#include <linux/mount.h>
#include <linux/writeback.h>
#include <linux/falloc.h>
+#include <linux/quotaops.h>
#define MLOG_MASK_PREFIX ML_INODE
#include <cluster/masklog.h>
#include "mmap.h"
#include "suballoc.h"
#include "super.h"
+#include "xattr.h"
+#include "acl.h"
+#include "quota.h"
#include "buffer_head_io.h"
if (err)
goto bail;
+ if (datasync && !(inode->i_state & I_DIRTY_DATASYNC))
+ goto bail;
+
journal = osb->journal->j_journal;
- err = journal_force_commit(journal);
+ err = jbd2_journal_force_commit(journal);
bail:
mlog_exit(err);
mlog_entry_void();
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
- if (handle == NULL) {
- ret = -ENOMEM;
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
mlog_errno(ret);
goto out;
}
- ret = ocfs2_journal_access(handle, inode, bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
+ ret = ocfs2_journal_access_di(handle, inode, bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out_commit;
return status;
}
-static int ocfs2_simple_size_update(struct inode *inode,
- struct buffer_head *di_bh,
- u64 new_i_size)
+int ocfs2_simple_size_update(struct inode *inode,
+ struct buffer_head *di_bh,
+ u64 new_i_size)
{
int ret;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
handle_t *handle = NULL;
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
- if (handle == NULL) {
- ret = -ENOMEM;
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
mlog_errno(ret);
goto out;
}
goto out;
}
- status = ocfs2_journal_access(handle, inode, fe_bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
+ status = ocfs2_journal_access_di(handle, inode, fe_bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
mlog_errno(status);
goto out_commit;
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)new_i_size);
+ /* We trust di_bh because it comes from ocfs2_inode_lock(), which
+ * already validated it */
fe = (struct ocfs2_dinode *) di_bh->b_data;
- if (!OCFS2_IS_VALID_DINODE(fe)) {
- OCFS2_RO_ON_INVALID_DINODE(inode->i_sb, fe);
- status = -EIO;
- goto bail;
- }
mlog_bug_on_msg(le64_to_cpu(fe->i_size) != i_size_read(inode),
"Inode %llu, inode i_size = %lld != di "
struct ocfs2_alloc_context *meta_ac,
enum ocfs2_alloc_restarted *reason_ret)
{
- struct ocfs2_dinode *fe = (struct ocfs2_dinode *) fe_bh->b_data;
- struct ocfs2_extent_list *el = &fe->id2.i_list;
+ int ret;
+ struct ocfs2_extent_tree et;
- return ocfs2_add_clusters_in_btree(osb, inode, logical_offset,
+ ocfs2_init_dinode_extent_tree(&et, inode, fe_bh);
+ ret = ocfs2_add_clusters_in_btree(osb, inode, logical_offset,
clusters_to_add, mark_unwritten,
- fe_bh, el, handle,
- data_ac, meta_ac, reason_ret,
- OCFS2_DINODE_EXTENT, NULL);
+ &et, handle,
+ data_ac, meta_ac, reason_ret);
+
+ return ret;
}
static int __ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
struct ocfs2_alloc_context *meta_ac = NULL;
enum ocfs2_alloc_restarted why;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
+ struct ocfs2_extent_tree et;
+ int did_quota = 0;
mlog_entry("(clusters_to_add = %u)\n", clusters_to_add);
*/
BUG_ON(mark_unwritten && !ocfs2_sparse_alloc(osb));
- status = ocfs2_read_block(osb, OCFS2_I(inode)->ip_blkno, &bh,
- OCFS2_BH_CACHED, inode);
+ status = ocfs2_read_inode_block(inode, &bh);
if (status < 0) {
mlog_errno(status);
goto leave;
}
-
fe = (struct ocfs2_dinode *) bh->b_data;
- if (!OCFS2_IS_VALID_DINODE(fe)) {
- OCFS2_RO_ON_INVALID_DINODE(inode->i_sb, fe);
- status = -EIO;
- goto leave;
- }
restart_all:
BUG_ON(le32_to_cpu(fe->i_clusters) != OCFS2_I(inode)->ip_clusters);
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(long long)i_size_read(inode), le32_to_cpu(fe->i_clusters),
clusters_to_add);
- status = ocfs2_lock_allocators(inode, bh, &fe->id2.i_list,
- clusters_to_add, 0, &data_ac,
- &meta_ac, OCFS2_DINODE_EXTENT, NULL);
+ ocfs2_init_dinode_extent_tree(&et, inode, bh);
+ status = ocfs2_lock_allocators(inode, &et, clusters_to_add, 0,
+ &data_ac, &meta_ac);
if (status) {
mlog_errno(status);
goto leave;
}
restarted_transaction:
+ if (vfs_dq_alloc_space_nodirty(inode, ocfs2_clusters_to_bytes(osb->sb,
+ clusters_to_add))) {
+ status = -EDQUOT;
+ goto leave;
+ }
+ did_quota = 1;
+
/* reserve a write to the file entry early on - that we if we
* run out of credits in the allocation path, we can still
* update i_size. */
- status = ocfs2_journal_access(handle, inode, bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
+ status = ocfs2_journal_access_di(handle, inode, bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
mlog_errno(status);
goto leave;
spin_lock(&OCFS2_I(inode)->ip_lock);
clusters_to_add -= (OCFS2_I(inode)->ip_clusters - prev_clusters);
spin_unlock(&OCFS2_I(inode)->ip_lock);
+ /* Release unused quota reservation */
+ vfs_dq_free_space(inode,
+ ocfs2_clusters_to_bytes(osb->sb, clusters_to_add));
+ did_quota = 0;
if (why != RESTART_NONE && clusters_to_add) {
if (why == RESTART_META) {
OCFS2_I(inode)->ip_clusters, (long long)i_size_read(inode));
leave:
+ if (status < 0 && did_quota)
+ vfs_dq_free_space(inode,
+ ocfs2_clusters_to_bytes(osb->sb, clusters_to_add));
if (handle) {
ocfs2_commit_trans(osb, handle);
handle = NULL;
restart_func = 0;
goto restart_all;
}
- if (bh) {
- brelse(bh);
- bh = NULL;
- }
+ brelse(bh);
+ bh = NULL;
mlog_exit(status);
return status;
/* Some parts of this taken from generic_cont_expand, which turned out
* to be too fragile to do exactly what we need without us having to
- * worry about recursive locking in ->prepare_write() and
- * ->commit_write(). */
+ * worry about recursive locking in ->write_begin() and ->write_end(). */
static int ocfs2_write_zero_page(struct inode *inode,
u64 size)
{
struct ocfs2_super *osb = OCFS2_SB(sb);
struct buffer_head *bh = NULL;
handle_t *handle = NULL;
+ int qtype;
+ struct dquot *transfer_from[MAXQUOTAS] = { };
+ struct dquot *transfer_to[MAXQUOTAS] = { };
mlog_entry("(0x%p, '%.*s')\n", dentry,
dentry->d_name.len, dentry->d_name.name);
goto bail_unlock;
}
- if (i_size_read(inode) > attr->ia_size)
+ if (i_size_read(inode) > attr->ia_size) {
+ if (ocfs2_should_order_data(inode)) {
+ status = ocfs2_begin_ordered_truncate(inode,
+ attr->ia_size);
+ if (status)
+ goto bail_unlock;
+ }
status = ocfs2_truncate_file(inode, bh, attr->ia_size);
- else
+ } else
status = ocfs2_extend_file(inode, bh, attr->ia_size);
if (status < 0) {
if (status != -ENOSPC)
}
}
- handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
- if (IS_ERR(handle)) {
- status = PTR_ERR(handle);
- mlog_errno(status);
- goto bail_unlock;
+ if ((attr->ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid) ||
+ (attr->ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid)) {
+ /*
+ * Gather pointers to quota structures so that allocation /
+ * freeing of quota structures happens here and not inside
+ * vfs_dq_transfer() where we have problems with lock ordering
+ */
+ if (attr->ia_valid & ATTR_UID && attr->ia_uid != inode->i_uid
+ && OCFS2_HAS_RO_COMPAT_FEATURE(sb,
+ OCFS2_FEATURE_RO_COMPAT_USRQUOTA)) {
+ transfer_to[USRQUOTA] = dqget(sb, attr->ia_uid,
+ USRQUOTA);
+ transfer_from[USRQUOTA] = dqget(sb, inode->i_uid,
+ USRQUOTA);
+ if (!transfer_to[USRQUOTA] || !transfer_from[USRQUOTA]) {
+ status = -ESRCH;
+ goto bail_unlock;
+ }
+ }
+ if (attr->ia_valid & ATTR_GID && attr->ia_gid != inode->i_gid
+ && OCFS2_HAS_RO_COMPAT_FEATURE(sb,
+ OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)) {
+ transfer_to[GRPQUOTA] = dqget(sb, attr->ia_gid,
+ GRPQUOTA);
+ transfer_from[GRPQUOTA] = dqget(sb, inode->i_gid,
+ GRPQUOTA);
+ if (!transfer_to[GRPQUOTA] || !transfer_from[GRPQUOTA]) {
+ status = -ESRCH;
+ goto bail_unlock;
+ }
+ }
+ handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS +
+ 2 * ocfs2_quota_trans_credits(sb));
+ if (IS_ERR(handle)) {
+ status = PTR_ERR(handle);
+ mlog_errno(status);
+ goto bail_unlock;
+ }
+ status = vfs_dq_transfer(inode, attr) ? -EDQUOT : 0;
+ if (status < 0)
+ goto bail_commit;
+ } else {
+ handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
+ if (IS_ERR(handle)) {
+ status = PTR_ERR(handle);
+ mlog_errno(status);
+ goto bail_unlock;
+ }
}
/*
if (size_change)
ocfs2_rw_unlock(inode, 1);
bail:
- if (bh)
- brelse(bh);
+ brelse(bh);
+
+ /* Release quota pointers in case we acquired them */
+ for (qtype = 0; qtype < MAXQUOTAS; qtype++) {
+ dqput(transfer_to[qtype]);
+ dqput(transfer_from[qtype]);
+ }
+
+ if (!status && attr->ia_valid & ATTR_MODE) {
+ status = ocfs2_acl_chmod(inode);
+ if (status < 0)
+ mlog_errno(status);
+ }
mlog_exit(status);
return status;
goto out;
}
- ret = generic_permission(inode, mask, NULL);
+ ret = generic_permission(inode, mask, ocfs2_check_acl);
ocfs2_inode_unlock(inode, 0);
out:
(unsigned long long)OCFS2_I(inode)->ip_blkno, inode->i_mode);
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
- if (handle == NULL) {
- ret = -ENOMEM;
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
mlog_errno(ret);
goto out;
}
- ret = ocfs2_journal_access(handle, inode, bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
+ ret = ocfs2_journal_access_di(handle, inode, bh,
+ OCFS2_JOURNAL_ACCESS_WRITE);
if (ret < 0) {
mlog_errno(ret);
goto out_trans;
{
int ret;
struct buffer_head *bh = NULL;
- struct ocfs2_inode_info *oi = OCFS2_I(inode);
- ret = ocfs2_read_block(OCFS2_SB(inode->i_sb),
- oi->ip_blkno, &bh, OCFS2_BH_CACHED, inode);
+ ret = ocfs2_read_inode_block(inode, &bh);
if (ret < 0) {
mlog_errno(ret);
goto out;
struct buffer_head *di_bh = NULL;
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
- ret = ocfs2_read_block(OCFS2_SB(inode->i_sb),
- OCFS2_I(inode)->ip_blkno, &di_bh,
- OCFS2_BH_CACHED, inode);
+ ret = ocfs2_read_inode_block(inode, &di_bh);
if (ret) {
mlog_errno(ret);
goto out;
return ret;
}
-static int __ocfs2_remove_inode_range(struct inode *inode,
- struct buffer_head *di_bh,
- u32 cpos, u32 phys_cpos, u32 len,
- struct ocfs2_cached_dealloc_ctxt *dealloc)
-{
- int ret;
- u64 phys_blkno = ocfs2_clusters_to_blocks(inode->i_sb, phys_cpos);
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
- struct inode *tl_inode = osb->osb_tl_inode;
- handle_t *handle;
- struct ocfs2_alloc_context *meta_ac = NULL;
- struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
-
- ret = ocfs2_lock_allocators(inode, di_bh, &di->id2.i_list,
- 0, 1, NULL, &meta_ac,
- OCFS2_DINODE_EXTENT, NULL);
- if (ret) {
- mlog_errno(ret);
- return ret;
- }
-
- mutex_lock(&tl_inode->i_mutex);
-
- if (ocfs2_truncate_log_needs_flush(osb)) {
- ret = __ocfs2_flush_truncate_log(osb);
- if (ret < 0) {
- mlog_errno(ret);
- goto out;
- }
- }
-
- handle = ocfs2_start_trans(osb, OCFS2_REMOVE_EXTENT_CREDITS);
- if (handle == NULL) {
- ret = -ENOMEM;
- mlog_errno(ret);
- goto out;
- }
-
- ret = ocfs2_journal_access(handle, inode, di_bh,
- OCFS2_JOURNAL_ACCESS_WRITE);
- if (ret) {
- mlog_errno(ret);
- goto out;
- }
-
- ret = ocfs2_remove_extent(inode, di_bh, cpos, len, handle, meta_ac,
- dealloc, OCFS2_DINODE_EXTENT, NULL);
- if (ret) {
- mlog_errno(ret);
- goto out_commit;
- }
-
- OCFS2_I(inode)->ip_clusters -= len;
- di->i_clusters = cpu_to_le32(OCFS2_I(inode)->ip_clusters);
-
- ret = ocfs2_journal_dirty(handle, di_bh);
- if (ret) {
- mlog_errno(ret);
- goto out_commit;
- }
-
- ret = ocfs2_truncate_log_append(osb, handle, phys_blkno, len);
- if (ret)
- mlog_errno(ret);
-
-out_commit:
- ocfs2_commit_trans(osb, handle);
-out:
- mutex_unlock(&tl_inode->i_mutex);
-
- if (meta_ac)
- ocfs2_free_alloc_context(meta_ac);
-
- return ret;
-}
-
/*
* Truncate a byte range, avoiding pages within partial clusters. This
* preserves those pages for the zeroing code to write to.
goto out;
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
- if (handle == NULL) {
- ret = -ENOMEM;
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
mlog_errno(ret);
goto out;
}
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct ocfs2_cached_dealloc_ctxt dealloc;
struct address_space *mapping = inode->i_mapping;
+ struct ocfs2_extent_tree et;
+ ocfs2_init_dinode_extent_tree(&et, inode, di_bh);
ocfs2_init_dealloc_ctxt(&dealloc);
if (byte_len == 0)
/* Only do work for non-holes */
if (phys_cpos != 0) {
- ret = __ocfs2_remove_inode_range(inode, di_bh, cpos,
- phys_cpos, alloc_size,
- &dealloc);
+ ret = ocfs2_remove_btree_range(inode, &et, cpos,
+ phys_cpos, alloc_size,
+ &dealloc);
if (ret) {
mlog_errno(ret);
goto out;
struct ocfs2_space_resv *sr)
{
struct inode *inode = file->f_path.dentry->d_inode;
- struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);;
+ struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
if ((cmd == OCFS2_IOC_RESVSP || cmd == OCFS2_IOC_RESVSP64) &&
!ocfs2_writes_unwritten_extents(osb))
written = generic_file_direct_write(iocb, iov, &nr_segs, *ppos,
ppos, count, ocount);
if (written < 0) {
+ /*
+ * direct write may have instantiated a few
+ * blocks outside i_size. Trim these off again.
+ * Don't need i_size_read because we hold i_mutex.
+ */
+ if (*ppos + count > inode->i_size)
+ vmtruncate(inode, inode->i_size);
ret = written;
goto out_dio;
}
*/
if (old_size != i_size_read(inode) ||
old_clusters != OCFS2_I(inode)->ip_clusters) {
- ret = journal_force_commit(osb->journal->j_journal);
+ ret = jbd2_journal_force_commit(osb->journal->j_journal);
if (ret < 0)
written = ret;
}
return written ? written : ret;
}
+static int ocfs2_splice_to_file(struct pipe_inode_info *pipe,
+ struct file *out,
+ struct splice_desc *sd)
+{
+ int ret;
+
+ ret = ocfs2_prepare_inode_for_write(out->f_path.dentry, &sd->pos,
+ sd->total_len, 0, NULL);
+ if (ret < 0) {
+ mlog_errno(ret);
+ return ret;
+ }
+
+ return splice_from_pipe_feed(pipe, sd, pipe_to_file);
+}
+
static ssize_t ocfs2_file_splice_write(struct pipe_inode_info *pipe,
struct file *out,
loff_t *ppos,
unsigned int flags)
{
int ret;
- struct inode *inode = out->f_path.dentry->d_inode;
+ struct address_space *mapping = out->f_mapping;
+ struct inode *inode = mapping->host;
+ struct splice_desc sd = {
+ .total_len = len,
+ .flags = flags,
+ .pos = *ppos,
+ .u.file = out,
+ };
mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", out, pipe,
(unsigned int)len,
out->f_path.dentry->d_name.len,
out->f_path.dentry->d_name.name);
- inode_double_lock(inode, pipe->inode);
+ if (pipe->inode)
+ mutex_lock_nested(&pipe->inode->i_mutex, I_MUTEX_PARENT);
- ret = ocfs2_rw_lock(inode, 1);
- if (ret < 0) {
- mlog_errno(ret);
- goto out;
- }
+ splice_from_pipe_begin(&sd);
+ do {
+ ret = splice_from_pipe_next(pipe, &sd);
+ if (ret <= 0)
+ break;
- ret = ocfs2_prepare_inode_for_write(out->f_path.dentry, ppos, len, 0,
- NULL);
- if (ret < 0) {
- mlog_errno(ret);
- goto out_unlock;
- }
+ mutex_lock_nested(&inode->i_mutex, I_MUTEX_CHILD);
+ ret = ocfs2_rw_lock(inode, 1);
+ if (ret < 0)
+ mlog_errno(ret);
+ else {
+ ret = ocfs2_splice_to_file(pipe, out, &sd);
+ ocfs2_rw_unlock(inode, 1);
+ }
+ mutex_unlock(&inode->i_mutex);
+ } while (ret > 0);
+ splice_from_pipe_end(pipe, &sd);
- ret = generic_file_splice_write_nolock(pipe, out, ppos, len, flags);
+ if (pipe->inode)
+ mutex_unlock(&pipe->inode->i_mutex);
-out_unlock:
- ocfs2_rw_unlock(inode, 1);
-out:
- inode_double_unlock(inode, pipe->inode);
+ if (sd.num_spliced)
+ ret = sd.num_spliced;
+
+ if (ret > 0) {
+ unsigned long nr_pages;
+
+ *ppos += ret;
+ nr_pages = (ret + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+
+ /*
+ * If file or inode is SYNC and we actually wrote some data,
+ * sync it.
+ */
+ if (unlikely((out->f_flags & O_SYNC) || IS_SYNC(inode))) {
+ int err;
+
+ mutex_lock(&inode->i_mutex);
+ err = ocfs2_rw_lock(inode, 1);
+ if (err < 0) {
+ mlog_errno(err);
+ } else {
+ err = generic_osync_inode(inode, mapping,
+ OSYNC_METADATA|OSYNC_DATA);
+ ocfs2_rw_unlock(inode, 1);
+ }
+ mutex_unlock(&inode->i_mutex);
+
+ if (err)
+ ret = err;
+ }
+ balance_dirty_pages_ratelimited_nr(mapping, nr_pages);
+ }
mlog_exit(ret);
return ret;
size_t len,
unsigned int flags)
{
- int ret = 0;
+ int ret = 0, lock_level = 0;
struct inode *inode = in->f_path.dentry->d_inode;
mlog_entry("(0x%p, 0x%p, %u, '%.*s')\n", in, pipe,
/*
* See the comment in ocfs2_file_aio_read()
*/
- ret = ocfs2_inode_lock(inode, NULL, 0);
+ ret = ocfs2_inode_lock_atime(inode, in->f_vfsmnt, &lock_level);
if (ret < 0) {
mlog_errno(ret);
goto bail;
}
- ocfs2_inode_unlock(inode, 0);
+ ocfs2_inode_unlock(inode, lock_level);
ret = generic_file_splice_read(in, ppos, pipe, len, flags);
.setattr = ocfs2_setattr,
.getattr = ocfs2_getattr,
.permission = ocfs2_permission,
+ .setxattr = generic_setxattr,
+ .getxattr = generic_getxattr,
+ .listxattr = ocfs2_listxattr,
+ .removexattr = generic_removexattr,
.fallocate = ocfs2_fallocate,
.fiemap = ocfs2_fiemap,
};