summaryrefslogtreecommitdiffstats
path: root/fs/gfs2
diff options
context:
space:
mode:
Diffstat (limited to 'fs/gfs2')
-rw-r--r--fs/gfs2/Kconfig1
-rw-r--r--fs/gfs2/acl.c6
-rw-r--r--fs/gfs2/acl.h2
-rw-r--r--fs/gfs2/aops.c31
-rw-r--r--fs/gfs2/bmap.c31
-rw-r--r--fs/gfs2/bmap.h2
-rw-r--r--fs/gfs2/dir.c46
-rw-r--r--fs/gfs2/export.c2
-rw-r--r--fs/gfs2/file.c15
-rw-r--r--fs/gfs2/glock.c100
-rw-r--r--fs/gfs2/incore.h15
-rw-r--r--fs/gfs2/inode.c136
-rw-r--r--fs/gfs2/inode.h4
-rw-r--r--fs/gfs2/log.c164
-rw-r--r--fs/gfs2/log.h30
-rw-r--r--fs/gfs2/lops.c2
-rw-r--r--fs/gfs2/main.c16
-rw-r--r--fs/gfs2/meta_io.c13
-rw-r--r--fs/gfs2/ops_fstype.c56
-rw-r--r--fs/gfs2/ops_inode.c19
-rw-r--r--fs/gfs2/quota.c135
-rw-r--r--fs/gfs2/quota.h2
-rw-r--r--fs/gfs2/recovery.c54
-rw-r--r--fs/gfs2/recovery.h6
-rw-r--r--fs/gfs2/rgrp.c81
-rw-r--r--fs/gfs2/super.c63
-rw-r--r--fs/gfs2/super.h2
-rw-r--r--fs/gfs2/sys.c66
-rw-r--r--fs/gfs2/trans.c18
-rw-r--r--fs/gfs2/xattr.c30
30 files changed, 738 insertions, 410 deletions
diff --git a/fs/gfs2/Kconfig b/fs/gfs2/Kconfig
index a47b43107112..cc9665522148 100644
--- a/fs/gfs2/Kconfig
+++ b/fs/gfs2/Kconfig
@@ -7,7 +7,6 @@ config GFS2_FS
select IP_SCTP if DLM_SCTP
select FS_POSIX_ACL
select CRC32
- select SLOW_WORK
select QUOTACTL
help
A cluster filesystem.
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 87ee309d4c24..48171f4c943d 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -236,10 +236,14 @@ static int gfs2_xattr_system_get(struct dentry *dentry, const char *name,
void *buffer, size_t size, int xtype)
{
struct inode *inode = dentry->d_inode;
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
struct posix_acl *acl;
int type;
int error;
+ if (!sdp->sd_args.ar_posix_acl)
+ return -EOPNOTSUPP;
+
type = gfs2_acl_type(name);
if (type < 0)
return type;
@@ -335,7 +339,7 @@ out:
return error;
}
-struct xattr_handler gfs2_xattr_system_handler = {
+const struct xattr_handler gfs2_xattr_system_handler = {
.prefix = XATTR_SYSTEM_PREFIX,
.flags = GFS2_EATYPE_SYS,
.get = gfs2_xattr_system_get,
diff --git a/fs/gfs2/acl.h b/fs/gfs2/acl.h
index 9306a2e6620c..b522b0cb39ea 100644
--- a/fs/gfs2/acl.h
+++ b/fs/gfs2/acl.h
@@ -19,6 +19,6 @@
extern int gfs2_check_acl(struct inode *inode, int mask);
extern int gfs2_acl_create(struct gfs2_inode *dip, struct inode *inode);
extern int gfs2_acl_chmod(struct gfs2_inode *ip, struct iattr *attr);
-extern struct xattr_handler gfs2_xattr_system_handler;
+extern const struct xattr_handler gfs2_xattr_system_handler;
#endif /* __ACL_DOT_H__ */
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 0c1d0b82dcf1..194fe16d8418 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -136,10 +136,7 @@ static int gfs2_writeback_writepage(struct page *page,
if (ret <= 0)
return ret;
- ret = mpage_writepage(page, gfs2_get_block_noalloc, wbc);
- if (ret == -EAGAIN)
- ret = block_write_full_page(page, gfs2_get_block_noalloc, wbc);
- return ret;
+ return nobh_writepage(page, gfs2_get_block_noalloc, wbc);
}
/**
@@ -418,6 +415,7 @@ static int gfs2_jdata_writepages(struct address_space *mapping,
static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
{
struct buffer_head *dibh;
+ u64 dsize = i_size_read(&ip->i_inode);
void *kaddr;
int error;
@@ -437,9 +435,10 @@ static int stuffed_readpage(struct gfs2_inode *ip, struct page *page)
return error;
kaddr = kmap_atomic(page, KM_USER0);
- memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode),
- ip->i_disksize);
- memset(kaddr + ip->i_disksize, 0, PAGE_CACHE_SIZE - ip->i_disksize);
+ if (dsize > (dibh->b_size - sizeof(struct gfs2_dinode)))
+ dsize = (dibh->b_size - sizeof(struct gfs2_dinode));
+ memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize);
+ memset(kaddr + dsize, 0, PAGE_CACHE_SIZE - dsize);
kunmap_atomic(kaddr, KM_USER0);
flush_dcache_page(page);
brelse(dibh);
@@ -635,9 +634,7 @@ static int gfs2_write_begin(struct file *file, struct address_space *mapping,
}
}
- error = gfs2_write_alloc_required(ip, pos, len, &alloc_required);
- if (error)
- goto out_unlock;
+ alloc_required = gfs2_write_alloc_required(ip, pos, len);
if (alloc_required || gfs2_is_jdata(ip))
gfs2_write_calc_reserv(ip, len, &data_blocks, &ind_blocks);
@@ -698,8 +695,14 @@ out:
return 0;
page_cache_release(page);
+
+ /*
+ * XXX(truncate): the call below should probably be replaced with
+ * a call to the gfs2-specific truncate blocks helper to actually
+ * release disk blocks..
+ */
if (pos + len > ip->i_inode.i_size)
- vmtruncate(&ip->i_inode, ip->i_inode.i_size);
+ truncate_setsize(&ip->i_inode, ip->i_inode.i_size);
out_endtrans:
gfs2_trans_end(sdp);
out_trans_fail:
@@ -1039,9 +1042,9 @@ static ssize_t gfs2_direct_IO(int rw, struct kiocb *iocb,
if (rv != 1)
goto out; /* dio not valid, fall back to buffered i/o */
- rv = blockdev_direct_IO_no_locking(rw, iocb, inode, inode->i_sb->s_bdev,
- iov, offset, nr_segs,
- gfs2_get_block_direct, NULL);
+ rv = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
+ offset, nr_segs, gfs2_get_block_direct,
+ NULL, NULL, 0);
out:
gfs2_glock_dq_m(1, &gh);
gfs2_holder_uninit(&gh);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 5e411d5f4697..6f482809d1a3 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -71,11 +71,13 @@ static int gfs2_unstuffer_page(struct gfs2_inode *ip, struct buffer_head *dibh,
if (!PageUptodate(page)) {
void *kaddr = kmap(page);
+ u64 dsize = i_size_read(inode);
+
+ if (dsize > (dibh->b_size - sizeof(struct gfs2_dinode)))
+ dsize = dibh->b_size - sizeof(struct gfs2_dinode);
- memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode),
- ip->i_disksize);
- memset(kaddr + ip->i_disksize, 0,
- PAGE_CACHE_SIZE - ip->i_disksize);
+ memcpy(kaddr, dibh->b_data + sizeof(struct gfs2_dinode), dsize);
+ memset(kaddr + dsize, 0, PAGE_CACHE_SIZE - dsize);
kunmap(page);
SetPageUptodate(page);
@@ -1038,13 +1040,15 @@ static int trunc_start(struct gfs2_inode *ip, u64 size)
goto out;
if (gfs2_is_stuffed(ip)) {
+ u64 dsize = size + sizeof(struct gfs2_dinode);
ip->i_disksize = size;
ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
gfs2_dinode_out(ip, dibh->b_data);
- gfs2_buffer_clear_tail(dibh, sizeof(struct gfs2_dinode) + size);
+ if (dsize > dibh->b_size)
+ dsize = dibh->b_size;
+ gfs2_buffer_clear_tail(dibh, dsize);
error = 1;
-
} else {
if (size & (u64)(sdp->sd_sb.sb_bsize - 1))
error = gfs2_block_truncate_page(ip->i_inode.i_mapping);
@@ -1240,13 +1244,12 @@ int gfs2_file_dealloc(struct gfs2_inode *ip)
* @ip: the file being written to
* @offset: the offset to write to
* @len: the number of bytes being written
- * @alloc_required: set to 1 if an alloc is required, 0 otherwise
*
- * Returns: errno
+ * Returns: 1 if an alloc is required, 0 otherwise
*/
int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
- unsigned int len, int *alloc_required)
+ unsigned int len)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct buffer_head bh;
@@ -1254,26 +1257,23 @@ int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
u64 lblock, lblock_stop, size;
u64 end_of_file;
- *alloc_required = 0;
-
if (!len)
return 0;
if (gfs2_is_stuffed(ip)) {
if (offset + len >
sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode))
- *alloc_required = 1;
+ return 1;
return 0;
}
- *alloc_required = 1;
shift = sdp->sd_sb.sb_bsize_shift;
BUG_ON(gfs2_is_dir(ip));
end_of_file = (ip->i_disksize + sdp->sd_sb.sb_bsize - 1) >> shift;
lblock = offset >> shift;
lblock_stop = (offset + len + sdp->sd_sb.sb_bsize - 1) >> shift;
if (lblock_stop > end_of_file)
- return 0;
+ return 1;
size = (lblock_stop - lblock) << shift;
do {
@@ -1281,12 +1281,11 @@ int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
bh.b_size = size;
gfs2_block_map(&ip->i_inode, lblock, &bh, 0);
if (!buffer_mapped(&bh))
- return 0;
+ return 1;
size -= bh.b_size;
lblock += (bh.b_size >> ip->i_inode.i_blkbits);
} while(size > 0);
- *alloc_required = 0;
return 0;
}
diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
index c983177e05ac..a20a5213135a 100644
--- a/fs/gfs2/bmap.h
+++ b/fs/gfs2/bmap.h
@@ -52,6 +52,6 @@ int gfs2_truncatei(struct gfs2_inode *ip, u64 size);
int gfs2_truncatei_resume(struct gfs2_inode *ip);
int gfs2_file_dealloc(struct gfs2_inode *ip);
int gfs2_write_alloc_required(struct gfs2_inode *ip, u64 offset,
- unsigned int len, int *alloc_required);
+ unsigned int len);
#endif /* __BMAP_DOT_H__ */
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 25fddc100f18..b9dd88a78dd4 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -392,7 +392,7 @@ static int gfs2_dirent_find_space(const struct gfs2_dirent *dent,
unsigned totlen = be16_to_cpu(dent->de_rec_len);
if (gfs2_dirent_sentinel(dent))
- actual = GFS2_DIRENT_SIZE(0);
+ actual = 0;
if (totlen - actual >= required)
return 1;
return 0;
@@ -955,7 +955,12 @@ static int dir_split_leaf(struct inode *inode, const struct qstr *name)
/* Change the pointers.
Don't bother distinguishing stuffed from non-stuffed.
This code is complicated enough already. */
- lp = kmalloc(half_len * sizeof(__be64), GFP_NOFS | __GFP_NOFAIL);
+ lp = kmalloc(half_len * sizeof(__be64), GFP_NOFS);
+ if (!lp) {
+ error = -ENOMEM;
+ goto fail_brelse;
+ }
+
/* Change the pointers */
for (x = 0; x < half_len; x++)
lp[x] = cpu_to_be64(bn);
@@ -1063,7 +1068,9 @@ static int dir_double_exhash(struct gfs2_inode *dip)
/* Allocate both the "from" and "to" buffers in one big chunk */
- buf = kcalloc(3, sdp->sd_hash_bsize, GFP_NOFS | __GFP_NOFAIL);
+ buf = kcalloc(3, sdp->sd_hash_bsize, GFP_NOFS);
+ if (!buf)
+ return -ENOMEM;
for (block = dip->i_disksize >> sdp->sd_hash_bsize_shift; block--;) {
error = gfs2_dir_read_data(dip, (char *)buf,
@@ -1231,6 +1238,25 @@ static int do_filldir_main(struct gfs2_inode *dip, u64 *offset,
return 0;
}
+static void *gfs2_alloc_sort_buffer(unsigned size)
+{
+ void *ptr = NULL;
+
+ if (size < KMALLOC_MAX_SIZE)
+ ptr = kmalloc(size, GFP_NOFS | __GFP_NOWARN);
+ if (!ptr)
+ ptr = __vmalloc(size, GFP_NOFS, PAGE_KERNEL);
+ return ptr;
+}
+
+static void gfs2_free_sort_buffer(void *ptr)
+{
+ if (is_vmalloc_addr(ptr))
+ vfree(ptr);
+ else
+ kfree(ptr);
+}
+
static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
filldir_t filldir, int *copied, unsigned *depth,
u64 leaf_no)
@@ -1271,7 +1297,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
* 99 is the maximum number of entries that can fit in a single
* leaf block.
*/
- larr = vmalloc((leaves + entries + 99) * sizeof(void *));
+ larr = gfs2_alloc_sort_buffer((leaves + entries + 99) * sizeof(void *));
if (!larr)
goto out;
darr = (const struct gfs2_dirent **)(larr + leaves);
@@ -1282,7 +1308,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
do {
error = get_leaf(ip, lfn, &bh);
if (error)
- goto out_kfree;
+ goto out_free;
lf = (struct gfs2_leaf *)bh->b_data;
lfn = be64_to_cpu(lf->lf_next);
if (lf->lf_entries) {
@@ -1291,7 +1317,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
gfs2_dirent_gather, NULL, &g);
error = PTR_ERR(dent);
if (IS_ERR(dent))
- goto out_kfree;
+ goto out_free;
if (entries2 != g.offset) {
fs_warn(sdp, "Number of entries corrupt in dir "
"leaf %llu, entries2 (%u) != "
@@ -1300,7 +1326,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
entries2, g.offset);
error = -EIO;
- goto out_kfree;
+ goto out_free;
}
error = 0;
larr[leaf++] = bh;
@@ -1312,10 +1338,10 @@ static int gfs2_dir_read_leaf(struct inode *inode, u64 *offset, void *opaque,
BUG_ON(entries2 != entries);
error = do_filldir_main(ip, offset, opaque, filldir, darr,
entries, copied);
-out_kfree:
+out_free:
for(i = 0; i < leaf; i++)
brelse(larr[i]);
- vfree(larr);
+ gfs2_free_sort_buffer(larr);
out:
return error;
}
@@ -1475,7 +1501,7 @@ struct inode *gfs2_dir_search(struct inode *dir, const struct qstr *name)
inode = gfs2_inode_lookup(dir->i_sb,
be16_to_cpu(dent->de_type),
be64_to_cpu(dent->de_inum.no_addr),
- be64_to_cpu(dent->de_inum.no_formal_ino), 0);
+ be64_to_cpu(dent->de_inum.no_formal_ino));
brelse(bh);
return inode;
}
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index c22c21174833..dfe237a3f8ad 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -168,7 +168,7 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb,
if (error)
goto fail;
- inode = gfs2_inode_lookup(sb, DT_UNKNOWN, inum->no_addr, 0, 0);
+ inode = gfs2_inode_lookup(sb, DT_UNKNOWN, inum->no_addr, 0);
if (IS_ERR(inode)) {
error = PTR_ERR(inode);
goto fail;
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index e6dd2aec6f82..4edd662c8232 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -218,6 +218,11 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
if (error)
goto out_drop_write;
+ error = -EACCES;
+ if (!is_owner_or_cap(inode))
+ goto out;
+
+ error = 0;
flags = ip->i_diskflags;
new_flags = (flags & ~mask) | (reqflags & mask);
if ((new_flags ^ flags) == 0)
@@ -275,8 +280,10 @@ static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
{
struct inode *inode = filp->f_path.dentry->d_inode;
u32 fsflags, gfsflags;
+
if (get_user(fsflags, ptr))
return -EFAULT;
+
gfsflags = fsflags_cvt(fsflags_to_gfs2, fsflags);
if (!S_ISDIR(inode->i_mode)) {
if (gfsflags & GFS2_DIF_INHERIT_JDATA)
@@ -344,7 +351,6 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
unsigned long last_index;
u64 pos = page->index << PAGE_CACHE_SHIFT;
unsigned int data_blocks, ind_blocks, rblocks;
- int alloc_required = 0;
struct gfs2_holder gh;
struct gfs2_alloc *al;
int ret;
@@ -357,8 +363,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
set_bit(GIF_SW_PAGED, &ip->i_flags);
- ret = gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE, &alloc_required);
- if (ret || !alloc_required)
+ if (!gfs2_write_alloc_required(ip, pos, PAGE_CACHE_SIZE))
goto out_unlock;
ret = -ENOMEM;
al = gfs2_alloc_get(ip);
@@ -547,9 +552,9 @@ static int gfs2_close(struct inode *inode, struct file *file)
* Returns: errno
*/
-static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync)
+static int gfs2_fsync(struct file *file, int datasync)
{
- struct inode *inode = dentry->d_inode;
+ struct inode *inode = file->f_mapping->host;
int sync_state = inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC);
int ret = 0;
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 454d4b4eb36b..9adf8f924e08 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -328,6 +328,30 @@ static void gfs2_holder_wake(struct gfs2_holder *gh)
}
/**
+ * do_error - Something unexpected has happened during a lock request
+ *
+ */
+
+static inline void do_error(struct gfs2_glock *gl, const int ret)
+{
+ struct gfs2_holder *gh, *tmp;
+
+ list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
+ if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+ continue;
+ if (ret & LM_OUT_ERROR)
+ gh->gh_error = -EIO;
+ else if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
+ gh->gh_error = GLR_TRYFAILED;
+ else
+ continue;
+ list_del_init(&gh->gh_list);
+ trace_gfs2_glock_queue(gh, 0);
+ gfs2_holder_wake(gh);
+ }
+}
+
+/**
* do_promote - promote as many requests as possible on the current queue
* @gl: The glock
*
@@ -375,36 +399,13 @@ restart:
}
if (gh->gh_list.prev == &gl->gl_holders)
return 1;
+ do_error(gl, 0);
break;
}
return 0;
}
/**
- * do_error - Something unexpected has happened during a lock request
- *
- */
-
-static inline void do_error(struct gfs2_glock *gl, const int ret)
-{
- struct gfs2_holder *gh, *tmp;
-
- list_for_each_entry_safe(gh, tmp, &gl->gl_holders, gh_list) {
- if (test_bit(HIF_HOLDER, &gh->gh_iflags))
- continue;
- if (ret & LM_OUT_ERROR)
- gh->gh_error = -EIO;
- else if (gh->gh_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB))
- gh->gh_error = GLR_TRYFAILED;
- else
- continue;
- list_del_init(&gh->gh_list);
- trace_gfs2_glock_queue(gh, 0);
- gfs2_holder_wake(gh);
- }
-}
-
-/**
* find_first_waiter - find the first gh that's waiting for the glock
* @gl: the glock
*/
@@ -855,6 +856,9 @@ void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *
gh->gh_flags = flags;
gh->gh_iflags = 0;
gh->gh_ip = (unsigned long)__builtin_return_address(0);
+ if (gh->gh_owner_pid)
+ put_pid(gh->gh_owner_pid);
+ gh->gh_owner_pid = get_pid(task_pid(current));
}
/**
@@ -1059,6 +1063,9 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
spin_lock(&gl->gl_spin);
add_to_queue(gh);
+ if ((LM_FLAG_NOEXP & gh->gh_flags) &&
+ test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))
+ set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
run_queue(gl, 1);
spin_unlock(&gl->gl_spin);
@@ -1316,6 +1323,36 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
}
/**
+ * gfs2_should_freeze - Figure out if glock should be frozen
+ * @gl: The glock in question
+ *
+ * Glocks are not frozen if (a) the result of the dlm operation is
+ * an error, (b) the locking operation was an unlock operation or
+ * (c) if there is a "noexp" flagged request anywhere in the queue
+ *
+ * Returns: 1 if freezing should occur, 0 otherwise
+ */
+
+static int gfs2_should_freeze(const struct gfs2_glock *gl)
+{
+ const struct gfs2_holder *gh;
+
+ if (gl->gl_reply & ~LM_OUT_ST_MASK)
+ return 0;
+ if (gl->gl_target == LM_ST_UNLOCKED)
+ return 0;
+
+ list_for_each_entry(gh, &gl->gl_holders, gh_list) {
+ if (test_bit(HIF_HOLDER, &gh->gh_iflags))
+ continue;
+ if (LM_FLAG_NOEXP & gh->gh_flags)
+ return 0;
+ }
+
+ return 1;
+}
+
+/**
* gfs2_glock_complete - Callback used by locking
* @gl: Pointer to the glock
* @ret: The return value from the dlm
@@ -1325,18 +1362,17 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
{
struct lm_lockstruct *ls = &gl->gl_sbd->sd_lockstruct;
+
gl->gl_reply = ret;
+
if (unlikely(test_bit(DFL_BLOCK_LOCKS, &ls->ls_flags))) {
- struct gfs2_holder *gh;
spin_lock(&gl->gl_spin);
- gh = find_first_waiter(gl);
- if ((!(gh && (gh->gh_flags & LM_FLAG_NOEXP)) &&
- (gl->gl_target != LM_ST_UNLOCKED)) ||
- ((ret & ~LM_OUT_ST_MASK) != 0))
+ if (gfs2_should_freeze(gl)) {
set_bit(GLF_FROZEN, &gl->gl_flags);
- spin_unlock(&gl->gl_spin);
- if (test_bit(GLF_FROZEN, &gl->gl_flags))
+ spin_unlock(&gl->gl_spin);
return;
+ }
+ spin_unlock(&gl->gl_spin);
}
set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
gfs2_glock_hold(gl);
@@ -1345,7 +1381,7 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
}
-static int gfs2_shrink_glock_memory(int nr, gfp_t gfp_mask)
+static int gfs2_shrink_glock_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
{
struct gfs2_glock *gl;
int may_demote;
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index 3aac46f6853e..fdbf4b366fa5 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -12,7 +12,6 @@
#include <linux/fs.h>
#include <linux/workqueue.h>
-#include <linux/slow-work.h>
#include <linux/dlm.h>
#include <linux/buffer_head.h>
@@ -383,7 +382,7 @@ struct gfs2_journal_extent {
struct gfs2_jdesc {
struct list_head jd_list;
struct list_head extent_list;
- struct slow_work jd_work;
+ struct work_struct jd_work;
struct inode *jd_inode;
unsigned long jd_flags;
#define JDF_RECOVERY 1
@@ -439,9 +438,6 @@ struct gfs2_args {
struct gfs2_tune {
spinlock_t gt_spin;
- unsigned int gt_incore_log_blocks;
- unsigned int gt_log_flush_secs;
-
unsigned int gt_logd_secs;
unsigned int gt_quota_simul_sync; /* Max quotavals to sync at once */
@@ -462,6 +458,8 @@ enum {
SDF_SHUTDOWN = 2,
SDF_NOBARRIERS = 3,
SDF_NORECOVERY = 4,
+ SDF_DEMOTE = 5,
+ SDF_NOJOURNALID = 6,
};
#define GFS2_FSNAME_LEN 256
@@ -618,6 +616,7 @@ struct gfs2_sbd {
unsigned int sd_log_commited_databuf;
int sd_log_commited_revoke;
+ atomic_t sd_log_pinned;
unsigned int sd_log_num_buf;
unsigned int sd_log_num_revoke;
unsigned int sd_log_num_rg;
@@ -629,15 +628,17 @@ struct gfs2_sbd {
struct list_head sd_log_le_databuf;
struct list_head sd_log_le_ordered;
+ atomic_t sd_log_thresh1;
+ atomic_t sd_log_thresh2;
atomic_t sd_log_blks_free;
- struct mutex sd_log_reserve_mutex;
+ wait_queue_head_t sd_log_waitq;
+ wait_queue_head_t sd_logd_waitq;
u64 sd_log_sequence;
unsigned int sd_log_head;
unsigned int sd_log_tail;
int sd_log_idle;
- unsigned long sd_log_flush_time;
struct rw_semaphore sd_log_flush_lock;
atomic_t sd_log_in_flight;
wait_queue_head_t sd_log_flush_wait;
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index b1bf2694fb2b..08140f185a37 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -84,7 +84,7 @@ static int iget_skip_test(struct inode *inode, void *opaque)
struct gfs2_skip_data *data = opaque;
if (ip->i_no_addr == data->no_addr) {
- if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)){
+ if (inode->i_state & (I_FREEING|I_WILL_FREE)){
data->skipped = 1;
return 0;
}
@@ -158,7 +158,6 @@ void gfs2_set_iop(struct inode *inode)
* @sb: The super block
* @no_addr: The inode number
* @type: The type of the inode
- * @skip_freeing: set this not return an inode if it is currently being freed.
*
* Returns: A VFS inode, or an error
*/
@@ -166,17 +165,14 @@ void gfs2_set_iop(struct inode *inode)
struct inode *gfs2_inode_lookup(struct super_block *sb,
unsigned int type,
u64 no_addr,
- u64 no_formal_ino, int skip_freeing)
+ u64 no_formal_ino)
{
struct inode *inode;
struct gfs2_inode *ip;
- struct gfs2_glock *io_gl;
+ struct gfs2_glock *io_gl = NULL;
int error;
- if (skip_freeing)
- inode = gfs2_iget_skip(sb, no_addr);
- else
- inode = gfs2_iget(sb, no_addr);
+ inode = gfs2_iget(sb, no_addr);
ip = GFS2_I(inode);
if (!inode)
@@ -202,6 +198,7 @@ struct inode *gfs2_inode_lookup(struct super_block *sb,
ip->i_iopen_gh.gh_gl->gl_object = ip;
gfs2_glock_put(io_gl);
+ io_gl = NULL;
if ((type == DT_UNKNOWN) && (no_formal_ino == 0))
goto gfs2_nfsbypass;
@@ -232,13 +229,107 @@ gfs2_nfsbypass:
fail_glock:
gfs2_glock_dq(&ip->i_iopen_gh);
fail_iopen:
+ if (io_gl)
+ gfs2_glock_put(io_gl);
+fail_put:
+ if (inode->i_state & I_NEW)
+ ip->i_gl->gl_object = NULL;
+ gfs2_glock_put(ip->i_gl);
+fail:
+ if (inode->i_state & I_NEW)
+ iget_failed(inode);
+ else
+ iput(inode);
+ return ERR_PTR(error);
+}
+
+/**
+ * gfs2_process_unlinked_inode - Lookup an unlinked inode for reclamation
+ * and try to reclaim it by doing iput.
+ *
+ * This function assumes no rgrp locks are currently held.
+ *
+ * @sb: The super block
+ * no_addr: The inode number
+ *
+ */
+
+void gfs2_process_unlinked_inode(struct super_block *sb, u64 no_addr)
+{
+ struct gfs2_sbd *sdp;
+ struct gfs2_inode *ip;
+ struct gfs2_glock *io_gl = NULL;
+ int error;
+ struct gfs2_holder gh;
+ struct inode *inode;
+
+ inode = gfs2_iget_skip(sb, no_addr);
+
+ if (!inode)
+ return;
+
+ /* If it's not a new inode, someone's using it, so leave it alone. */
+ if (!(inode->i_state & I_NEW)) {
+ iput(inode);
+ return;
+ }
+
+ ip = GFS2_I(inode);
+ sdp = GFS2_SB(inode);
+ ip->i_no_formal_ino = -1;
+
+ error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
+ if (unlikely(error))
+ goto fail;
+ ip->i_gl->gl_object = ip;
+
+ error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
+ if (unlikely(error))
+ goto fail_put;
+
+ set_bit(GIF_INVALID, &ip->i_flags);
+ error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, LM_FLAG_TRY | GL_EXACT,
+ &ip->i_iopen_gh);
+ if (unlikely(error))
+ goto fail_iopen;
+
+ ip->i_iopen_gh.gh_gl->gl_object = ip;
gfs2_glock_put(io_gl);
+ io_gl = NULL;
+
+ inode->i_mode = DT2IF(DT_UNKNOWN);
+
+ /*
+ * We must read the inode in order to work out its type in
+ * this case. Note that this doesn't happen often as we normally
+ * know the type beforehand. This code path only occurs during
+ * unlinked inode recovery (where it is safe to do this glock,
+ * which is not true in the general case).
+ */
+ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, LM_FLAG_TRY,
+ &gh);
+ if (unlikely(error))
+ goto fail_glock;
+
+ /* Inode is now uptodate */
+ gfs2_glock_dq_uninit(&gh);
+ gfs2_set_iop(inode);
+
+ /* The iput will cause it to be deleted. */
+ iput(inode);
+ return;
+
+fail_glock:
+ gfs2_glock_dq(&ip->i_iopen_gh);
+fail_iopen:
+ if (io_gl)
+ gfs2_glock_put(io_gl);
fail_put:
ip->i_gl->gl_object = NULL;
gfs2_glock_put(ip->i_gl);
fail:
iget_failed(inode);
- return ERR_PTR(error);
+ return;
}
static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
@@ -862,7 +953,7 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
goto fail_gunlock2;
inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode), inum.no_addr,
- inum.no_formal_ino, 0);
+ inum.no_formal_ino);
if (IS_ERR(inode))
goto fail_gunlock2;
@@ -900,18 +991,29 @@ fail:
static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
{
+ struct inode *inode = &ip->i_inode;
struct buffer_head *dibh;
int error;
error = gfs2_meta_inode_buffer(ip, &dibh);
- if (!error) {
- error = inode_setattr(&ip->i_inode, attr);
- gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error);
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
- gfs2_dinode_out(ip, dibh->b_data);
- brelse(dibh);
+ if (error)
+ return error;
+
+ if ((attr->ia_valid & ATTR_SIZE) &&
+ attr->ia_size != i_size_read(inode)) {
+ error = vmtruncate(inode, attr->ia_size);
+ if (error)
+ return error;
}
- return error;
+
+ setattr_copy(inode, attr);
+ mark_inode_dirty(inode);
+
+ gfs2_assert_warn(GFS2_SB(inode), !error);
+ gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_dinode_out(ip, dibh->b_data);
+ brelse(dibh);
+ return 0;
}
/**
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index c341aaf67adb..300ada3f21de 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -83,8 +83,8 @@ static inline void gfs2_inum_out(const struct gfs2_inode *ip,
extern void gfs2_set_iop(struct inode *inode);
extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type,
- u64 no_addr, u64 no_formal_ino,
- int skip_freeing);
+ u64 no_addr, u64 no_formal_ino);
+extern void gfs2_process_unlinked_inode(struct super_block *sb, u64 no_addr);
extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr);
extern int gfs2_inode_refresh(struct gfs2_inode *ip);
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index e5bf4b59d46e..cde1248a6225 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -168,12 +168,11 @@ static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int fl
return list_empty(&ai->ai_ail1_list);
}
-static void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags)
+static void gfs2_ail1_start(struct gfs2_sbd *sdp)
{
struct list_head *head;
u64 sync_gen;
- struct list_head *first;
- struct gfs2_ail *first_ai, *ai, *tmp;
+ struct gfs2_ail *ai;
int done = 0;
gfs2_log_lock(sdp);
@@ -184,21 +183,9 @@ static void gfs2_ail1_start(struct gfs2_sbd *sdp, int flags)
}
sync_gen = sdp->sd_ail_sync_gen++;
- first = head->prev;
- first_ai = list_entry(first, struct gfs2_ail, ai_list);
- first_ai->ai_sync_gen = sync_gen;
- gfs2_ail1_start_one(sdp, first_ai); /* This may drop log lock */
-
- if (flags & DIO_ALL)
- first = NULL;
-
while(!done) {
- if (first && (head->prev != first ||
- gfs2_ail1_empty_one(sdp, first_ai, 0)))
- break;
-
done = 1;
- list_for_each_entry_safe_reverse(ai, tmp, head, ai_list) {
+ list_for_each_entry_reverse(ai, head, ai_list) {
if (ai->ai_sync_gen >= sync_gen)
continue;
ai->ai_sync_gen = sync_gen;
@@ -290,58 +277,57 @@ static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
* flush time, so we ensure that we have just enough free blocks at all
* times to avoid running out during a log flush.
*
+ * We no longer flush the log here, instead we wake up logd to do that
+ * for us. To avoid the thundering herd and to ensure that we deal fairly
+ * with queued waiters, we use an exclusive wait. This means that when we
+ * get woken with enough journal space to get our reservation, we need to
+ * wake the next waiter on the list.
+ *
* Returns: errno
*/
int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
{
- unsigned int try = 0;
unsigned reserved_blks = 6 * (4096 / sdp->sd_vfs->s_blocksize);
+ unsigned wanted = blks + reserved_blks;
+ DEFINE_WAIT(wait);
+ int did_wait = 0;
+ unsigned int free_blocks;
if (gfs2_assert_warn(sdp, blks) ||
gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
return -EINVAL;
-
- mutex_lock(&sdp->sd_log_reserve_mutex);
- gfs2_log_lock(sdp);
- while(atomic_read(&sdp->sd_log_blks_free) <= (blks + reserved_blks)) {
- gfs2_log_unlock(sdp);
- gfs2_ail1_empty(sdp, 0);
- gfs2_log_flush(sdp, NULL);
-
- if (try++)
- gfs2_ail1_start(sdp, 0);
- gfs2_log_lock(sdp);
+retry:
+ free_blocks = atomic_read(&sdp->sd_log_blks_free);
+ if (unlikely(free_blocks <= wanted)) {
+ do {
+ prepare_to_wait_exclusive(&sdp->sd_log_waitq, &wait,
+ TASK_UNINTERRUPTIBLE);
+ wake_up(&sdp->sd_logd_waitq);
+ did_wait = 1;
+ if (atomic_read(&sdp->sd_log_blks_free) <= wanted)
+ io_schedule();
+ free_blocks = atomic_read(&sdp->sd_log_blks_free);
+ } while(free_blocks <= wanted);
+ finish_wait(&sdp->sd_log_waitq, &wait);
}
- atomic_sub(blks, &sdp->sd_log_blks_free);
+ if (atomic_cmpxchg(&sdp->sd_log_blks_free, free_blocks,
+ free_blocks - blks) != free_blocks)
+ goto retry;
trace_gfs2_log_blocks(sdp, -blks);
- gfs2_log_unlock(sdp);
- mutex_unlock(&sdp->sd_log_reserve_mutex);
+
+ /*
+ * If we waited, then so might others, wake them up _after_ we get
+ * our share of the log.
+ */
+ if (unlikely(did_wait))
+ wake_up(&sdp->sd_log_waitq);
down_read(&sdp->sd_log_flush_lock);
return 0;
}
-/**
- * gfs2_log_release - Release a given number of log blocks
- * @sdp: The GFS2 superblock
- * @blks: The number of blocks
- *
- */
-
-void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
-{
-
- gfs2_log_lock(sdp);
- atomic_add(blks, &sdp->sd_log_blks_free);
- trace_gfs2_log_blocks(sdp, blks);
- gfs2_assert_withdraw(sdp,
- atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks);
- gfs2_log_unlock(sdp);
- up_read(&sdp->sd_log_flush_lock);
-}
-
static u64 log_bmap(struct gfs2_sbd *sdp, unsigned int lbn)
{
struct gfs2_journal_extent *je;
@@ -559,11 +545,10 @@ static void log_pull_tail(struct gfs2_sbd *sdp, unsigned int new_tail)
ail2_empty(sdp, new_tail);
- gfs2_log_lock(sdp);
atomic_add(dist, &sdp->sd_log_blks_free);
trace_gfs2_log_blocks(sdp, dist);
- gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <= sdp->sd_jdesc->jd_blocks);
- gfs2_log_unlock(sdp);
+ gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
+ sdp->sd_jdesc->jd_blocks);
sdp->sd_log_tail = new_tail;
}
@@ -610,16 +595,17 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
goto skip_barrier;
get_bh(bh);
- submit_bh(WRITE_SYNC | (1 << BIO_RW_BARRIER) | (1 << BIO_RW_META), bh);
+ submit_bh(WRITE_BARRIER | REQ_META, bh);
wait_on_buffer(bh);
if (buffer_eopnotsupp(bh)) {
clear_buffer_eopnotsupp(bh);
set_buffer_uptodate(bh);
+ fs_info(sdp, "barrier sync failed - disabling barriers\n");
set_bit(SDF_NOBARRIERS, &sdp->sd_flags);
lock_buffer(bh);
skip_barrier:
get_bh(bh);
- submit_bh(WRITE_SYNC | (1 << BIO_RW_META), bh);
+ submit_bh(WRITE_SYNC | REQ_META, bh);
wait_on_buffer(bh);
}
if (!buffer_uptodate(bh))
@@ -710,7 +696,7 @@ static void gfs2_ordered_wait(struct gfs2_sbd *sdp)
*
*/
-void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
+void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
{
struct gfs2_ail *ai;
@@ -822,6 +808,13 @@ static void buf_lo_incore_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
* @sdp: the filesystem
* @tr: the transaction
*
+ * We wake up gfs2_logd if the number of pinned blocks exceed thresh1
+ * or the total number of used blocks (pinned blocks plus AIL blocks)
+ * is greater than thresh2.
+ *
+ * At mount time thresh1 is 1/3rd of journal size, thresh2 is 2/3rd of
+ * journal size.
+ *
* Returns: errno
*/
@@ -832,10 +825,10 @@ void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
up_read(&sdp->sd_log_flush_lock);
- gfs2_log_lock(sdp);
- if (sdp->sd_log_num_buf > gfs2_tune_get(sdp, gt_incore_log_blocks))
- wake_up_process(sdp->sd_logd_process);
- gfs2_log_unlock(sdp);
+ if (atomic_read(&sdp->sd_log_pinned) > atomic_read(&sdp->sd_log_thresh1) ||
+ ((sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free)) >
+ atomic_read(&sdp->sd_log_thresh2)))
+ wake_up(&sdp->sd_logd_waitq);
}
/**
@@ -882,13 +875,23 @@ void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
{
gfs2_log_flush(sdp, NULL);
for (;;) {
- gfs2_ail1_start(sdp, DIO_ALL);
+ gfs2_ail1_start(sdp);
if (gfs2_ail1_empty(sdp, DIO_ALL))
break;
msleep(10);
}
}
+static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
+{
+ return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1));
+}
+
+static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
+{
+ unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free);
+ return used_blocks >= atomic_read(&sdp->sd_log_thresh2);
+}
/**
* gfs2_logd - Update log tail as Active Items get flushed to in-place blocks
@@ -901,28 +904,43 @@ void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
int gfs2_logd(void *data)
{
struct gfs2_sbd *sdp = data;
- unsigned long t;
- int need_flush;
+ unsigned long t = 1;
+ DEFINE_WAIT(wait);
+ unsigned preflush;
while (!kthread_should_stop()) {
- /* Advance the log tail */
- t = sdp->sd_log_flush_time +
- gfs2_tune_get(sdp, gt_log_flush_secs) * HZ;
+ preflush = atomic_read(&sdp->sd_log_pinned);
+ if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
+ gfs2_ail1_empty(sdp, DIO_ALL);
+ gfs2_log_flush(sdp, NULL);
+ gfs2_ail1_empty(sdp, DIO_ALL);
+ }
- gfs2_ail1_empty(sdp, DIO_ALL);
- gfs2_log_lock(sdp);
- need_flush = sdp->sd_log_num_buf > gfs2_tune_get(sdp, gt_incore_log_blocks);
- gfs2_log_unlock(sdp);
- if (need_flush || time_after_eq(jiffies, t)) {
+ if (gfs2_ail_flush_reqd(sdp)) {
+ gfs2_ail1_start(sdp);
+ io_schedule();
+ gfs2_ail1_empty(sdp, 0);
gfs2_log_flush(sdp, NULL);
- sdp->sd_log_flush_time = jiffies;
+ gfs2_ail1_empty(sdp, DIO_ALL);
}
+ wake_up(&sdp->sd_log_waitq);
t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
if (freezing(current))
refrigerator();
- schedule_timeout_interruptible(t);
+
+ do {
+ prepare_to_wait(&sdp->sd_logd_waitq, &wait,
+ TASK_UNINTERRUPTIBLE);
+ if (!gfs2_ail_flush_reqd(sdp) &&
+ !gfs2_jrnl_flush_reqd(sdp) &&
+ !kthread_should_stop())
+ t = schedule_timeout(t);
+ } while(t && !gfs2_ail_flush_reqd(sdp) &&
+ !gfs2_jrnl_flush_reqd(sdp) &&
+ !kthread_should_stop());
+ finish_wait(&sdp->sd_logd_waitq, &wait);
}
return 0;
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 7c64510ccfd2..0d007f920234 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -47,29 +47,21 @@ static inline void gfs2_log_pointers_init(struct gfs2_sbd *sdp,
sdp->sd_log_head = sdp->sd_log_tail = value;
}
-unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
+extern unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
unsigned int ssize);
-int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
-void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks);
-void gfs2_log_incr_head(struct gfs2_sbd *sdp);
+extern int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks);
+extern void gfs2_log_incr_head(struct gfs2_sbd *sdp);
-struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp);
-struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
+extern struct buffer_head *gfs2_log_get_buf(struct gfs2_sbd *sdp);
+extern struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
struct buffer_head *real);
-void __gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl);
+extern void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl);
+extern void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
+extern void gfs2_remove_from_ail(struct gfs2_bufdata *bd);
-static inline void gfs2_log_flush(struct gfs2_sbd *sbd, struct gfs2_glock *gl)
-{
- if (!gl || test_bit(GLF_LFLUSH, &gl->gl_flags))
- __gfs2_log_flush(sbd, gl);
-}
-
-void gfs2_log_commit(struct gfs2_sbd *sdp, struct gfs2_trans *trans);
-void gfs2_remove_from_ail(struct gfs2_bufdata *bd);
-
-void gfs2_log_shutdown(struct gfs2_sbd *sdp);
-void gfs2_meta_syncfs(struct gfs2_sbd *sdp);
-int gfs2_logd(void *data);
+extern void gfs2_log_shutdown(struct gfs2_sbd *sdp);
+extern void gfs2_meta_syncfs(struct gfs2_sbd *sdp);
+extern int gfs2_logd(void *data);
#endif /* __LOG_DOT_H__ */
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index adc260fbea90..bf33f822058d 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -54,6 +54,7 @@ static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
if (bd->bd_ail)
list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list);
get_bh(bh);
+ atomic_inc(&sdp->sd_log_pinned);
trace_gfs2_pin(bd, 1);
}
@@ -94,6 +95,7 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
trace_gfs2_pin(bd, 0);
gfs2_log_unlock(sdp);
unlock_buffer(bh);
+ atomic_dec(&sdp->sd_log_pinned);
}
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index a88fadc704bb..b1e9630eb46a 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -15,7 +15,6 @@
#include <linux/init.h>
#include <linux/gfs2_ondisk.h>
#include <asm/atomic.h>
-#include <linux/slow-work.h>
#include "gfs2.h"
#include "incore.h"
@@ -24,6 +23,7 @@
#include "util.h"
#include "glock.h"
#include "quota.h"
+#include "recovery.h"
static struct shrinker qd_shrinker = {
.shrink = gfs2_shrink_qd_memory,
@@ -94,7 +94,7 @@ static int __init init_gfs2_fs(void)
if (!gfs2_glock_cachep)
goto fail;
- gfs2_glock_aspace_cachep = kmem_cache_create("gfs2_glock (aspace)",
+ gfs2_glock_aspace_cachep = kmem_cache_create("gfs2_glock(aspace)",
sizeof(struct gfs2_glock) +
sizeof(struct address_space),
0, 0, gfs2_init_gl_aspace_once);
@@ -138,9 +138,11 @@ static int __init init_gfs2_fs(void)
if (error)
goto fail_unregister;
- error = slow_work_register_user(THIS_MODULE);
- if (error)
- goto fail_slow;
+ error = -ENOMEM;
+ gfs_recovery_wq = alloc_workqueue("gfs_recovery",
+ WQ_NON_REENTRANT | WQ_RESCUER, 0);
+ if (!gfs_recovery_wq)
+ goto fail_wq;
gfs2_register_debugfs();
@@ -148,7 +150,7 @@ static int __init init_gfs2_fs(void)
return 0;
-fail_slow:
+fail_wq:
unregister_filesystem(&gfs2meta_fs_type);
fail_unregister:
unregister_filesystem(&gfs2_fs_type);
@@ -190,7 +192,7 @@ static void __exit exit_gfs2_fs(void)
gfs2_unregister_debugfs();
unregister_filesystem(&gfs2_fs_type);
unregister_filesystem(&gfs2meta_fs_type);
- slow_work_unregister_user(THIS_MODULE);
+ destroy_workqueue(gfs_recovery_wq);
kmem_cache_destroy(gfs2_quotad_cachep);
kmem_cache_destroy(gfs2_rgrpd_cachep);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 0bb12c80937a..f3b071f921aa 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -34,11 +34,10 @@
static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc)
{
- int err;
struct buffer_head *bh, *head;
int nr_underway = 0;
- int write_op = (1 << BIO_RW_META) | ((wbc->sync_mode == WB_SYNC_ALL ?
- WRITE_SYNC_PLUG : WRITE));
+ int write_op = REQ_META |
+ (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC_PLUG : WRITE);
BUG_ON(!PageLocked(page));
BUG_ON(!page_has_buffers(page));
@@ -86,11 +85,10 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb
} while (bh != head);
unlock_page(page);
- err = 0;
if (nr_underway == 0)
end_page_writeback(page);
- return err;
+ return 0;
}
const struct address_space_operations gfs2_meta_aops = {
@@ -227,7 +225,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
}
bh->b_end_io = end_buffer_read_sync;
get_bh(bh);
- submit_bh(READ_SYNC | (1 << BIO_RW_META), bh);
+ submit_bh(READ_SYNC | REQ_META, bh);
if (!(flags & DIO_WAIT))
return 0;
@@ -313,6 +311,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int
struct gfs2_bufdata *bd = bh->b_private;
if (test_clear_buffer_pinned(bh)) {
+ atomic_dec(&sdp->sd_log_pinned);
list_del_init(&bd->bd_le.le_list);
if (meta) {
gfs2_assert_warn(sdp, sdp->sd_log_num_buf);
@@ -433,7 +432,7 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen)
if (buffer_uptodate(first_bh))
goto out;
if (!buffer_locked(first_bh))
- ll_rw_block(READ_SYNC | (1 << BIO_RW_META), 1, &first_bh);
+ ll_rw_block(READ_SYNC | REQ_META, 1, &first_bh);
dblock++;
extlen--;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index c1309ed1c496..4d4b1e8ac64c 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -17,7 +17,6 @@
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/gfs2_ondisk.h>
-#include <linux/slow-work.h>
#include <linux/quotaops.h>
#include "gfs2.h"
@@ -57,8 +56,6 @@ static void gfs2_tune_init(struct gfs2_tune *gt)
{
spin_lock_init(&gt->gt_spin);
- gt->gt_incore_log_blocks = 1024;
- gt->gt_logd_secs = 1;
gt->gt_quota_simul_sync = 64;
gt->gt_quota_warn_period = 10;
gt->gt_quota_scale_num = 1;
@@ -78,7 +75,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
sb->s_fs_info = sdp;
sdp->sd_vfs = sb;
-
+ set_bit(SDF_NOJOURNALID, &sdp->sd_flags);
gfs2_tune_init(&sdp->sd_tune);
init_waitqueue_head(&sdp->sd_glock_wait);
@@ -101,14 +98,15 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
spin_lock_init(&sdp->sd_trunc_lock);
spin_lock_init(&sdp->sd_log_lock);
-
+ atomic_set(&sdp->sd_log_pinned, 0);
INIT_LIST_HEAD(&sdp->sd_log_le_buf);
INIT_LIST_HEAD(&sdp->sd_log_le_revoke);
INIT_LIST_HEAD(&sdp->sd_log_le_rg);
INIT_LIST_HEAD(&sdp->sd_log_le_databuf);
INIT_LIST_HEAD(&sdp->sd_log_le_ordered);
- mutex_init(&sdp->sd_log_reserve_mutex);
+ init_waitqueue_head(&sdp->sd_log_waitq);
+ init_waitqueue_head(&sdp->sd_logd_waitq);
INIT_LIST_HEAD(&sdp->sd_ail1_list);
INIT_LIST_HEAD(&sdp->sd_ail2_list);
@@ -276,7 +274,7 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector)
bio->bi_end_io = end_bio_io_page;
bio->bi_private = page;
- submit_bio(READ_SYNC | (1 << BIO_RW_META), bio);
+ submit_bio(READ_SYNC | REQ_META, bio);
wait_on_page_locked(page);
bio_put(bio);
if (!PageUptodate(page)) {
@@ -487,7 +485,7 @@ static int gfs2_lookup_root(struct super_block *sb, struct dentry **dptr,
struct dentry *dentry;
struct inode *inode;
- inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
+ inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0);
if (IS_ERR(inode)) {
fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
return PTR_ERR(inode);
@@ -674,7 +672,7 @@ static int gfs2_jindex_hold(struct gfs2_sbd *sdp, struct gfs2_holder *ji_gh)
break;
INIT_LIST_HEAD(&jd->extent_list);
- slow_work_init(&jd->jd_work, &gfs2_recover_ops);
+ INIT_WORK(&jd->jd_work, gfs2_recover_func);
jd->jd_inode = gfs2_lookupi(sdp->sd_jindex, &name, 1);
if (!jd->jd_inode || IS_ERR(jd->jd_inode)) {
if (!jd->jd_inode)
@@ -733,6 +731,8 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
if (sdp->sd_args.ar_spectator) {
sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
+ atomic_set(&sdp->sd_log_thresh1, 2*sdp->sd_jdesc->jd_blocks/5);
+ atomic_set(&sdp->sd_log_thresh2, 4*sdp->sd_jdesc->jd_blocks/5);
} else {
if (sdp->sd_lockstruct.ls_jid >= gfs2_jindex_size(sdp)) {
fs_err(sdp, "can't mount journal #%u\n",
@@ -770,6 +770,8 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
goto fail_jinode_gh;
}
atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
+ atomic_set(&sdp->sd_log_thresh1, 2*sdp->sd_jdesc->jd_blocks/5);
+ atomic_set(&sdp->sd_log_thresh2, 4*sdp->sd_jdesc->jd_blocks/5);
/* Map the extents for this journal's blocks */
map_journal_extents(sdp);
@@ -779,7 +781,8 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
if (sdp->sd_lockstruct.ls_first) {
unsigned int x;
for (x = 0; x < sdp->sd_journals; x++) {
- error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x));
+ error = gfs2_recover_journal(gfs2_jdesc_find(sdp, x),
+ true);
if (error) {
fs_err(sdp, "error recovering journal %u: %d\n",
x, error);
@@ -789,7 +792,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
gfs2_others_may_mount(sdp);
} else if (!sdp->sd_args.ar_spectator) {
- error = gfs2_recover_journal(sdp->sd_jdesc);
+ error = gfs2_recover_journal(sdp->sd_jdesc, true);
if (error) {
fs_err(sdp, "error recovering my journal: %d\n", error);
goto fail_jinode_gh;
@@ -951,8 +954,6 @@ static int init_threads(struct gfs2_sbd *sdp, int undo)
if (undo)
goto fail_quotad;
- sdp->sd_log_flush_time = jiffies;
-
p = kthread_run(gfs2_logd, sdp, "gfs2_logd");
error = IS_ERR(p);
if (error) {
@@ -1049,7 +1050,8 @@ static int gfs2_lm_mount(struct gfs2_sbd *sdp, int silent)
ret = match_int(&tmp[0], &option);
if (ret || option < 0)
goto hostdata_error;
- ls->ls_jid = option;
+ if (test_and_clear_bit(SDF_NOJOURNALID, &sdp->sd_flags))
+ ls->ls_jid = option;
break;
case Opt_id:
/* Obsolete, but left for backward compat purposes */
@@ -1101,6 +1103,24 @@ void gfs2_lm_unmount(struct gfs2_sbd *sdp)
lm->lm_unmount(sdp);
}
+static int gfs2_journalid_wait(void *word)
+{
+ if (signal_pending(current))
+ return -EINTR;
+ schedule();
+ return 0;
+}
+
+static int wait_on_journal(struct gfs2_sbd *sdp)
+{
+ if (sdp->sd_args.ar_spectator)
+ return 0;
+ if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
+ return 0;
+
+ return wait_on_bit(&sdp->sd_flags, SDF_NOJOURNALID, gfs2_journalid_wait, TASK_INTERRUPTIBLE);
+}
+
void gfs2_online_uevent(struct gfs2_sbd *sdp)
{
struct super_block *sb = sdp->sd_vfs;
@@ -1160,7 +1180,7 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent
GFS2_BASIC_BLOCK_SHIFT;
sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
- sdp->sd_tune.gt_log_flush_secs = sdp->sd_args.ar_commit;
+ sdp->sd_tune.gt_logd_secs = sdp->sd_args.ar_commit;
sdp->sd_tune.gt_quota_quantum = sdp->sd_args.ar_quota_quantum;
if (sdp->sd_args.ar_statfs_quantum) {
sdp->sd_tune.gt_statfs_slow = 0;
@@ -1193,6 +1213,10 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent
if (error)
goto fail_locking;
+ error = wait_on_journal(sdp);
+ if (error)
+ goto fail_sb;
+
error = init_inodes(sdp, DO);
if (error)
goto fail_sb;
@@ -1323,7 +1347,7 @@ static int gfs2_get_sb(struct file_system_type *fs_type, int flags,
memset(&args, 0, sizeof(args));
args.ar_quota = GFS2_QUOTA_DEFAULT;
args.ar_data = GFS2_DATA_DEFAULT;
- args.ar_commit = 60;
+ args.ar_commit = 30;
args.ar_statfs_quantum = 30;
args.ar_quota_quantum = 60;
args.ar_errors = GFS2_ERRORS_DEFAULT;
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
index 4e64352d49de..1009be2c9737 100644
--- a/fs/gfs2/ops_inode.c
+++ b/fs/gfs2/ops_inode.c
@@ -1071,6 +1071,9 @@ int gfs2_permission(struct inode *inode, int mask)
return error;
}
+/*
+ * XXX(truncate): the truncate_setsize calls should be moved to the end.
+ */
static int setattr_size(struct inode *inode, struct iattr *attr)
{
struct gfs2_inode *ip = GFS2_I(inode);
@@ -1081,10 +1084,8 @@ static int setattr_size(struct inode *inode, struct iattr *attr)
error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
if (error)
return error;
- error = vmtruncate(inode, attr->ia_size);
+ truncate_setsize(inode, attr->ia_size);
gfs2_trans_end(sdp);
- if (error)
- return error;
}
error = gfs2_truncatei(ip, attr->ia_size);
@@ -1133,8 +1134,16 @@ static int setattr_chown(struct inode *inode, struct iattr *attr)
if (error)
goto out_end_trans;
- error = inode_setattr(inode, attr);
- gfs2_assert_warn(sdp, !error);
+ if ((attr->ia_valid & ATTR_SIZE) &&
+ attr->ia_size != i_size_read(inode)) {
+ int error;
+
+ error = vmtruncate(inode, attr->ia_size);
+ gfs2_assert_warn(sdp, !error);
+ }
+
+ setattr_copy(inode, attr);
+ mark_inode_dirty(inode);
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
gfs2_dinode_out(ip, dibh->b_data);
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index 6dbcbad6ab17..1bc6b5695e6d 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -77,7 +77,7 @@ static LIST_HEAD(qd_lru_list);
static atomic_t qd_lru_count = ATOMIC_INIT(0);
static DEFINE_SPINLOCK(qd_lru_lock);
-int gfs2_shrink_qd_memory(int nr, gfp_t gfp_mask)
+int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
{
struct gfs2_quota_data *qd;
struct gfs2_sbd *sdp;
@@ -637,15 +637,40 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
unsigned blocksize, iblock, pos;
struct buffer_head *bh, *dibh;
struct page *page;
- void *kaddr;
- struct gfs2_quota *qp;
- s64 value;
- int err = -EIO;
+ void *kaddr, *ptr;
+ struct gfs2_quota q, *qp;
+ int err, nbytes;
u64 size;
if (gfs2_is_stuffed(ip))
gfs2_unstuff_dinode(ip, NULL);
-
+
+ memset(&q, 0, sizeof(struct gfs2_quota));
+ err = gfs2_internal_read(ip, NULL, (char *)&q, &loc, sizeof(q));
+ if (err < 0)
+ return err;
+
+ err = -EIO;
+ qp = &q;
+ qp->qu_value = be64_to_cpu(qp->qu_value);
+ qp->qu_value += change;
+ qp->qu_value = cpu_to_be64(qp->qu_value);
+ qd->qd_qb.qb_value = qp->qu_value;
+ if (fdq) {
+ if (fdq->d_fieldmask & FS_DQ_BSOFT) {
+ qp->qu_warn = cpu_to_be64(fdq->d_blk_softlimit);
+ qd->qd_qb.qb_warn = qp->qu_warn;
+ }
+ if (fdq->d_fieldmask & FS_DQ_BHARD) {
+ qp->qu_limit = cpu_to_be64(fdq->d_blk_hardlimit);
+ qd->qd_qb.qb_limit = qp->qu_limit;
+ }
+ }
+
+ /* Write the quota into the quota file on disk */
+ ptr = qp;
+ nbytes = sizeof(struct gfs2_quota);
+get_a_page:
page = grab_cache_page(mapping, index);
if (!page)
return -ENOMEM;
@@ -667,7 +692,10 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
if (!buffer_mapped(bh)) {
gfs2_block_map(inode, iblock, bh, 1);
if (!buffer_mapped(bh))
- goto unlock;
+ goto unlock_out;
+ /* If it's a newly allocated disk block for quota, zero it */
+ if (buffer_new(bh))
+ zero_user(page, pos - blocksize, bh->b_size);
}
if (PageUptodate(page))
@@ -677,32 +705,34 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
ll_rw_block(READ_META, 1, &bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh))
- goto unlock;
+ goto unlock_out;
}
gfs2_trans_add_bh(ip->i_gl, bh, 0);
kaddr = kmap_atomic(page, KM_USER0);
- qp = kaddr + offset;
- value = (s64)be64_to_cpu(qp->qu_value) + change;
- qp->qu_value = cpu_to_be64(value);
- qd->qd_qb.qb_value = qp->qu_value;
- if (fdq) {
- if (fdq->d_fieldmask & FS_DQ_BSOFT) {
- qp->qu_warn = cpu_to_be64(fdq->d_blk_softlimit);
- qd->qd_qb.qb_warn = qp->qu_warn;
- }
- if (fdq->d_fieldmask & FS_DQ_BHARD) {
- qp->qu_limit = cpu_to_be64(fdq->d_blk_hardlimit);
- qd->qd_qb.qb_limit = qp->qu_limit;
- }
- }
+ if (offset + sizeof(struct gfs2_quota) > PAGE_CACHE_SIZE)
+ nbytes = PAGE_CACHE_SIZE - offset;
+ memcpy(kaddr + offset, ptr, nbytes);
flush_dcache_page(page);
kunmap_atomic(kaddr, KM_USER0);
+ unlock_page(page);
+ page_cache_release(page);
+
+ /* If quota straddles page boundary, we need to update the rest of the
+ * quota at the beginning of the next page */
+ if ((offset + sizeof(struct gfs2_quota)) > PAGE_CACHE_SIZE) {
+ ptr = ptr + nbytes;
+ nbytes = sizeof(struct gfs2_quota) - nbytes;
+ offset = 0;
+ index++;
+ goto get_a_page;
+ }
+ /* Update the disk inode timestamp and size (if extended) */
err = gfs2_meta_inode_buffer(ip, &dibh);
if (err)
- goto unlock;
+ goto out;
size = loc + sizeof(struct gfs2_quota);
if (size > inode->i_size) {
@@ -715,7 +745,9 @@ static int gfs2_adjust_quota(struct gfs2_inode *ip, loff_t loc,
brelse(dibh);
mark_inode_dirty(inode);
-unlock:
+out:
+ return err;
+unlock_out:
unlock_page(page);
page_cache_release(page);
return err;
@@ -755,15 +787,9 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
goto out;
for (x = 0; x < num_qd; x++) {
- int alloc_required;
-
offset = qd2offset(qda[x]);
- error = gfs2_write_alloc_required(ip, offset,
- sizeof(struct gfs2_quota),
- &alloc_required);
- if (error)
- goto out_gunlock;
- if (alloc_required)
+ if (gfs2_write_alloc_required(ip, offset,
+ sizeof(struct gfs2_quota)))
nalloc++;
}
@@ -779,8 +805,10 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
* rgrp since it won't be allocated during the transaction
*/
al->al_requested = 1;
- /* +1 in the end for block requested above for unstuffing */
- blocks = num_qd * data_blocks + RES_DINODE + num_qd + 1;
+ /* +3 in the end for unstuffing block, inode size update block
+ * and another block in case quota straddles page boundary and
+ * two blocks need to be updated instead of 1 */
+ blocks = num_qd * data_blocks + RES_DINODE + num_qd + 3;
if (nalloc)
al->al_requested += nalloc * (data_blocks + ind_blocks);
@@ -1418,10 +1446,18 @@ static int gfs2_quota_get_xstate(struct super_block *sb,
memset(fqs, 0, sizeof(struct fs_quota_stat));
fqs->qs_version = FS_QSTAT_VERSION;
- if (sdp->sd_args.ar_quota == GFS2_QUOTA_ON)
- fqs->qs_flags = (XFS_QUOTA_UDQ_ENFD | XFS_QUOTA_GDQ_ENFD);
- else if (sdp->sd_args.ar_quota == GFS2_QUOTA_ACCOUNT)
- fqs->qs_flags = (XFS_QUOTA_UDQ_ACCT | XFS_QUOTA_GDQ_ACCT);
+
+ switch (sdp->sd_args.ar_quota) {
+ case GFS2_QUOTA_ON:
+ fqs->qs_flags |= (FS_QUOTA_UDQ_ENFD | FS_QUOTA_GDQ_ENFD);
+ /*FALLTHRU*/
+ case GFS2_QUOTA_ACCOUNT:
+ fqs->qs_flags |= (FS_QUOTA_UDQ_ACCT | FS_QUOTA_GDQ_ACCT);
+ break;
+ case GFS2_QUOTA_OFF:
+ break;
+ }
+
if (sdp->sd_quota_inode) {
fqs->qs_uquota.qfs_ino = GFS2_I(sdp->sd_quota_inode)->i_no_addr;
fqs->qs_uquota.qfs_nblks = sdp->sd_quota_inode->i_blocks;
@@ -1432,8 +1468,8 @@ static int gfs2_quota_get_xstate(struct super_block *sb,
return 0;
}
-static int gfs2_xquota_get(struct super_block *sb, int type, qid_t id,
- struct fs_disk_quota *fdq)
+static int gfs2_get_dqblk(struct super_block *sb, int type, qid_t id,
+ struct fs_disk_quota *fdq)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_quota_lvb *qlvb;
@@ -1462,7 +1498,7 @@ static int gfs2_xquota_get(struct super_block *sb, int type, qid_t id,
qlvb = (struct gfs2_quota_lvb *)qd->qd_gl->gl_lvb;
fdq->d_version = FS_DQUOT_VERSION;
- fdq->d_flags = (type == QUOTA_USER) ? XFS_USER_QUOTA : XFS_GROUP_QUOTA;
+ fdq->d_flags = (type == QUOTA_USER) ? FS_USER_QUOTA : FS_GROUP_QUOTA;
fdq->d_id = id;
fdq->d_blk_hardlimit = be64_to_cpu(qlvb->qb_limit);
fdq->d_blk_softlimit = be64_to_cpu(qlvb->qb_warn);
@@ -1477,8 +1513,8 @@ out:
/* GFS2 only supports a subset of the XFS fields */
#define GFS2_FIELDMASK (FS_DQ_BSOFT|FS_DQ_BHARD)
-static int gfs2_xquota_set(struct super_block *sb, int type, qid_t id,
- struct fs_disk_quota *fdq)
+static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id,
+ struct fs_disk_quota *fdq)
{
struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_inode *ip = GFS2_I(sdp->sd_quota_inode);
@@ -1497,12 +1533,12 @@ static int gfs2_xquota_set(struct super_block *sb, int type, qid_t id,
switch(type) {
case USRQUOTA:
type = QUOTA_USER;
- if (fdq->d_flags != XFS_USER_QUOTA)
+ if (fdq->d_flags != FS_USER_QUOTA)
return -EINVAL;
break;
case GRPQUOTA:
type = QUOTA_GROUP;
- if (fdq->d_flags != XFS_GROUP_QUOTA)
+ if (fdq->d_flags != FS_GROUP_QUOTA)
return -EINVAL;
break;
default:
@@ -1542,10 +1578,7 @@ static int gfs2_xquota_set(struct super_block *sb, int type, qid_t id,
goto out_i;
offset = qd2offset(qd);
- error = gfs2_write_alloc_required(ip, offset, sizeof(struct gfs2_quota),
- &alloc_required);
- if (error)
- goto out_i;
+ alloc_required = gfs2_write_alloc_required(ip, offset, sizeof(struct gfs2_quota));
if (alloc_required) {
al = gfs2_alloc_get(ip);
if (al == NULL)
@@ -1585,7 +1618,7 @@ out_put:
const struct quotactl_ops gfs2_quotactl_ops = {
.quota_sync = gfs2_quota_sync,
.get_xstate = gfs2_quota_get_xstate,
- .get_xquota = gfs2_xquota_get,
- .set_xquota = gfs2_xquota_set,
+ .get_dqblk = gfs2_get_dqblk,
+ .set_dqblk = gfs2_set_dqblk,
};
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index 195f60c8bd14..e7d236ca48bd 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -51,7 +51,7 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip)
return ret;
}
-extern int gfs2_shrink_qd_memory(int nr, gfp_t gfp_mask);
+extern int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask);
extern const struct quotactl_ops gfs2_quotactl_ops;
#endif /* __QUOTA_DOT_H__ */
diff --git a/fs/gfs2/recovery.c b/fs/gfs2/recovery.c
index 4b9bece3d437..f7f89a94a5a4 100644
--- a/fs/gfs2/recovery.c
+++ b/fs/gfs2/recovery.c
@@ -14,7 +14,6 @@
#include <linux/buffer_head.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
-#include <linux/slow-work.h>
#include "gfs2.h"
#include "incore.h"
@@ -28,6 +27,8 @@
#include "util.h"
#include "dir.h"
+struct workqueue_struct *gfs_recovery_wq;
+
int gfs2_replay_read_block(struct gfs2_jdesc *jd, unsigned int blk,
struct buffer_head **bh)
{
@@ -443,23 +444,7 @@ static void gfs2_recovery_done(struct gfs2_sbd *sdp, unsigned int jid,
kobject_uevent_env(&sdp->sd_kobj, KOBJ_CHANGE, envp);
}
-static int gfs2_recover_get_ref(struct slow_work *work)
-{
- struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
- if (test_and_set_bit(JDF_RECOVERY, &jd->jd_flags))
- return -EBUSY;
- return 0;
-}
-
-static void gfs2_recover_put_ref(struct slow_work *work)
-{
- struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
- clear_bit(JDF_RECOVERY, &jd->jd_flags);
- smp_mb__after_clear_bit();
- wake_up_bit(&jd->jd_flags, JDF_RECOVERY);
-}
-
-static void gfs2_recover_work(struct slow_work *work)
+void gfs2_recover_func(struct work_struct *work)
{
struct gfs2_jdesc *jd = container_of(work, struct gfs2_jdesc, jd_work);
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
@@ -578,7 +563,7 @@ static void gfs2_recover_work(struct slow_work *work)
gfs2_glock_dq_uninit(&j_gh);
fs_info(sdp, "jid=%u: Done\n", jd->jd_jid);
- return;
+ goto done;
fail_gunlock_tr:
gfs2_glock_dq_uninit(&t_gh);
@@ -590,32 +575,35 @@ fail_gunlock_j:
}
fs_info(sdp, "jid=%u: %s\n", jd->jd_jid, (error) ? "Failed" : "Done");
-
fail:
gfs2_recovery_done(sdp, jd->jd_jid, LM_RD_GAVEUP);
+done:
+ clear_bit(JDF_RECOVERY, &jd->jd_flags);
+ smp_mb__after_clear_bit();
+ wake_up_bit(&jd->jd_flags, JDF_RECOVERY);
}
-struct slow_work_ops gfs2_recover_ops = {
- .owner = THIS_MODULE,
- .get_ref = gfs2_recover_get_ref,
- .put_ref = gfs2_recover_put_ref,
- .execute = gfs2_recover_work,
-};
-
-
static int gfs2_recovery_wait(void *word)
{
schedule();
return 0;
}
-int gfs2_recover_journal(struct gfs2_jdesc *jd)
+int gfs2_recover_journal(struct gfs2_jdesc *jd, bool wait)
{
int rv;
- rv = slow_work_enqueue(&jd->jd_work);
- if (rv)
- return rv;
- wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait, TASK_UNINTERRUPTIBLE);
+
+ if (test_and_set_bit(JDF_RECOVERY, &jd->jd_flags))
+ return -EBUSY;
+
+ /* we have JDF_RECOVERY, queue should always succeed */
+ rv = queue_work(gfs_recovery_wq, &jd->jd_work);
+ BUG_ON(!rv);
+
+ if (wait)
+ wait_on_bit(&jd->jd_flags, JDF_RECOVERY, gfs2_recovery_wait,
+ TASK_UNINTERRUPTIBLE);
+
return 0;
}
diff --git a/fs/gfs2/recovery.h b/fs/gfs2/recovery.h
index 1616ac22569a..2226136c7647 100644
--- a/fs/gfs2/recovery.h
+++ b/fs/gfs2/recovery.h
@@ -12,6 +12,8 @@
#include "incore.h"
+extern struct workqueue_struct *gfs_recovery_wq;
+
static inline void gfs2_replay_incr_blk(struct gfs2_sbd *sdp, unsigned int *blk)
{
if (++*blk == sdp->sd_jdesc->jd_blocks)
@@ -27,8 +29,8 @@ extern void gfs2_revoke_clean(struct gfs2_sbd *sdp);
extern int gfs2_find_jhead(struct gfs2_jdesc *jd,
struct gfs2_log_header_host *head);
-extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd);
-extern struct slow_work_ops gfs2_recover_ops;
+extern int gfs2_recover_journal(struct gfs2_jdesc *gfs2_jd, bool wait);
+extern void gfs2_recover_func(struct work_struct *work);
#endif /* __RECOVERY_DOT_H__ */
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 503b842f3ba2..171a744f8e45 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -854,7 +854,8 @@ static void gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
if ((start + nr_sects) != blk) {
rv = blkdev_issue_discard(bdev, start,
nr_sects, GFP_NOFS,
- DISCARD_FL_BARRIER);
+ BLKDEV_IFL_WAIT |
+ BLKDEV_IFL_BARRIER);
if (rv)
goto fail;
nr_sects = 0;
@@ -869,7 +870,7 @@ start_new_extent:
}
if (nr_sects) {
rv = blkdev_issue_discard(bdev, start, nr_sects, GFP_NOFS,
- DISCARD_FL_BARRIER);
+ BLKDEV_IFL_WAIT | BLKDEV_IFL_BARRIER);
if (rv)
goto fail;
}
@@ -948,13 +949,13 @@ static int try_rgrp_fit(struct gfs2_rgrpd *rgd, struct gfs2_alloc *al)
* try_rgrp_unlink - Look for any unlinked, allocated, but unused inodes
* @rgd: The rgrp
*
- * Returns: The inode, if one has been found
+ * Returns: 0 if no error
+ * The inode, if one has been found, in inode.
*/
-static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked,
- u64 skip)
+static u64 try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked,
+ u64 skip)
{
- struct inode *inode;
u32 goal = 0, block;
u64 no_addr;
struct gfs2_sbd *sdp = rgd->rd_sbd;
@@ -979,14 +980,11 @@ static struct inode *try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked,
if (no_addr == skip)
continue;
*last_unlinked = no_addr;
- inode = gfs2_inode_lookup(rgd->rd_sbd->sd_vfs, DT_UNKNOWN,
- no_addr, -1, 1);
- if (!IS_ERR(inode))
- return inode;
+ return no_addr;
}
rgd->rd_flags &= ~GFS2_RDF_CHECK;
- return NULL;
+ return 0;
}
/**
@@ -1067,11 +1065,12 @@ static void forward_rgrp_set(struct gfs2_sbd *sdp, struct gfs2_rgrpd *rgd)
* Try to acquire rgrp in way which avoids contending with others.
*
* Returns: errno
+ * unlinked: the block address of an unlinked block to be reclaimed
*/
-static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
+static int get_local_rgrp(struct gfs2_inode *ip, u64 *unlinked,
+ u64 *last_unlinked)
{
- struct inode *inode = NULL;
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_rgrpd *rgd, *begin = NULL;
struct gfs2_alloc *al = ip->i_alloc;
@@ -1080,6 +1079,7 @@ static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
int loops = 0;
int error, rg_locked;
+ *unlinked = 0;
rgd = gfs2_blk2rgrpd(sdp, ip->i_goal);
while (rgd) {
@@ -1096,19 +1096,24 @@ static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
case 0:
if (try_rgrp_fit(rgd, al))
goto out;
- if (rgd->rd_flags & GFS2_RDF_CHECK)
- inode = try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr);
+ /* If the rg came in already locked, there's no
+ way we can recover from a failed try_rgrp_unlink
+ because that would require an iput which can only
+ happen after the rgrp is unlocked. */
+ if (!rg_locked && rgd->rd_flags & GFS2_RDF_CHECK)
+ *unlinked = try_rgrp_unlink(rgd, last_unlinked,
+ ip->i_no_addr);
if (!rg_locked)
gfs2_glock_dq_uninit(&al->al_rgd_gh);
- if (inode)
- return inode;
+ if (*unlinked)
+ return -EAGAIN;
/* fall through */
case GLR_TRYFAILED:
rgd = recent_rgrp_next(rgd);
break;
default:
- return ERR_PTR(error);
+ return error;
}
}
@@ -1130,12 +1135,13 @@ static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
case 0:
if (try_rgrp_fit(rgd, al))
goto out;
- if (rgd->rd_flags & GFS2_RDF_CHECK)
- inode = try_rgrp_unlink(rgd, last_unlinked, ip->i_no_addr);
+ if (!rg_locked && rgd->rd_flags & GFS2_RDF_CHECK)
+ *unlinked = try_rgrp_unlink(rgd, last_unlinked,
+ ip->i_no_addr);
if (!rg_locked)
gfs2_glock_dq_uninit(&al->al_rgd_gh);
- if (inode)
- return inode;
+ if (*unlinked)
+ return -EAGAIN;
break;
case GLR_TRYFAILED:
@@ -1143,7 +1149,7 @@ static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
break;
default:
- return ERR_PTR(error);
+ return error;
}
rgd = gfs2_rgrpd_get_next(rgd);
@@ -1152,7 +1158,7 @@ static struct inode *get_local_rgrp(struct gfs2_inode *ip, u64 *last_unlinked)
if (rgd == begin) {
if (++loops >= 3)
- return ERR_PTR(-ENOSPC);
+ return -ENOSPC;
if (!skipped)
loops++;
flags = 0;
@@ -1172,7 +1178,7 @@ out:
forward_rgrp_set(sdp, rgd);
}
- return NULL;
+ return 0;
}
/**
@@ -1186,9 +1192,8 @@ int gfs2_inplace_reserve_i(struct gfs2_inode *ip, char *file, unsigned int line)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_alloc *al = ip->i_alloc;
- struct inode *inode;
int error = 0;
- u64 last_unlinked = NO_BLOCK;
+ u64 last_unlinked = NO_BLOCK, unlinked;
if (gfs2_assert_warn(sdp, al->al_requested))
return -EINVAL;
@@ -1204,17 +1209,27 @@ try_again:
if (error)
return error;
- inode = get_local_rgrp(ip, &last_unlinked);
- if (inode) {
+ /* Find an rgrp suitable for allocation. If it encounters any unlinked
+ dinodes along the way, error will equal -EAGAIN and unlinked will
+ contains it block address. We then need to look up that inode and
+ try to free it, and try the allocation again. */
+ error = get_local_rgrp(ip, &unlinked, &last_unlinked);
+ if (error) {
if (ip != GFS2_I(sdp->sd_rindex))
gfs2_glock_dq_uninit(&al->al_ri_gh);
- if (IS_ERR(inode))
- return PTR_ERR(inode);
- iput(inode);
+ if (error != -EAGAIN)
+ return error;
+
+ gfs2_process_unlinked_inode(ip->i_inode.i_sb, unlinked);
+ /* regardless of whether or not gfs2_process_unlinked_inode
+ was successful, we don't want to repeat it again. */
+ last_unlinked = unlinked;
gfs2_log_flush(sdp, NULL);
+ error = 0;
+
goto try_again;
}
-
+ /* no error, so we have the rgrp set in the inode's allocation. */
al->al_file = file;
al->al_line = line;
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index 50aac606b990..77cb9f830ee4 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -342,8 +342,6 @@ int gfs2_jdesc_check(struct gfs2_jdesc *jd)
{
struct gfs2_inode *ip = GFS2_I(jd->jd_inode);
struct gfs2_sbd *sdp = GFS2_SB(jd->jd_inode);
- int ar;
- int error;
if (ip->i_disksize < (8 << 20) || ip->i_disksize > (1 << 30) ||
(ip->i_disksize & (sdp->sd_sb.sb_bsize - 1))) {
@@ -352,13 +350,12 @@ int gfs2_jdesc_check(struct gfs2_jdesc *jd)
}
jd->jd_blocks = ip->i_disksize >> sdp->sd_sb.sb_bsize_shift;
- error = gfs2_write_alloc_required(ip, 0, ip->i_disksize, &ar);
- if (!error && ar) {
+ if (gfs2_write_alloc_required(ip, 0, ip->i_disksize)) {
gfs2_consist_inode(ip);
- error = -EIO;
+ return -EIO;
}
- return error;
+ return 0;
}
/**
@@ -1113,7 +1110,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
int error;
spin_lock(&gt->gt_spin);
- args.ar_commit = gt->gt_log_flush_secs;
+ args.ar_commit = gt->gt_logd_secs;
args.ar_quota_quantum = gt->gt_quota_quantum;
if (gt->gt_statfs_slow)
args.ar_statfs_quantum = 0;
@@ -1160,7 +1157,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
else
clear_bit(SDF_NOBARRIERS, &sdp->sd_flags);
spin_lock(&gt->gt_spin);
- gt->gt_log_flush_secs = args.ar_commit;
+ gt->gt_logd_secs = args.ar_commit;
gt->gt_quota_quantum = args.ar_quota_quantum;
if (args.ar_statfs_quantum) {
gt->gt_statfs_slow = 0;
@@ -1191,7 +1188,7 @@ static int gfs2_remount_fs(struct super_block *sb, int *flags, char *data)
* node for later deallocation.
*/
-static void gfs2_drop_inode(struct inode *inode)
+static int gfs2_drop_inode(struct inode *inode)
{
struct gfs2_inode *ip = GFS2_I(inode);
@@ -1200,26 +1197,7 @@ static void gfs2_drop_inode(struct inode *inode)
if (gl && test_bit(GLF_DEMOTE, &gl->gl_flags))
clear_nlink(inode);
}
- generic_drop_inode(inode);
-}
-
-/**
- * gfs2_clear_inode - Deallocate an inode when VFS is done with it
- * @inode: The VFS inode
- *
- */
-
-static void gfs2_clear_inode(struct inode *inode)
-{
- struct gfs2_inode *ip = GFS2_I(inode);
-
- ip->i_gl->gl_object = NULL;
- gfs2_glock_put(ip->i_gl);
- ip->i_gl = NULL;
- if (ip->i_iopen_gh.gh_gl) {
- ip->i_iopen_gh.gh_gl->gl_object = NULL;
- gfs2_glock_dq_uninit(&ip->i_iopen_gh);
- }
+ return generic_drop_inode(inode);
}
static int is_ancestor(const struct dentry *d1, const struct dentry *d2)
@@ -1305,8 +1283,8 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
}
if (args->ar_discard)
seq_printf(s, ",discard");
- val = sdp->sd_tune.gt_log_flush_secs;
- if (val != 60)
+ val = sdp->sd_tune.gt_logd_secs;
+ if (val != 30)
seq_printf(s, ",commit=%d", val);
val = sdp->sd_tune.gt_statfs_quantum;
if (val != 30)
@@ -1334,7 +1312,8 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
}
if (test_bit(SDF_NOBARRIERS, &sdp->sd_flags))
seq_printf(s, ",nobarrier");
-
+ if (test_bit(SDF_DEMOTE, &sdp->sd_flags))
+ seq_printf(s, ",demote_interface_used");
return 0;
}
@@ -1346,13 +1325,16 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
* is safe, just less efficient.
*/
-static void gfs2_delete_inode(struct inode *inode)
+static void gfs2_evict_inode(struct inode *inode)
{
struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int error;
+ if (inode->i_nlink)
+ goto out;
+
error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
if (unlikely(error)) {
gfs2_glock_dq_uninit(&ip->i_iopen_gh);
@@ -1406,10 +1388,18 @@ out_unlock:
gfs2_holder_uninit(&ip->i_iopen_gh);
gfs2_glock_dq_uninit(&gh);
if (error && error != GLR_TRYFAILED && error != -EROFS)
- fs_warn(sdp, "gfs2_delete_inode: %d\n", error);
+ fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
out:
truncate_inode_pages(&inode->i_data, 0);
- clear_inode(inode);
+ end_writeback(inode);
+
+ ip->i_gl->gl_object = NULL;
+ gfs2_glock_put(ip->i_gl);
+ ip->i_gl = NULL;
+ if (ip->i_iopen_gh.gh_gl) {
+ ip->i_iopen_gh.gh_gl->gl_object = NULL;
+ gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+ }
}
static struct inode *gfs2_alloc_inode(struct super_block *sb)
@@ -1433,14 +1423,13 @@ const struct super_operations gfs2_super_ops = {
.alloc_inode = gfs2_alloc_inode,
.destroy_inode = gfs2_destroy_inode,
.write_inode = gfs2_write_inode,
- .delete_inode = gfs2_delete_inode,
+ .evict_inode = gfs2_evict_inode,
.put_super = gfs2_put_super,
.sync_fs = gfs2_sync_fs,
.freeze_fs = gfs2_freeze,
.unfreeze_fs = gfs2_unfreeze,
.statfs = gfs2_statfs,
.remount_fs = gfs2_remount_fs,
- .clear_inode = gfs2_clear_inode,
.drop_inode = gfs2_drop_inode,
.show_options = gfs2_show_options,
};
diff --git a/fs/gfs2/super.h b/fs/gfs2/super.h
index 3df60f2d84e3..a0464680af0b 100644
--- a/fs/gfs2/super.h
+++ b/fs/gfs2/super.h
@@ -54,7 +54,7 @@ extern struct file_system_type gfs2meta_fs_type;
extern const struct export_operations gfs2_export_ops;
extern const struct super_operations gfs2_super_ops;
extern const struct dentry_operations gfs2_dops;
-extern struct xattr_handler *gfs2_xattr_handlers[];
+extern const struct xattr_handler *gfs2_xattr_handlers[];
#endif /* __SUPER_DOT_H__ */
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 54fd98425991..ccacffd2faaa 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -25,6 +25,7 @@
#include "quota.h"
#include "util.h"
#include "glops.h"
+#include "recovery.h"
struct gfs2_attr {
struct attribute attr;
@@ -232,6 +233,8 @@ static ssize_t demote_rq_store(struct gfs2_sbd *sdp, const char *buf, size_t len
glops = gfs2_glops_list[gltype];
if (glops == NULL)
return -EINVAL;
+ if (!test_and_set_bit(SDF_DEMOTE, &sdp->sd_flags))
+ fs_info(sdp, "demote interface used\n");
rv = gfs2_glock_get(sdp, glnum, glops, 0, &gl);
if (rv)
return rv;
@@ -323,6 +326,30 @@ static ssize_t lkfirst_show(struct gfs2_sbd *sdp, char *buf)
return sprintf(buf, "%d\n", ls->ls_first);
}
+static ssize_t lkfirst_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+ unsigned first;
+ int rv;
+
+ rv = sscanf(buf, "%u", &first);
+ if (rv != 1 || first > 1)
+ return -EINVAL;
+ spin_lock(&sdp->sd_jindex_spin);
+ rv = -EBUSY;
+ if (test_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0)
+ goto out;
+ rv = -EINVAL;
+ if (sdp->sd_args.ar_spectator)
+ goto out;
+ if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
+ goto out;
+ sdp->sd_lockstruct.ls_first = first;
+ rv = 0;
+out:
+ spin_unlock(&sdp->sd_jindex_spin);
+ return rv ? rv : len;
+}
+
static ssize_t first_done_show(struct gfs2_sbd *sdp, char *buf)
{
struct lm_lockstruct *ls = &sdp->sd_lockstruct;
@@ -350,7 +377,7 @@ static ssize_t recover_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
list_for_each_entry(jd, &sdp->sd_jindex_list, jd_list) {
if (jd->jd_jid != jid)
continue;
- rv = slow_work_enqueue(&jd->jd_work);
+ rv = gfs2_recover_journal(jd, false);
break;
}
out:
@@ -375,14 +402,41 @@ static ssize_t jid_show(struct gfs2_sbd *sdp, char *buf)
return sprintf(buf, "%u\n", sdp->sd_lockstruct.ls_jid);
}
+static ssize_t jid_store(struct gfs2_sbd *sdp, const char *buf, size_t len)
+{
+ unsigned jid;
+ int rv;
+
+ rv = sscanf(buf, "%u", &jid);
+ if (rv != 1)
+ return -EINVAL;
+
+ spin_lock(&sdp->sd_jindex_spin);
+ rv = -EINVAL;
+ if (sdp->sd_args.ar_spectator)
+ goto out;
+ if (sdp->sd_lockstruct.ls_ops->lm_mount == NULL)
+ goto out;
+ rv = -EBUSY;
+ if (test_and_clear_bit(SDF_NOJOURNALID, &sdp->sd_flags) == 0)
+ goto out;
+ sdp->sd_lockstruct.ls_jid = jid;
+ smp_mb__after_clear_bit();
+ wake_up_bit(&sdp->sd_flags, SDF_NOJOURNALID);
+ rv = 0;
+out:
+ spin_unlock(&sdp->sd_jindex_spin);
+ return rv ? rv : len;
+}
+
#define GDLM_ATTR(_name,_mode,_show,_store) \
static struct gfs2_attr gdlm_attr_##_name = __ATTR(_name,_mode,_show,_store)
GDLM_ATTR(proto_name, 0444, proto_name_show, NULL);
GDLM_ATTR(block, 0644, block_show, block_store);
GDLM_ATTR(withdraw, 0644, withdraw_show, withdraw_store);
-GDLM_ATTR(jid, 0444, jid_show, NULL);
-GDLM_ATTR(first, 0444, lkfirst_show, NULL);
+GDLM_ATTR(jid, 0644, jid_show, jid_store);
+GDLM_ATTR(first, 0644, lkfirst_show, lkfirst_store);
GDLM_ATTR(first_done, 0444, first_done_show, NULL);
GDLM_ATTR(recover, 0600, NULL, recover_store);
GDLM_ATTR(recover_done, 0444, recover_done_show, NULL);
@@ -468,8 +522,6 @@ static ssize_t name##_store(struct gfs2_sbd *sdp, const char *buf, size_t len)\
} \
TUNE_ATTR_2(name, name##_store)
-TUNE_ATTR(incore_log_blocks, 0);
-TUNE_ATTR(log_flush_secs, 0);
TUNE_ATTR(quota_warn_period, 0);
TUNE_ATTR(quota_quantum, 0);
TUNE_ATTR(max_readahead, 0);
@@ -481,8 +533,6 @@ TUNE_ATTR(statfs_quantum, 1);
TUNE_ATTR_3(quota_scale, quota_scale_show, quota_scale_store);
static struct attribute *tune_attrs[] = {
- &tune_attr_incore_log_blocks.attr,
- &tune_attr_log_flush_secs.attr,
&tune_attr_quota_warn_period.attr,
&tune_attr_quota_quantum.attr,
&tune_attr_max_readahead.attr,
@@ -566,7 +616,7 @@ static int gfs2_uevent(struct kset *kset, struct kobject *kobj,
add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name);
add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name);
- if (!sdp->sd_args.ar_spectator)
+ if (!test_bit(SDF_NOJOURNALID, &sdp->sd_flags))
add_uevent_var(env, "JOURNALID=%u", sdp->sd_lockstruct.ls_jid);
if (gfs2_uuid_valid(uuid))
add_uevent_var(env, "UUID=%pUB", uuid);
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 4ef0e9fa3549..9ec73a854111 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -23,6 +23,7 @@
#include "meta_io.h"
#include "trans.h"
#include "util.h"
+#include "trace_gfs2.h"
int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
unsigned int revokes)
@@ -75,6 +76,23 @@ fail_holder_uninit:
return error;
}
+/**
+ * gfs2_log_release - Release a given number of log blocks
+ * @sdp: The GFS2 superblock
+ * @blks: The number of blocks
+ *
+ */
+
+static void gfs2_log_release(struct gfs2_sbd *sdp, unsigned int blks)
+{
+
+ atomic_add(blks, &sdp->sd_log_blks_free);
+ trace_gfs2_log_blocks(sdp, blks);
+ gfs2_assert_withdraw(sdp, atomic_read(&sdp->sd_log_blks_free) <=
+ sdp->sd_jdesc->jd_blocks);
+ up_read(&sdp->sd_log_flush_lock);
+}
+
void gfs2_trans_end(struct gfs2_sbd *sdp)
{
struct gfs2_trans *tr = current->journal_info;
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index c2ebdf2c01d4..776af6eb4bcb 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -1296,6 +1296,7 @@ fail:
int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
{
+ struct inode *inode = &ip->i_inode;
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_ea_location el;
struct buffer_head *dibh;
@@ -1321,14 +1322,25 @@ int gfs2_xattr_acl_chmod(struct gfs2_inode *ip, struct iattr *attr, char *data)
return error;
error = gfs2_meta_inode_buffer(ip, &dibh);
- if (!error) {
- error = inode_setattr(&ip->i_inode, attr);
- gfs2_assert_warn(GFS2_SB(&ip->i_inode), !error);
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
- gfs2_dinode_out(ip, dibh->b_data);
- brelse(dibh);
+ if (error)
+ goto out_trans_end;
+
+ if ((attr->ia_valid & ATTR_SIZE) &&
+ attr->ia_size != i_size_read(inode)) {
+ int error;
+
+ error = vmtruncate(inode, attr->ia_size);
+ gfs2_assert_warn(GFS2_SB(inode), !error);
}
+ setattr_copy(inode, attr);
+ mark_inode_dirty(inode);
+
+ gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_dinode_out(ip, dibh->b_data);
+ brelse(dibh);
+
+out_trans_end:
gfs2_trans_end(sdp);
return error;
}
@@ -1535,21 +1547,21 @@ out_alloc:
return error;
}
-static struct xattr_handler gfs2_xattr_user_handler = {
+static const struct xattr_handler gfs2_xattr_user_handler = {
.prefix = XATTR_USER_PREFIX,
.flags = GFS2_EATYPE_USR,
.get = gfs2_xattr_get,
.set = gfs2_xattr_set,
};
-static struct xattr_handler gfs2_xattr_security_handler = {
+static const struct xattr_handler gfs2_xattr_security_handler = {
.prefix = XATTR_SECURITY_PREFIX,
.flags = GFS2_EATYPE_SECURITY,
.get = gfs2_xattr_get,
.set = gfs2_xattr_set,
};
-struct xattr_handler *gfs2_xattr_handlers[] = {
+const struct xattr_handler *gfs2_xattr_handlers[] = {
&gfs2_xattr_user_handler,
&gfs2_xattr_security_handler,
&gfs2_xattr_system_handler,
OpenPOWER on IntegriCloud