summaryrefslogtreecommitdiffstats
path: root/fs/xfs
diff options
context:
space:
mode:
Diffstat (limited to 'fs/xfs')
-rw-r--r--fs/xfs/xfs_aops.c51
-rw-r--r--fs/xfs/xfs_attr.c24
-rw-r--r--fs/xfs/xfs_attr_leaf.c21
-rw-r--r--fs/xfs/xfs_attr_list.c1
-rw-r--r--fs/xfs/xfs_attr_remote.c8
-rw-r--r--fs/xfs/xfs_bmap.c17
-rw-r--r--fs/xfs/xfs_bmap_util.c13
-rw-r--r--fs/xfs/xfs_buf.c16
-rw-r--r--fs/xfs/xfs_da_btree.h2
-rw-r--r--fs/xfs/xfs_file.c12
-rw-r--r--fs/xfs/xfs_inode.c5
-rw-r--r--fs/xfs/xfs_inode.h2
-rw-r--r--fs/xfs/xfs_iops.c41
-rw-r--r--fs/xfs/xfs_log.c63
-rw-r--r--fs/xfs/xfs_mount.c2
-rw-r--r--fs/xfs/xfs_sb.c4
-rw-r--r--fs/xfs/xfs_trace.h1
17 files changed, 216 insertions, 67 deletions
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 75df77d09f75..0479c32c5eb1 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -1344,6 +1344,14 @@ __xfs_get_blocks(
/*
* If this is O_DIRECT or the mpage code calling tell them how large
* the mapping is, so that we can avoid repeated get_blocks calls.
+ *
+ * If the mapping spans EOF, then we have to break the mapping up as the
+ * mapping for blocks beyond EOF must be marked new so that sub block
+ * regions can be correctly zeroed. We can't do this for mappings within
+ * EOF unless the mapping was just allocated or is unwritten, otherwise
+ * the callers would overwrite existing data with zeros. Hence we have
+ * to split the mapping into a range up to and including EOF, and a
+ * second mapping for beyond EOF.
*/
if (direct || size > (1 << inode->i_blkbits)) {
xfs_off_t mapping_size;
@@ -1354,6 +1362,12 @@ __xfs_get_blocks(
ASSERT(mapping_size > 0);
if (mapping_size > size)
mapping_size = size;
+ if (offset < i_size_read(inode) &&
+ offset + mapping_size >= i_size_read(inode)) {
+ /* limit mapping to block that spans EOF */
+ mapping_size = roundup_64(i_size_read(inode) - offset,
+ 1 << inode->i_blkbits);
+ }
if (mapping_size > LONG_MAX)
mapping_size = LONG_MAX;
@@ -1566,6 +1580,16 @@ xfs_vm_write_failed(
xfs_vm_kill_delalloc_range(inode, block_offset,
block_offset + bh->b_size);
+
+ /*
+ * This buffer does not contain data anymore. make sure anyone
+ * who finds it knows that for certain.
+ */
+ clear_buffer_delay(bh);
+ clear_buffer_uptodate(bh);
+ clear_buffer_mapped(bh);
+ clear_buffer_new(bh);
+ clear_buffer_dirty(bh);
}
}
@@ -1599,12 +1623,21 @@ xfs_vm_write_begin(
status = __block_write_begin(page, pos, len, xfs_get_blocks);
if (unlikely(status)) {
struct inode *inode = mapping->host;
+ size_t isize = i_size_read(inode);
xfs_vm_write_failed(inode, page, pos, len);
unlock_page(page);
- if (pos + len > i_size_read(inode))
- truncate_pagecache(inode, i_size_read(inode));
+ /*
+ * If the write is beyond EOF, we only want to kill blocks
+ * allocated in this write, not blocks that were previously
+ * written successfully.
+ */
+ if (pos + len > isize) {
+ ssize_t start = max_t(ssize_t, pos, isize);
+
+ truncate_pagecache_range(inode, start, pos + len);
+ }
page_cache_release(page);
page = NULL;
@@ -1615,9 +1648,12 @@ xfs_vm_write_begin(
}
/*
- * On failure, we only need to kill delalloc blocks beyond EOF because they
- * will never be written. For blocks within EOF, generic_write_end() zeros them
- * so they are safe to leave alone and be written with all the other valid data.
+ * On failure, we only need to kill delalloc blocks beyond EOF in the range of
+ * this specific write because they will never be written. Previous writes
+ * beyond EOF where block allocation succeeded do not need to be trashed, so
+ * only new blocks from this write should be trashed. For blocks within
+ * EOF, generic_write_end() zeros them so they are safe to leave alone and be
+ * written with all the other valid data.
*/
STATIC int
xfs_vm_write_end(
@@ -1640,8 +1676,11 @@ xfs_vm_write_end(
loff_t to = pos + len;
if (to > isize) {
- truncate_pagecache(inode, isize);
+ /* only kill blocks in this write beyond EOF */
+ if (pos > isize)
+ isize = pos;
xfs_vm_kill_delalloc_range(inode, isize, to);
+ truncate_pagecache_range(inode, isize, to);
}
}
return ret;
diff --git a/fs/xfs/xfs_attr.c b/fs/xfs/xfs_attr.c
index 01b6a0102fbd..abda1124a70f 100644
--- a/fs/xfs/xfs_attr.c
+++ b/fs/xfs/xfs_attr.c
@@ -213,7 +213,7 @@ xfs_attr_calc_size(
* Out of line attribute, cannot double split, but
* make room for the attribute value itself.
*/
- uint dblocks = XFS_B_TO_FSB(mp, valuelen);
+ uint dblocks = xfs_attr3_rmt_blocks(mp, valuelen);
nblks += dblocks;
nblks += XFS_NEXTENTADD_SPACE_RES(mp, dblocks, XFS_ATTR_FORK);
}
@@ -698,11 +698,22 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
trace_xfs_attr_leaf_replace(args);
+ /* save the attribute state for later removal*/
args->op_flags |= XFS_DA_OP_RENAME; /* an atomic rename */
args->blkno2 = args->blkno; /* set 2nd entry info*/
args->index2 = args->index;
args->rmtblkno2 = args->rmtblkno;
args->rmtblkcnt2 = args->rmtblkcnt;
+ args->rmtvaluelen2 = args->rmtvaluelen;
+
+ /*
+ * clear the remote attr state now that it is saved so that the
+ * values reflect the state of the attribute we are about to
+ * add, not the attribute we just found and will remove later.
+ */
+ args->rmtblkno = 0;
+ args->rmtblkcnt = 0;
+ args->rmtvaluelen = 0;
}
/*
@@ -794,6 +805,7 @@ xfs_attr_leaf_addname(xfs_da_args_t *args)
args->blkno = args->blkno2;
args->rmtblkno = args->rmtblkno2;
args->rmtblkcnt = args->rmtblkcnt2;
+ args->rmtvaluelen = args->rmtvaluelen2;
if (args->rmtblkno) {
error = xfs_attr_rmtval_remove(args);
if (error)
@@ -999,13 +1011,22 @@ restart:
trace_xfs_attr_node_replace(args);
+ /* save the attribute state for later removal*/
args->op_flags |= XFS_DA_OP_RENAME; /* atomic rename op */
args->blkno2 = args->blkno; /* set 2nd entry info*/
args->index2 = args->index;
args->rmtblkno2 = args->rmtblkno;
args->rmtblkcnt2 = args->rmtblkcnt;
+ args->rmtvaluelen2 = args->rmtvaluelen;
+
+ /*
+ * clear the remote attr state now that it is saved so that the
+ * values reflect the state of the attribute we are about to
+ * add, not the attribute we just found and will remove later.
+ */
args->rmtblkno = 0;
args->rmtblkcnt = 0;
+ args->rmtvaluelen = 0;
}
retval = xfs_attr3_leaf_add(blk->bp, state->args);
@@ -1133,6 +1154,7 @@ restart:
args->blkno = args->blkno2;
args->rmtblkno = args->rmtblkno2;
args->rmtblkcnt = args->rmtblkcnt2;
+ args->rmtvaluelen = args->rmtvaluelen2;
if (args->rmtblkno) {
error = xfs_attr_rmtval_remove(args);
if (error)
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index fe9587fab17a..511c283459b1 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -1229,6 +1229,7 @@ xfs_attr3_leaf_add_work(
name_rmt->valueblk = 0;
args->rmtblkno = 1;
args->rmtblkcnt = xfs_attr3_rmt_blocks(mp, args->valuelen);
+ args->rmtvaluelen = args->valuelen;
}
xfs_trans_log_buf(args->trans, bp,
XFS_DA_LOGRANGE(leaf, xfs_attr3_leaf_name(leaf, args->index),
@@ -2167,11 +2168,11 @@ xfs_attr3_leaf_lookup_int(
if (!xfs_attr_namesp_match(args->flags, entry->flags))
continue;
args->index = probe;
- args->valuelen = be32_to_cpu(name_rmt->valuelen);
+ args->rmtvaluelen = be32_to_cpu(name_rmt->valuelen);
args->rmtblkno = be32_to_cpu(name_rmt->valueblk);
args->rmtblkcnt = xfs_attr3_rmt_blocks(
args->dp->i_mount,
- args->valuelen);
+ args->rmtvaluelen);
return XFS_ERROR(EEXIST);
}
}
@@ -2220,19 +2221,19 @@ xfs_attr3_leaf_getvalue(
name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index);
ASSERT(name_rmt->namelen == args->namelen);
ASSERT(memcmp(args->name, name_rmt->name, args->namelen) == 0);
- valuelen = be32_to_cpu(name_rmt->valuelen);
+ args->rmtvaluelen = be32_to_cpu(name_rmt->valuelen);
args->rmtblkno = be32_to_cpu(name_rmt->valueblk);
args->rmtblkcnt = xfs_attr3_rmt_blocks(args->dp->i_mount,
- valuelen);
+ args->rmtvaluelen);
if (args->flags & ATTR_KERNOVAL) {
- args->valuelen = valuelen;
+ args->valuelen = args->rmtvaluelen;
return 0;
}
- if (args->valuelen < valuelen) {
- args->valuelen = valuelen;
+ if (args->valuelen < args->rmtvaluelen) {
+ args->valuelen = args->rmtvaluelen;
return XFS_ERROR(ERANGE);
}
- args->valuelen = valuelen;
+ args->valuelen = args->rmtvaluelen;
}
return 0;
}
@@ -2519,7 +2520,7 @@ xfs_attr3_leaf_clearflag(
ASSERT((entry->flags & XFS_ATTR_LOCAL) == 0);
name_rmt = xfs_attr3_leaf_name_remote(leaf, args->index);
name_rmt->valueblk = cpu_to_be32(args->rmtblkno);
- name_rmt->valuelen = cpu_to_be32(args->valuelen);
+ name_rmt->valuelen = cpu_to_be32(args->rmtvaluelen);
xfs_trans_log_buf(args->trans, bp,
XFS_DA_LOGRANGE(leaf, name_rmt, sizeof(*name_rmt)));
}
@@ -2677,7 +2678,7 @@ xfs_attr3_leaf_flipflags(
ASSERT((entry1->flags & XFS_ATTR_LOCAL) == 0);
name_rmt = xfs_attr3_leaf_name_remote(leaf1, args->index);
name_rmt->valueblk = cpu_to_be32(args->rmtblkno);
- name_rmt->valuelen = cpu_to_be32(args->valuelen);
+ name_rmt->valuelen = cpu_to_be32(args->rmtvaluelen);
xfs_trans_log_buf(args->trans, bp1,
XFS_DA_LOGRANGE(leaf1, name_rmt, sizeof(*name_rmt)));
}
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 01db96f60cf0..833fe5d98d80 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -447,6 +447,7 @@ xfs_attr3_leaf_list_int(
args.dp = context->dp;
args.whichfork = XFS_ATTR_FORK;
args.valuelen = valuelen;
+ args.rmtvaluelen = valuelen;
args.value = kmem_alloc(valuelen, KM_SLEEP | KM_NOFS);
args.rmtblkno = be32_to_cpu(name_rmt->valueblk);
args.rmtblkcnt = xfs_attr3_rmt_blocks(
diff --git a/fs/xfs/xfs_attr_remote.c b/fs/xfs/xfs_attr_remote.c
index 6e37823e2932..d2e6e948cec7 100644
--- a/fs/xfs/xfs_attr_remote.c
+++ b/fs/xfs/xfs_attr_remote.c
@@ -337,7 +337,7 @@ xfs_attr_rmtval_get(
struct xfs_buf *bp;
xfs_dablk_t lblkno = args->rmtblkno;
__uint8_t *dst = args->value;
- int valuelen = args->valuelen;
+ int valuelen;
int nmap;
int error;
int blkcnt = args->rmtblkcnt;
@@ -347,7 +347,9 @@ xfs_attr_rmtval_get(
trace_xfs_attr_rmtval_get(args);
ASSERT(!(args->flags & ATTR_KERNOVAL));
+ ASSERT(args->rmtvaluelen == args->valuelen);
+ valuelen = args->rmtvaluelen;
while (valuelen > 0) {
nmap = ATTR_RMTVALUE_MAPSIZE;
error = xfs_bmapi_read(args->dp, (xfs_fileoff_t)lblkno,
@@ -415,7 +417,7 @@ xfs_attr_rmtval_set(
* attributes have headers, we can't just do a straight byte to FSB
* conversion and have to take the header space into account.
*/
- blkcnt = xfs_attr3_rmt_blocks(mp, args->valuelen);
+ blkcnt = xfs_attr3_rmt_blocks(mp, args->rmtvaluelen);
error = xfs_bmap_first_unused(args->trans, args->dp, blkcnt, &lfileoff,
XFS_ATTR_FORK);
if (error)
@@ -480,7 +482,7 @@ xfs_attr_rmtval_set(
*/
lblkno = args->rmtblkno;
blkcnt = args->rmtblkcnt;
- valuelen = args->valuelen;
+ valuelen = args->rmtvaluelen;
while (valuelen > 0) {
struct xfs_buf *bp;
xfs_daddr_t dblkno;
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index 5b6092ef51ef..f0efc7e970ef 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -5413,6 +5413,7 @@ xfs_bmap_shift_extents(
int whichfork = XFS_DATA_FORK;
int logflags;
xfs_filblks_t blockcount = 0;
+ int total_extents;
if (unlikely(XFS_TEST_ERROR(
(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
@@ -5429,7 +5430,6 @@ xfs_bmap_shift_extents(
ASSERT(current_ext != NULL);
ifp = XFS_IFORK_PTR(ip, whichfork);
-
if (!(ifp->if_flags & XFS_IFEXTENTS)) {
/* Read in all the extents */
error = xfs_iread_extents(tp, ip, whichfork);
@@ -5456,7 +5456,6 @@ xfs_bmap_shift_extents(
/* We are going to change core inode */
logflags = XFS_ILOG_CORE;
-
if (ifp->if_flags & XFS_IFBROOT) {
cur = xfs_bmbt_init_cursor(mp, tp, ip, whichfork);
cur->bc_private.b.firstblock = *firstblock;
@@ -5467,8 +5466,14 @@ xfs_bmap_shift_extents(
logflags |= XFS_ILOG_DEXT;
}
- while (nexts++ < num_exts &&
- *current_ext < XFS_IFORK_NEXTENTS(ip, whichfork)) {
+ /*
+ * There may be delalloc extents in the data fork before the range we
+ * are collapsing out, so we cannot
+ * use the count of real extents here. Instead we have to calculate it
+ * from the incore fork.
+ */
+ total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
+ while (nexts++ < num_exts && *current_ext < total_extents) {
gotp = xfs_iext_get_ext(ifp, *current_ext);
xfs_bmbt_get_all(gotp, &got);
@@ -5556,10 +5561,11 @@ xfs_bmap_shift_extents(
}
(*current_ext)++;
+ total_extents = ifp->if_bytes / sizeof(xfs_bmbt_rec_t);
}
/* Check if we are done */
- if (*current_ext == XFS_IFORK_NEXTENTS(ip, whichfork))
+ if (*current_ext == total_extents)
*done = 1;
del_cursor:
@@ -5568,6 +5574,5 @@ del_cursor:
error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
xfs_trans_log_inode(tp, ip, logflags);
-
return error;
}
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index 01f6a646caa1..296160b8e78c 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -1418,6 +1418,8 @@ xfs_zero_file_space(
xfs_off_t end_boundary;
int error;
+ trace_xfs_zero_file_space(ip);
+
granularity = max_t(uint, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
/*
@@ -1432,9 +1434,18 @@ xfs_zero_file_space(
ASSERT(end_boundary <= offset + len);
if (start_boundary < end_boundary - 1) {
- /* punch out the page cache over the conversion range */
+ /*
+ * punch out delayed allocation blocks and the page cache over
+ * the conversion range
+ */
+ xfs_ilock(ip, XFS_ILOCK_EXCL);
+ error = xfs_bmap_punch_delalloc_range(ip,
+ XFS_B_TO_FSBT(mp, start_boundary),
+ XFS_B_TO_FSB(mp, end_boundary - start_boundary));
+ xfs_iunlock(ip, XFS_ILOCK_EXCL);
truncate_pagecache_range(VFS_I(ip), start_boundary,
end_boundary - 1);
+
/* convert the blocks */
error = xfs_alloc_file_space(ip, start_boundary,
end_boundary - start_boundary - 1,
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index 107f2fdfe41f..cb10a0aaab3a 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -1372,21 +1372,29 @@ xfs_buf_iorequest(
xfs_buf_wait_unpin(bp);
xfs_buf_hold(bp);
- /* Set the count to 1 initially, this will stop an I/O
+ /*
+ * Set the count to 1 initially, this will stop an I/O
* completion callout which happens before we have started
* all the I/O from calling xfs_buf_ioend too early.
*/
atomic_set(&bp->b_io_remaining, 1);
_xfs_buf_ioapply(bp);
- _xfs_buf_ioend(bp, 1);
+ /*
+ * If _xfs_buf_ioapply failed, we'll get back here with
+ * only the reference we took above. _xfs_buf_ioend will
+ * drop it to zero, so we'd better not queue it for later,
+ * or we'll free it before it's done.
+ */
+ _xfs_buf_ioend(bp, bp->b_error ? 0 : 1);
xfs_buf_rele(bp);
}
/*
* Waits for I/O to complete on the buffer supplied. It returns immediately if
- * no I/O is pending or there is already a pending error on the buffer. It
- * returns the I/O error code, if any, or 0 if there was no error.
+ * no I/O is pending or there is already a pending error on the buffer, in which
+ * case nothing will ever complete. It returns the I/O error code, if any, or
+ * 0 if there was no error.
*/
int
xfs_buf_iowait(
diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h
index 6e95ea79f5d7..201c6091d26a 100644
--- a/fs/xfs/xfs_da_btree.h
+++ b/fs/xfs/xfs_da_btree.h
@@ -60,10 +60,12 @@ typedef struct xfs_da_args {
int index; /* index of attr of interest in blk */
xfs_dablk_t rmtblkno; /* remote attr value starting blkno */
int rmtblkcnt; /* remote attr value block count */
+ int rmtvaluelen; /* remote attr value length in bytes */
xfs_dablk_t blkno2; /* blkno of 2nd attr leaf of interest */
int index2; /* index of 2nd attr in blk */
xfs_dablk_t rmtblkno2; /* remote attr value starting blkno */
int rmtblkcnt2; /* remote attr value block count */
+ int rmtvaluelen2; /* remote attr value length in bytes */
int op_flags; /* operation flags */
enum xfs_dacmp cmpresult; /* name compare result for lookups */
} xfs_da_args_t;
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 79e96ce98733..951a2321ee01 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -679,7 +679,7 @@ xfs_file_dio_aio_write(
goto out;
if (mapping->nrpages) {
- ret = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+ ret = filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
pos, -1);
if (ret)
goto out;
@@ -841,7 +841,15 @@ xfs_file_fallocate(
goto out_unlock;
}
- ASSERT(offset + len < i_size_read(inode));
+ /*
+ * There is no need to overlap collapse range with EOF,
+ * in which case it is effectively a truncate operation
+ */
+ if (offset + len >= i_size_read(inode)) {
+ error = -EINVAL;
+ goto out_unlock;
+ }
+
new_size = i_size_read(inode) - len;
error = xfs_collapse_file_space(ip, offset, len);
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index 5e7a38fa6ee6..768087bedbac 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -1334,7 +1334,8 @@ int
xfs_create_tmpfile(
struct xfs_inode *dp,
struct dentry *dentry,
- umode_t mode)
+ umode_t mode,
+ struct xfs_inode **ipp)
{
struct xfs_mount *mp = dp->i_mount;
struct xfs_inode *ip = NULL;
@@ -1402,7 +1403,6 @@ xfs_create_tmpfile(
xfs_qm_vop_create_dqattach(tp, ip, udqp, gdqp, pdqp);
ip->i_d.di_nlink--;
- d_tmpfile(dentry, VFS_I(ip));
error = xfs_iunlink(tp, ip);
if (error)
goto out_trans_abort;
@@ -1415,6 +1415,7 @@ xfs_create_tmpfile(
xfs_qm_dqrele(gdqp);
xfs_qm_dqrele(pdqp);
+ *ipp = ip;
return 0;
out_trans_abort:
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 396cc1fafd0d..f2fcde52b66d 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -334,7 +334,7 @@ int xfs_lookup(struct xfs_inode *dp, struct xfs_name *name,
int xfs_create(struct xfs_inode *dp, struct xfs_name *name,
umode_t mode, xfs_dev_t rdev, struct xfs_inode **ipp);
int xfs_create_tmpfile(struct xfs_inode *dp, struct dentry *dentry,
- umode_t mode);
+ umode_t mode, struct xfs_inode **ipp);
int xfs_remove(struct xfs_inode *dp, struct xfs_name *name,
struct xfs_inode *ip);
int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip,
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 89b07e43ca28..301ecbfcc0be 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -124,15 +124,15 @@ xfs_cleanup_inode(
xfs_dentry_to_name(&teardown, dentry, 0);
xfs_remove(XFS_I(dir), &teardown, XFS_I(inode));
- iput(inode);
}
STATIC int
-xfs_vn_mknod(
+xfs_generic_create(
struct inode *dir,
struct dentry *dentry,
umode_t mode,
- dev_t rdev)
+ dev_t rdev,
+ bool tmpfile) /* unnamed file */
{
struct inode *inode;
struct xfs_inode *ip = NULL;
@@ -156,8 +156,12 @@ xfs_vn_mknod(
if (error)
return error;
- xfs_dentry_to_name(&name, dentry, mode);
- error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
+ if (!tmpfile) {
+ xfs_dentry_to_name(&name, dentry, mode);
+ error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip);
+ } else {
+ error = xfs_create_tmpfile(XFS_I(dir), dentry, mode, &ip);
+ }
if (unlikely(error))
goto out_free_acl;
@@ -180,7 +184,11 @@ xfs_vn_mknod(
}
#endif
- d_instantiate(dentry, inode);
+ if (tmpfile)
+ d_tmpfile(dentry, inode);
+ else
+ d_instantiate(dentry, inode);
+
out_free_acl:
if (default_acl)
posix_acl_release(default_acl);
@@ -189,11 +197,23 @@ xfs_vn_mknod(
return -error;
out_cleanup_inode:
- xfs_cleanup_inode(dir, inode, dentry);
+ if (!tmpfile)
+ xfs_cleanup_inode(dir, inode, dentry);
+ iput(inode);
goto out_free_acl;
}
STATIC int
+xfs_vn_mknod(
+ struct inode *dir,
+ struct dentry *dentry,
+ umode_t mode,
+ dev_t rdev)
+{
+ return xfs_generic_create(dir, dentry, mode, rdev, false);
+}
+
+STATIC int
xfs_vn_create(
struct inode *dir,
struct dentry *dentry,
@@ -353,6 +373,7 @@ xfs_vn_symlink(
out_cleanup_inode:
xfs_cleanup_inode(dir, inode, dentry);
+ iput(inode);
out:
return -error;
}
@@ -1053,11 +1074,7 @@ xfs_vn_tmpfile(
struct dentry *dentry,
umode_t mode)
{
- int error;
-
- error = xfs_create_tmpfile(XFS_I(dir), dentry, mode);
-
- return -error;
+ return xfs_generic_create(dir, dentry, mode, 0, true);
}
static const struct inode_operations xfs_inode_operations = {
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index 8497a00e399d..a5f8bd9899d3 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -616,11 +616,13 @@ xfs_log_mount(
int error = 0;
int min_logfsbs;
- if (!(mp->m_flags & XFS_MOUNT_NORECOVERY))
- xfs_notice(mp, "Mounting Filesystem");
- else {
+ if (!(mp->m_flags & XFS_MOUNT_NORECOVERY)) {
+ xfs_notice(mp, "Mounting V%d Filesystem",
+ XFS_SB_VERSION_NUM(&mp->m_sb));
+ } else {
xfs_notice(mp,
-"Mounting filesystem in no-recovery mode. Filesystem will be inconsistent.");
+"Mounting V%d filesystem in no-recovery mode. Filesystem will be inconsistent.",
+ XFS_SB_VERSION_NUM(&mp->m_sb));
ASSERT(mp->m_flags & XFS_MOUNT_RDONLY);
}
@@ -1181,11 +1183,14 @@ xlog_iodone(xfs_buf_t *bp)
/* log I/O is always issued ASYNC */
ASSERT(XFS_BUF_ISASYNC(bp));
xlog_state_done_syncing(iclog, aborted);
+
/*
- * do not reference the buffer (bp) here as we could race
- * with it being freed after writing the unmount record to the
- * log.
+ * drop the buffer lock now that we are done. Nothing references
+ * the buffer after this, so an unmount waiting on this lock can now
+ * tear it down safely. As such, it is unsafe to reference the buffer
+ * (bp) after the unlock as we could race with it being freed.
*/
+ xfs_buf_unlock(bp);
}
/*
@@ -1368,8 +1373,16 @@ xlog_alloc_log(
bp = xfs_buf_alloc(mp->m_logdev_targp, 0, BTOBB(log->l_iclog_size), 0);
if (!bp)
goto out_free_log;
- bp->b_iodone = xlog_iodone;
+
+ /*
+ * The iclogbuf buffer locks are held over IO but we are not going to do
+ * IO yet. Hence unlock the buffer so that the log IO path can grab it
+ * when appropriately.
+ */
ASSERT(xfs_buf_islocked(bp));
+ xfs_buf_unlock(bp);
+
+ bp->b_iodone = xlog_iodone;
log->l_xbuf = bp;
spin_lock_init(&log->l_icloglock);
@@ -1398,6 +1411,9 @@ xlog_alloc_log(
if (!bp)
goto out_free_iclog;
+ ASSERT(xfs_buf_islocked(bp));
+ xfs_buf_unlock(bp);
+
bp->b_iodone = xlog_iodone;
iclog->ic_bp = bp;
iclog->ic_data = bp->b_addr;
@@ -1422,7 +1438,6 @@ xlog_alloc_log(
iclog->ic_callback_tail = &(iclog->ic_callback);
iclog->ic_datap = (char *)iclog->ic_data + log->l_iclog_hsize;
- ASSERT(xfs_buf_islocked(iclog->ic_bp));
init_waitqueue_head(&iclog->ic_force_wait);
init_waitqueue_head(&iclog->ic_write_wait);
@@ -1631,6 +1646,12 @@ xlog_cksum(
* we transition the iclogs to IOERROR state *after* flushing all existing
* iclogs to disk. This is because we don't want anymore new transactions to be
* started or completed afterwards.
+ *
+ * We lock the iclogbufs here so that we can serialise against IO completion
+ * during unmount. We might be processing a shutdown triggered during unmount,
+ * and that can occur asynchronously to the unmount thread, and hence we need to
+ * ensure that completes before tearing down the iclogbufs. Hence we need to
+ * hold the buffer lock across the log IO to acheive that.
*/
STATIC int
xlog_bdstrat(
@@ -1638,6 +1659,7 @@ xlog_bdstrat(
{
struct xlog_in_core *iclog = bp->b_fspriv;
+ xfs_buf_lock(bp);
if (iclog->ic_state & XLOG_STATE_IOERROR) {
xfs_buf_ioerror(bp, EIO);
xfs_buf_stale(bp);
@@ -1645,7 +1667,8 @@ xlog_bdstrat(
/*
* It would seem logical to return EIO here, but we rely on
* the log state machine to propagate I/O errors instead of
- * doing it here.
+ * doing it here. Similarly, IO completion will unlock the
+ * buffer, so we don't do it here.
*/
return 0;
}
@@ -1847,14 +1870,28 @@ xlog_dealloc_log(
xlog_cil_destroy(log);
/*
- * always need to ensure that the extra buffer does not point to memory
- * owned by another log buffer before we free it.
+ * Cycle all the iclogbuf locks to make sure all log IO completion
+ * is done before we tear down these buffers.
*/
+ iclog = log->l_iclog;
+ for (i = 0; i < log->l_iclog_bufs; i++) {
+ xfs_buf_lock(iclog->ic_bp);
+ xfs_buf_unlock(iclog->ic_bp);
+ iclog = iclog->ic_next;
+ }
+
+ /*
+ * Always need to ensure that the extra buffer does not point to memory
+ * owned by another log buffer before we free it. Also, cycle the lock
+ * first to ensure we've completed IO on it.
+ */
+ xfs_buf_lock(log->l_xbuf);
+ xfs_buf_unlock(log->l_xbuf);
xfs_buf_set_empty(log->l_xbuf, BTOBB(log->l_iclog_size));
xfs_buf_free(log->l_xbuf);
iclog = log->l_iclog;
- for (i=0; i<log->l_iclog_bufs; i++) {
+ for (i = 0; i < log->l_iclog_bufs; i++) {
xfs_buf_free(iclog->ic_bp);
next_iclog = iclog->ic_next;
kmem_free(iclog);
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 993cb19e7d39..944f3d9456a8 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -743,8 +743,6 @@ xfs_mountfs(
new_size *= mp->m_sb.sb_inodesize / XFS_DINODE_MIN_SIZE;
if (mp->m_sb.sb_inoalignmt >= XFS_B_TO_FSBT(mp, new_size))
mp->m_inode_cluster_size = new_size;
- xfs_info(mp, "Using inode cluster size of %d bytes",
- mp->m_inode_cluster_size);
}
/*
diff --git a/fs/xfs/xfs_sb.c b/fs/xfs/xfs_sb.c
index 0c0e41bbe4e3..8baf61afae1d 100644
--- a/fs/xfs/xfs_sb.c
+++ b/fs/xfs/xfs_sb.c
@@ -201,10 +201,6 @@ xfs_mount_validate_sb(
* write validation, we don't need to check feature masks.
*/
if (check_version && XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) {
- xfs_alert(mp,
-"Version 5 superblock detected. This kernel has EXPERIMENTAL support enabled!\n"
-"Use of these features in this kernel is at your own risk!");
-
if (xfs_sb_has_compat_feature(sbp,
XFS_SB_FEAT_COMPAT_UNKNOWN)) {
xfs_warn(mp,
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index a4ae41c179a8..65d8c793a25c 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -603,6 +603,7 @@ DEFINE_INODE_EVENT(xfs_readlink);
DEFINE_INODE_EVENT(xfs_inactive_symlink);
DEFINE_INODE_EVENT(xfs_alloc_file_space);
DEFINE_INODE_EVENT(xfs_free_file_space);
+DEFINE_INODE_EVENT(xfs_zero_file_space);
DEFINE_INODE_EVENT(xfs_collapse_file_space);
DEFINE_INODE_EVENT(xfs_readdir);
#ifdef CONFIG_XFS_POSIX_ACL
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-28 21:00:54 +0100