bmap_util.c40
-rw-r--r--fs/xfs/xfs_bmap_util.h13
-rw-r--r--fs/xfs/xfs_error.c2
-rw-r--r--fs/xfs/xfs_file.c2
-rw-r--r--fs/xfs/xfs_inode.c8
-rw-r--r--fs/xfs/xfs_inode_item.c86
-rw-r--r--fs/xfs/xfs_iomap.c7
-rw-r--r--fs/xfs/xfs_iomap.h2
-rw-r--r--fs/xfs/xfs_ondisk.h2
-rw-r--r--fs/xfs/xfs_pnfs.c2
-rw-r--r--fs/xfs/xfs_reflink.c9
21 files changed, 236 insertions, 104 deletions
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index bb4606368eb1..a755fa1a0017 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -108,6 +108,11 @@ static int validate_user_key(struct fscrypt_info *crypt_info,
goto out;
}
ukp = user_key_payload(keyring_key);
+ if (!ukp) {
+ /* key was revoked before we acquired its semaphore */
+ res = -EKEYREVOKED;
+ goto out;
+ }
if (ukp->datalen != sizeof(struct fscrypt_key)) {
res = -EINVAL;
goto out;
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index 5d5ddaa84b21..37e0c31d284f 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -330,6 +330,13 @@ static void fscache_objlist_config(struct fscache_objlist_data *data)
rcu_read_lock();
confkey = user_key_payload(key);
+ if (!confkey) {
+ /* key was revoked */
+ rcu_read_unlock();
+ key_put(key);
+ goto no_config;
+ }
+
buf = confkey->data;
for (len = confkey->datalen - 1; len >= 0; len--) {
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 33db69be4832..eed8f5867c46 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -157,7 +157,8 @@ __xfs_ag_resv_free(
trace_xfs_ag_resv_free(pag, type, 0);
resv = xfs_perag_resv(pag, type);
- pag->pag_mount->m_ag_max_usable += resv->ar_asked;
+ if (pag->pag_agno == 0)
+ pag->pag_mount->m_ag_max_usable += resv->ar_asked;
/*
* AGFL blocks are always considered "free", so whatever
* was reserved at mount time must be given back at umount.
@@ -217,7 +218,14 @@ __xfs_ag_resv_init(
return error;
}
- mp->m_ag_max_usable -= ask;
+ /*
+ * Reduce the maximum per-AG allocation length by however much we're
+ * trying to reserve for an AG. Since this is a filesystem-wide
+ * counter, we only make the adjustment for AG 0. This assumes that
+ * there aren't any AGs hungrier for per-AG reservation than AG 0.
+ */
+ if (pag->pag_agno == 0)
+ mp->m_ag_max_usable -= ask;
resv = xfs_perag_resv(pag, type);
resv->ar_asked = ask;
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 9f06a211e157..c3702cda010a 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -1579,6 +1579,10 @@ xfs_alloc_ag_vextent_small(
bp = xfs_btree_get_bufs(args->mp, args->tp,
args->agno, fbno, 0);
+ if (!bp) {
+ error = -EFSCORRUPTED;
+ goto error0;
+ }
xfs_trans_binval(args->tp, bp);
}
args->len = 1;
@@ -2136,6 +2140,10 @@ xfs_alloc_fix_freelist(
if (error)
goto out_agbp_relse;
bp = xfs_btree_get_bufs(mp, tp, args->agno, bno, 0);
+ if (!bp) {
+ error = -EFSCORRUPTED;
+ goto out_agbp_relse;
+ }
xfs_trans_binval(tp, bp);
}
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index d2f4ab175096..7eb99701054f 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -4057,6 +4057,17 @@ xfs_trim_extent(
}
}
+/* trim extent to within eof */
+void
+xfs_trim_extent_eof(
+ struct xfs_bmbt_irec *irec,
+ struct xfs_inode *ip)
+
+{
+ xfs_trim_extent(irec, 0, XFS_B_TO_FSB(ip->i_mount,
+ i_size_read(VFS_I(ip))));
+}
+
/*
* Trim the returned map to the required bounds
*/
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index db53ac7ff6df..f1446d127120 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -196,6 +196,7 @@ void xfs_bmap_trace_exlist(struct xfs_inode *ip, xfs_extnum_t cnt,
void xfs_trim_extent(struct xfs_bmbt_irec *irec, xfs_fileoff_t bno,
xfs_filblks_t len);
+void xfs_trim_extent_eof(struct xfs_bmbt_irec *, struct xfs_inode *);
int xfs_bmap_add_attrfork(struct xfs_inode *ip, int size, int rsvd);
void xfs_bmap_local_to_extents_empty(struct xfs_inode *ip, int whichfork);
void xfs_bmap_add_free(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 083cdd6d6c28..ce6958b1385c 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -270,6 +270,7 @@ typedef struct xfs_inode_log_format {
__uint32_t ilf_fields; /* flags for fields logged */
__uint16_t ilf_asize; /* size of attr d/ext/root */
__uint16_t ilf_dsize; /* size of data/ext/root */
+ __uint32_t ilf_pad; /* pad for 64 bit boundary */
__uint64_t ilf_ino; /* inode number */
union {
__uint32_t ilfu_rdev; /* rdev value for dev inode*/
@@ -280,29 +281,17 @@ typedef struct xfs_inode_log_format {
__int32_t ilf_boffset; /* off of inode in buffer */
} xfs_inode_log_format_t;
-typedef struct xfs_inode_log_format_32 {
- __uint16_t ilf_type; /* inode log item type */
- __uint16_t ilf_size; /* size of this item */
- __uint32_t ilf_fields; /* flags for fields logged */
- __uint16_t ilf_asize; /* size of attr d/ext/root */
- __uint16_t ilf_dsize; /* size of data/ext/root */
- __uint64_t ilf_ino; /* inode number */
- union {
- __uint32_t ilfu_rdev; /* rdev value for dev inode*/
- uuid_t ilfu_uuid; /* mount point value */
- } ilf_u;
- __int64_t ilf_blkno; /* blkno of inode buffer */
- __int32_t ilf_len; /* len of inode buffer */
- __int32_t ilf_boffset; /* off of inode in buffer */
-} __attribute__((packed)) xfs_inode_log_format_32_t;
-
-typedef struct xfs_inode_log_format_64 {
+/*
+ * Old 32 bit systems will log in this format without the 64 bit
+ * alignment padding. Recovery will detect this and convert it to the
+ * correct format.
+ */
+struct xfs_inode_log_format_32 {
__uint16_t ilf_type; /* inode log item type */
__uint16_t ilf_size; /* size of this item */
__uint32_t ilf_fields; /* flags for fields logged */
__uint16_t ilf_asize; /* size of attr d/ext/root */
__uint16_t ilf_dsize; /* size of data/ext/root */
- __uint32_t ilf_pad; /* pad for 64 bit boundary */
__uint64_t ilf_ino; /* inode number */
union {
__uint32_t ilfu_rdev; /* rdev value for dev inode*/
@@ -311,7 +300,7 @@ typedef struct xfs_inode_log_format_64 {
__int64_t ilf_blkno; /* blkno of inode buffer */
__int32_t ilf_len; /* len of inode buffer */
__int32_t ilf_boffset; /* off of inode in buffer */
-} xfs_inode_log_format_64_t;
+} __attribute__((packed));
/*
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index 7034e17535de..3354140de07e 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -247,6 +247,8 @@ xfs_set_mode(struct inode *inode, umode_t mode)
int
xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
{
+ umode_t mode;
+ bool set_mode = false;
int error = 0;
if (!acl)
@@ -257,16 +259,24 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
return error;
if (type == ACL_TYPE_ACCESS) {
- umode_t mode;
-
error = posix_acl_update_mode(inode, &mode, &acl);
if (error)
return error;
- error = xfs_set_mode(inode, mode);
- if (error)
- return error;
+ set_mode = true;
}
set_acl:
- return __xfs_set_acl(inode, acl, type);
+ error = __xfs_set_acl(inode, acl, type);
+ if (error)
+ return error;
+
+ /*
+ * We set the mode after successfully updating the ACL xattr because the
+ * xattr update can fail at ENOSPC and we don't want to change the mode
+ * if the ACL update hasn't been applied.
+ */
+ if (set_mode)
+ error = xfs_set_mode(inode, mode);
+
+ return error;
}
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index d23889e0bedc..d31cd1ebd8e9 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -335,7 +335,8 @@ xfs_end_io(
error = xfs_reflink_end_cow(ip, offset, size);
break;
case XFS_IO_UNWRITTEN:
- error = xfs_iomap_write_unwritten(ip, offset, size);
+ /* writeback should never update isize */
+ error = xfs_iomap_write_unwritten(ip, offset, size, false);
break;
default:
ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans);
@@ -437,6 +438,19 @@ xfs_imap_valid(
{
offset >>= inode->i_blkbits;
+ /*
+ * We have to make sure the cached mapping is within EOF to protect
+ * against eofblocks trimming on file release leaving us with a stale
+ * mapping. Otherwise, a page for a subsequent file extending buffered
+ * write could get picked up by this writeback cycle and written to the
+ * wrong blocks.
+ *
+ * Note that what we really want here is a generic mapping invalidation
+ * mechanism to protect us from arbitrary extent modifying contexts, not
+ * just eofblocks.
+ */
+ xfs_trim_extent_eof(imap, XFS_I(inode));
+
return offset >= imap->br_startoff &&
offset < imap->br_startoff + imap->br_blockcount;
}
@@ -725,6 +739,14 @@ xfs_vm_invalidatepage(
{
trace_xfs_invalidatepage(page->mapping->host, page, offset,
length);
+
+ /*
+ * If we are invalidating the entire page, clear the dirty state from it
+ * so that we can check for attempts to release dirty cached pages in
+ * xfs_vm_releasepage().
+ */
+ if (offset == 0 && length >= PAGE_SIZE)
+ cancel_dirty_page(page);
block_invalidatepage(page, offset, length);
}
@@ -1180,25 +1202,27 @@ xfs_vm_releasepage(
* mm accommodates an old ext3 case where clean pages might not have had
* the dirty bit cleared. Thus, it can send actual dirty pages to
* ->releasepage() via shrink_active_list(). Conversely,
- * block_invalidatepage() can send pages that are still marked dirty
- * but otherwise have invalidated buffers.
+ * block_invalidatepage() can send pages that are still marked dirty but
+ * otherwise have invalidated buffers.
*
* We want to release the latter to avoid unnecessary buildup of the
- * LRU, skip the former and warn if we've left any lingering
- * delalloc/unwritten buffers on clean pages. Skip pages with delalloc
- * or unwritten buffers and warn if the page is not dirty. Otherwise
- * try to release the buffers.
+ * LRU, so xfs_vm_invalidatepage() clears the page dirty flag on pages
+ * that are entirely invalidated and need to be released. Hence the
+ * only time we should get dirty pages here is through
+ * shrink_active_list() and so we can simply skip those now.
+ *
+ * warn if we've left any lingering delalloc/unwritten buffers on clean
+ * or invalidated pages we are about to release.
*/
+ if (PageDirty(page))
+ return 0;
+
xfs_count_page_state(page, &delalloc, &unwritten);
- if (delalloc) {
- WARN_ON_ONCE(!PageDirty(page));
+ if (WARN_ON_ONCE(delalloc))
return 0;
- }
- if (unwritten) {
- WARN_ON_ONCE(!PageDirty(page));
+ if (WARN_ON_ONCE(unwritten))
return 0;
- }
return try_to_free_buffers(page);
}
@@ -1532,6 +1556,21 @@ xfs_end_io_direct_write(
return 0;
}
+ if (flags & XFS_DIO_FLAG_COW)
+ error = xfs_reflink_end_cow(ip, offset, size);
+
+ /*
+ * Unwritten conversion updates the in-core isize after extent
+ * conversion but before updating the on-disk size. Updating isize any
+ * earlier allows a racing dio read to find unwritten extents before
+ * they are converted.
+ */
+ if (flags & XFS_DIO_FLAG_UNWRITTEN) {
+ trace_xfs_end_io_direct_write_unwritten(ip, offset, size);
+
+ return xfs_iomap_write_unwritten(ip, offset, size, true);
+ }
+
/*
* We need to update the in-core inode size here so that we don't end up
* with the on-disk inode size being outside the in-core inode size. We
@@ -1548,13 +1587,6 @@ xfs_end_io_direct_write(
i_size_write(inode, offset + size);
spin_unlock(&ip->i_flags_lock);
- if (flags & XFS_DIO_FLAG_COW)
- error = xfs_reflink_end_cow(ip, offset, size);
- if (flags & XFS_DIO_FLAG_UNWRITTEN) {
- trace_xfs_end_io_direct_write_unwritten(ip, offset, size);
-
- error = xfs_iomap_write_unwritten(ip, offset, size);
- }
if (flags & XFS_DIO_FLAG_APPEND) {
trace_xfs_end_io_direct_write_append(ip, offset, size);
diff --git a/fs/xfs/xfs_attr_inactive.c b/fs/xfs/xfs_attr_inactive.c
index be0b79d8900f..c6643004e583 100644
--- a/fs/xfs/xfs_attr_inactive.c
+++ b/fs/xfs/xfs_attr_inactive.c
@@ -302,6 +302,8 @@ xfs_attr3_node_inactive(
&bp, XFS_ATTR_FORK);
if (error)
return error;
+ node = bp->b_addr;
+ btree = dp->d_ops->node_tree_p(node);
child_fsb = be32_to_cpu(btree[i + 1].before);
xfs_trans_brelse(*trans, bp);
}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 5ffefac081f7..cb62871fb91d 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -84,6 +84,7 @@ xfs_zero_extent(
GFP_NOFS, true);
}
+#ifdef CONFIG_XFS_RT
int
xfs_bmap_rtalloc(
struct xfs_bmalloca *ap) /* bmap alloc argument struct */
@@ -195,6 +196,7 @@ xfs_bmap_rtalloc(
}
return 0;
}
+#endif /* CONFIG_XFS_RT */
/*
* Check if the endoff is outside the last extent. If so the caller will grow
@@ -1445,7 +1447,19 @@ xfs_shift_file_space(
return error;
/*
- * The extent shiting code works on extent granularity. So, if
+ * Clean out anything hanging around in the cow fork now that
+ * we've flushed all the dirty data out to disk to avoid having
+ * CoW extents at the wrong offsets.
+ */
+ if (xfs_is_reflink_inode(ip)) {
+ error = xfs_reflink_cancel_cow_range(ip, offset, NULLFILEOFF,
+ true);
+ if (error)
+ return error;
+ }
+
+ /*
+ * The extent shifting code works on extent granularity. So, if
* stop_fsb is not the starting block of extent, we need to split
* the extent at stop_fsb.
*/
@@ -2094,11 +2108,31 @@ xfs_swap_extents(
ip->i_d.di_flags2 |= tip->i_d.di_flags2 & XFS_DIFLAG2_REFLINK;
tip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
tip->i_d.di_flags2 |= f & XFS_DIFLAG2_REFLINK;
+ }
+
+ /* Swap the cow forks. */
+ if (xfs_sb_version_hasreflink(&mp->m_sb)) {
+ xfs_extnum_t extnum;
+
+ ASSERT(ip->i_cformat == XFS_DINODE_FMT_EXTENTS);
+ ASSERT(tip->i_cformat == XFS_DINODE_FMT_EXTENTS);
+
+ extnum = ip->i_cnextents;
+ ip->i_cnextents = tip->i_cnextents;
+ tip->i_cnextents = extnum;
+
cowfp = ip->i_cowfp;
ip->i_cowfp = tip->i_cowfp;
tip->i_cowfp = cowfp;
- xfs_inode_set_cowblocks_tag(ip);
- xfs_inode_set_cowblocks_tag(tip);
+
+ if (ip->i_cowfp && ip->i_cnextents)
+ xfs_inode_set_cowblocks_tag(ip);
+ else
+ xfs_inode_clear_cowblocks_tag(ip);
+ if (tip->i_cowfp && tip->i_cnextents)
+ xfs_inode_set_cowblocks_tag(tip);
+ else
+ xfs_inode_clear_cowblocks_tag(tip);
}
xfs_trans_log_inode(tp, ip, src_log_flags);
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index f1005393785c..ce330f06563e 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -28,7 +28,20 @@ struct xfs_mount;
struct xfs_trans;
struct xfs_bmalloca;
+#ifdef CONFIG_XFS_RT
int xfs_bmap_rtalloc(struct xfs_bmalloca *ap);
+#else /* !CONFIG_XFS_RT */
+/*
+ * Attempts to allocate RT extents when RT is disable indicates corruption and
+ * should trigger a shutdown.
+ */
+static inline int
+xfs_bmap_rtalloc(struct xfs_bmalloca *ap)
+{
+ return -EFSCORRUPTED;
+}
+#endif /* CONFIG_XFS_RT */
+
int xfs_bmap_eof(struct xfs_inode *ip, xfs_fileoff_t endoff,
int whichfork, int *eof);
int xfs_bmap_punch_delalloc_range(struct xfs_inode *ip,
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index ed7ee4e8af73..bcf72970ca6b 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -167,7 +167,7 @@ xfs_verifier_error(
{
struct xfs_mount *mp = bp->b_target->bt_mount;
- xfs_alert(mp, "Metadata %s detected at %pF, %s block 0x%llx",
+ xfs_alert(mp, "Metadata %s detected at %pS, %s block 0x%llx",
bp->b_error == -EFSBADCRC ? "CRC error" : "corruption",
__return_address, bp->b_ops->name, bp->b_bn);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 586b398f268d..362c6b4c1186 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -92,7 +92,7 @@ xfs_zero_range(
xfs_off_t count,
bool *did_zero)
{
- return iomap_zero_range(VFS_I(ip), pos, count, NULL, &xfs_iomap_ops);
+ return iomap_zero_range(VFS_I(ip), pos, count, did_zero, &xfs_iomap_ops);
}
int
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 9e795ab08a53..fe9a9a183b2d 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1632,10 +1632,12 @@ xfs_itruncate_extents(
goto out;
/*
- * Clear the reflink flag if we truncated everything.
+ * Clear the reflink flag if there are no data fork blocks and
+ * there are no extents staged in the cow fork.
*/
- if (ip->i_d.di_nblocks == 0 && xfs_is_reflink_inode(ip)) {
- ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
+ if (xfs_is_reflink_inode(ip) && ip->i_cnextents == 0) {
+ if (ip->i_d.di_nblocks == 0)
+ ip->i_d.di_flags2 &= ~XFS_DIFLAG2_REFLINK;
xfs_inode_clear_cowblocks_tag(ip);
}
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index 94915747042c..d0a3c4bd2c38 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -364,6 +364,9 @@ xfs_inode_to_log_dinode(
to->di_dmstate = from->di_dmstate;
to->di_flags = from->di_flags;
+ /* log a dummy value to ensure log structure is fully initialised */
+ to->di_next_unlinked = NULLAGINO;
+
if (from->di_version == 3) {
to->di_changecount = inode->i_version;
to->di_crtime.t_sec = from->di_crtime.t_sec;
@@ -404,6 +407,11 @@ xfs_inode_item_format_core(
* the second with the on-disk inode structure, and a possible third and/or
* fourth with the inode data/extents/b-tree root and inode attributes
* data/extents/b-tree root.
+ *
+ * Note: Always use the 64 bit inode log format structure so we don't
+ * leave an uninitialised hole in the format item on 64 bit systems. Log
+ * recovery on 32 bit systems handles this just fine, so there's no reason
+ * for not using an initialising the properly padded structure all the time.
*/
STATIC void
xfs_inode_item_format(
@@ -412,8 +420,8 @@ xfs_inode_item_format(
{
struct xfs_inode_log_item *iip = INODE_ITEM(lip);
struct xfs_inode *ip = iip->ili_inode;
- struct xfs_inode_log_format *ilf;
struct xfs_log_iovec *vecp = NULL;
+ struct xfs_inode_log_format *ilf;
ASSERT(ip->i_d.di_version > 1);
@@ -425,7 +433,17 @@ xfs_inode_item_format(
ilf->ilf_boffset = ip->i_imap.im_boffset;
ilf->ilf_fields = XFS_ILOG_CORE;
ilf->ilf_size = 2; /* format + core */
- xlog_finish_iovec(lv, vecp, sizeof(struct xfs_inode_log_format));
+
+ /*
+ * make sure we don't leak uninitialised data into the log in the case
+ * when we don't log every field in the inode.
+ */
+ ilf->ilf_dsize = 0;
+ ilf->ilf_asize = 0;
+ ilf->ilf_pad = 0;
+ memset(&ilf->ilf_u.ilfu_uuid, 0, sizeof(ilf->ilf_u.ilfu_uuid));
+
+ xlog_finish_iovec(lv, vecp, sizeof(*ilf));
xfs_inode_item_format_core(ip, lv, &vecp);
xfs_inode_item_format_data_fork(iip, ilf, lv, &vecp);
@@ -745,7 +763,7 @@ xfs_iflush_done(
*/
iip = INODE_ITEM(blip);
if ((iip->ili_logged && blip->li_lsn == iip->ili_flush_lsn) ||
- lip->li_flags & XFS_LI_FAILED)
+ (blip->li_flags & XFS_LI_FAILED))
need_ail++;
blip = next;
@@ -855,48 +873,30 @@ xfs_istale_done(
}
/*
- * convert an xfs_inode_log_format struct from either 32 or 64 bit versions
- * (which can have different field alignments) to the native version
+ * convert an xfs_inode_log_format struct from the old 32 bit version
+ * (which can have different field alignments) to the native 64 bit version
*/
int
xfs_inode_item_format_convert(
- xfs_log_iovec_t *buf,
- xfs_inode_log_format_t *in_f)
+ struct xfs_log_iovec *buf,
+ struct xfs_inode_log_format *in_f)
{
- if (buf->i_len == sizeof(xfs_inode_log_format_32_t)) {
- xfs_inode_log_format_32_t *in_f32 = buf->i_addr;
-
- in_f->ilf_type = in_f32->ilf_type;
- in_f->ilf_size = in_f32->ilf_size;
- in_f->ilf_fields = in_f32->ilf_fields;
- in_f->ilf_asize = in_f32->ilf_asize;
- in_f->ilf_dsize = in_f32->ilf_dsize;
- in_f->ilf_ino = in_f32->ilf_ino;
- /* copy biggest field of ilf_u */
- memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
- in_f32->ilf_u.ilfu_uuid.__u_bits,
- sizeof(uuid_t));
- in_f->ilf_blkno = in_f32->ilf_blkno;
- in_f->ilf_len = in_f32->ilf_len;
- in_f->ilf_boffset = in_f32->ilf_boffset;
- return 0;
- } else if (buf->i_len == sizeof(xfs_inode_log_format_64_t)){
- xfs_inode_log_format_64_t *in_f64 = buf->i_addr;
-
- in_f->ilf_type = in_f64->ilf_type;
- in_f->ilf_size = in_f64->ilf_size;
- in_f->ilf_fields = in_f64->ilf_fields;
- in_f->ilf_asize = in_f64->ilf_asize;
- in_f->ilf_dsize = in_f64->ilf_dsize;
- in_f->ilf_ino = in_f64->ilf_ino;
- /* copy biggest field of ilf_u */
- memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
- in_f64->ilf_u.ilfu_uuid.__u_bits,
- sizeof(uuid_t));
- in_f->ilf_blkno = in_f64->ilf_blkno;
- in_f->ilf_len = in_f64->ilf_len;
- in_f->ilf_boffset = in_f64->ilf_boffset;
- return 0;
- }
- return -EFSCORRUPTED;
+ struct xfs_inode_log_format_32 *in_f32 = buf->i_addr;
+
+ if (buf->i_len != sizeof(*in_f32))
+ return -EFSCORRUPTED;
+
+ in_f->ilf_type = in_f32->ilf_type;
+ in_f->ilf_size = in_f32->ilf_size;
+ in_f->ilf_fields = in_f32->ilf_fields;
+ in_f->ilf_asize = in_f32->ilf_asize;
+ in_f->ilf_dsize = in_f32->ilf_dsize;
+ in_f->ilf_ino = in_f32->ilf_ino;
+ /* copy biggest field of ilf_u */
+ memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
+ in_f32->ilf_u.ilfu_uuid.__u_bits, sizeof(uuid_t));
+ in_f->ilf_blkno = in_f32->ilf_blkno;
+ in_f->ilf_len = in_f32->ilf_len;
+ in_f->ilf_boffset = in_f32->ilf_boffset;
+ return 0;
}
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 65740d1cbd92..f286f63c430c 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -836,7 +836,8 @@ int
xfs_iomap_write_unwritten(
xfs_inode_t *ip,
xfs_off_t offset,
- xfs_off_t count)
+ xfs_off_t count,
+ bool update_isize)
{
xfs_mount_t *mp = ip->i_mount;
xfs_fileoff_t offset_fsb;
@@ -847,6 +848,7 @@ xfs_iomap_write_unwritten(
xfs_trans_t *tp;
xfs_bmbt_irec_t imap;
struct xfs_defer_ops dfops;
+ struct inode *inode = VFS_I(ip);
xfs_fsize_t i_size;
uint resblks;
int error;
@@ -906,7 +908,8 @@ xfs_iomap_write_unwritten(
i_size = XFS_FSB_TO_B(mp, offset_fsb + count_fsb);
if (i_size > offset + count)
i_size = offset + count;
-
+ if (update_isize && i_size > i_size_read(inode))
+ i_size_write(inode, i_size);
i_size = xfs_new_eof(ip, i_size);
if (i_size) {
ip->i_d.di_size = i_size;
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 6d45cf01fcff..d71703af5c76 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -27,7 +27,7 @@ int xfs_iomap_write_direct(struct xfs_inode *, xfs_off_t, size_t,
struct xfs_bmbt_irec *, int);
int xfs_iomap_write_allocate(struct xfs_inode *, int, xfs_off_t,
struct xfs_bmbt_irec *);
-int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t);
+int xfs_iomap_write_unwritten(struct xfs_inode *, xfs_off_t, xfs_off_t, bool);
void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
struct xfs_bmbt_irec *);
diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h
index 0c381d71b242..0492436a053f 100644
--- a/fs/xfs/xfs_ondisk.h
+++ b/fs/xfs/xfs_ondisk.h
@@ -134,7 +134,7 @@ xfs_check_ondisk_structs(void)
XFS_CHECK_STRUCT_SIZE(struct xfs_icreate_log, 28);
XFS_CHECK_STRUCT_SIZE(struct xfs_ictimestamp, 8);
XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_32, 52);
- XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format_64, 56);
+ XFS_CHECK_STRUCT_SIZE(struct xfs_inode_log_format, 56);
XFS_CHECK_STRUCT_SIZE(struct xfs_qoff_logformat, 20);
XFS_CHECK_STRUCT_SIZE(struct xfs_trans_header, 16);
}
diff --git a/fs/xfs/xfs_pnfs.c b/fs/xfs/xfs_pnfs.c
index 93a7aafa56d6..cecd37569ddb 100644
--- a/fs/xfs/xfs_pnfs.c
+++ b/fs/xfs/xfs_pnfs.c
@@ -279,7 +279,7 @@ xfs_fs_commit_blocks(
(end - 1) >> PAGE_SHIFT);
WARN_ON_ONCE(error);
- error = xfs_iomap_write_unwritten(ip, start, length);
+ error = xfs_iomap_write_unwritten(ip, start, length, false);
if (error)
goto out_drop_iolock;
}
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 0015c19c7455..17d3c964a2a2 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -767,7 +767,13 @@ xfs_reflink_end_cow(
/* If there is a hole at end_fsb - 1 go to the previous extent */
if (eof || got.br_startoff > end_fsb) {
- ASSERT(idx > 0);
+ /*
+ * In case of racing, overlapping AIO writes no COW extents
+ * might be left by the time I/O completes for the loser of
+ * the race. In that case we are done.
+ */
+ if (idx <= 0)
+ goto out_cancel;
xfs_bmbt_get_all(xfs_iext_get_ext(ifp, --idx), &got);
}
@@ -841,6 +847,7 @@ next_extent:
out_defer:
xfs_defer_cancel(&dfops);
+out_cancel:
xfs_trans_cancel(tp);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out:
View Lorry Controller Status