summaryrefslogtreecommitdiffstats
path: root/fs/gfs2
diff options
context:
space:
mode:
Diffstat (limited to 'fs/gfs2')
-rw-r--r--fs/gfs2/Makefile6
-rw-r--r--fs/gfs2/acl.c7
-rw-r--r--fs/gfs2/aops.c14
-rw-r--r--fs/gfs2/bmap.c24
-rw-r--r--fs/gfs2/dentry.c2
-rw-r--r--fs/gfs2/dir.c199
-rw-r--r--fs/gfs2/dir.h4
-rw-r--r--fs/gfs2/export.c10
-rw-r--r--fs/gfs2/file.c181
-rw-r--r--fs/gfs2/glock.c463
-rw-r--r--fs/gfs2/glock.h38
-rw-r--r--fs/gfs2/glops.c203
-rw-r--r--fs/gfs2/glops.h2
-rw-r--r--fs/gfs2/incore.h15
-rw-r--r--fs/gfs2/inode.c1567
-rw-r--r--fs/gfs2/inode.h11
-rw-r--r--fs/gfs2/lock_dlm.c14
-rw-r--r--fs/gfs2/log.c228
-rw-r--r--fs/gfs2/log.h2
-rw-r--r--fs/gfs2/lops.c55
-rw-r--r--fs/gfs2/main.c20
-rw-r--r--fs/gfs2/meta_io.c7
-rw-r--r--fs/gfs2/meta_io.h2
-rw-r--r--fs/gfs2/ops_fstype.c45
-rw-r--r--fs/gfs2/ops_inode.c1344
-rw-r--r--fs/gfs2/quota.c26
-rw-r--r--fs/gfs2/quota.h4
-rw-r--r--fs/gfs2/rgrp.c62
-rw-r--r--fs/gfs2/rgrp.h2
-rw-r--r--fs/gfs2/super.c154
-rw-r--r--fs/gfs2/sys.c6
-rw-r--r--fs/gfs2/trace_gfs2.h38
32 files changed, 2333 insertions, 2422 deletions
diff --git a/fs/gfs2/Makefile b/fs/gfs2/Makefile
index 21f7e46da4c..86128202384 100644
--- a/fs/gfs2/Makefile
+++ b/fs/gfs2/Makefile
@@ -1,9 +1,9 @@
-EXTRA_CFLAGS := -I$(src)
+ccflags-y := -I$(src)
obj-$(CONFIG_GFS2_FS) += gfs2.o
gfs2-y := acl.o bmap.o dir.o xattr.o glock.o \
- glops.o inode.o log.o lops.o main.o meta_io.o \
+ glops.o log.o lops.o main.o meta_io.o \
aops.o dentry.o export.o file.o \
- ops_fstype.o ops_inode.o quota.o \
+ ops_fstype.o inode.o quota.o \
recovery.o rgrp.o super.o sys.o trans.o util.o
gfs2-$(CONFIG_GFS2_FS_LOCKING_DLM) += lock_dlm.o
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 7118f1a780a..cbc07155b1a 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -80,8 +80,11 @@ int gfs2_check_acl(struct inode *inode, int mask, unsigned int flags)
struct posix_acl *acl;
int error;
- if (flags & IPERM_FLAG_RCU)
- return -ECHILD;
+ if (flags & IPERM_FLAG_RCU) {
+ if (!negative_cached_acl(inode, ACL_TYPE_ACCESS))
+ return -ECHILD;
+ return -EAGAIN;
+ }
acl = gfs2_acl_get(GFS2_I(inode), ACL_TYPE_ACCESS);
if (IS_ERR(acl))
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 4f36f8832b9..802ac5eeba2 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -695,6 +695,7 @@ out:
if (error == 0)
return 0;
+ unlock_page(page);
page_cache_release(page);
gfs2_trans_end(sdp);
@@ -883,8 +884,8 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
}
brelse(dibh);
- gfs2_trans_end(sdp);
failed:
+ gfs2_trans_end(sdp);
if (al) {
gfs2_inplace_release(ip);
gfs2_quota_unlock(ip);
@@ -1075,8 +1076,8 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
bd = bh->b_private;
if (bd && bd->bd_ail)
goto cannot_release;
- gfs2_assert_warn(sdp, !buffer_pinned(bh));
- gfs2_assert_warn(sdp, !buffer_dirty(bh));
+ if (buffer_pinned(bh) || buffer_dirty(bh))
+ goto not_possible;
bh = bh->b_this_page;
} while(bh != head);
gfs2_log_unlock(sdp);
@@ -1106,6 +1107,10 @@ int gfs2_releasepage(struct page *page, gfp_t gfp_mask)
} while (bh != head);
return try_to_free_buffers(page);
+
+not_possible: /* Should never happen */
+ WARN_ON(buffer_dirty(bh));
+ WARN_ON(buffer_pinned(bh));
cannot_release:
gfs2_log_unlock(sdp);
return 0;
@@ -1116,7 +1121,6 @@ static const struct address_space_operations gfs2_writeback_aops = {
.writepages = gfs2_writeback_writepages,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
- .sync_page = block_sync_page,
.write_begin = gfs2_write_begin,
.write_end = gfs2_write_end,
.bmap = gfs2_bmap,
@@ -1132,7 +1136,6 @@ static const struct address_space_operations gfs2_ordered_aops = {
.writepage = gfs2_ordered_writepage,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
- .sync_page = block_sync_page,
.write_begin = gfs2_write_begin,
.write_end = gfs2_write_end,
.set_page_dirty = gfs2_set_page_dirty,
@@ -1150,7 +1153,6 @@ static const struct address_space_operations gfs2_jdata_aops = {
.writepages = gfs2_jdata_writepages,
.readpage = gfs2_readpage,
.readpages = gfs2_readpages,
- .sync_page = block_sync_page,
.write_begin = gfs2_write_begin,
.write_end = gfs2_write_end,
.set_page_dirty = gfs2_set_page_dirty,
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 3c4039d5eef..e65493a8ac0 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -21,6 +21,7 @@
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
+#include "super.h"
#include "trans.h"
#include "dir.h"
#include "util.h"
@@ -757,7 +758,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_rgrp_list rlist;
u64 bn, bstart;
- u32 blen;
+ u32 blen, btotal;
__be64 *p;
unsigned int rg_blocks = 0;
int metadata;
@@ -779,6 +780,8 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
metadata = (height != ip->i_height - 1);
if (metadata)
revokes = (height) ? sdp->sd_inptrs : sdp->sd_diptrs;
+ else if (ip->i_depth)
+ revokes = sdp->sd_inptrs;
if (ip != GFS2_I(sdp->sd_rindex))
error = gfs2_rindex_hold(sdp, &ip->i_alloc->al_ri_gh);
@@ -839,6 +842,7 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
bstart = 0;
blen = 0;
+ btotal = 0;
for (p = top; p < bottom; p++) {
if (!*p)
@@ -851,9 +855,11 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
else {
if (bstart) {
if (metadata)
- gfs2_free_meta(ip, bstart, blen);
+ __gfs2_free_meta(ip, bstart, blen);
else
- gfs2_free_data(ip, bstart, blen);
+ __gfs2_free_data(ip, bstart, blen);
+
+ btotal += blen;
}
bstart = bn;
@@ -865,11 +871,17 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
}
if (bstart) {
if (metadata)
- gfs2_free_meta(ip, bstart, blen);
+ __gfs2_free_meta(ip, bstart, blen);
else
- gfs2_free_data(ip, bstart, blen);
+ __gfs2_free_data(ip, bstart, blen);
+
+ btotal += blen;
}
+ gfs2_statfs_change(sdp, 0, +btotal, 0);
+ gfs2_quota_change(ip, -(s64)btotal, ip->i_inode.i_uid,
+ ip->i_inode.i_gid);
+
ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
gfs2_dinode_out(ip, dibh->b_data);
@@ -1126,7 +1138,7 @@ void gfs2_trim_blocks(struct inode *inode)
* earlier versions of GFS2 have a bug in the stuffed file reading
* code which will result in a buffer overrun if the size is larger
* than the max stuffed file size. In order to prevent this from
- * occuring, such files are unstuffed, but in other cases we can
+ * occurring, such files are unstuffed, but in other cases we can
* just update the inode size directly.
*
* Returns: 0 on success, or -ve on error
diff --git a/fs/gfs2/dentry.c b/fs/gfs2/dentry.c
index 4a456338b87..0da8da2c991 100644
--- a/fs/gfs2/dentry.c
+++ b/fs/gfs2/dentry.c
@@ -44,7 +44,7 @@ static int gfs2_drevalidate(struct dentry *dentry, struct nameidata *nd)
int error;
int had_lock = 0;
- if (nd->flags & LOOKUP_RCU)
+ if (nd && nd->flags & LOOKUP_RCU)
return -ECHILD;
parent = dget_parent(dentry);
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 5c356d09c32..091ee477953 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -82,12 +82,9 @@
struct qstr gfs2_qdot __read_mostly;
struct qstr gfs2_qdotdot __read_mostly;
-typedef int (*leaf_call_t) (struct gfs2_inode *dip, u32 index, u32 len,
- u64 leaf_no, void *data);
typedef int (*gfs2_dscan_t)(const struct gfs2_dirent *dent,
const struct qstr *name, void *opaque);
-
int gfs2_dir_get_new_buffer(struct gfs2_inode *ip, u64 block,
struct buffer_head **bhp)
{
@@ -1506,7 +1503,7 @@ 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));
+ be64_to_cpu(dent->de_inum.no_formal_ino), 0);
brelse(bh);
return inode;
}
@@ -1600,7 +1597,7 @@ static int dir_new_leaf(struct inode *inode, const struct qstr *name)
*/
int gfs2_dir_add(struct inode *inode, const struct qstr *name,
- const struct gfs2_inode *nip, unsigned type)
+ const struct gfs2_inode *nip)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct buffer_head *bh;
@@ -1616,7 +1613,7 @@ int gfs2_dir_add(struct inode *inode, const struct qstr *name,
return PTR_ERR(dent);
dent = gfs2_init_dirent(inode, dent, name, bh);
gfs2_inum_out(nip, dent);
- dent->de_type = cpu_to_be16(type);
+ dent->de_type = cpu_to_be16(IF2DT(nip->i_inode.i_mode));
if (ip->i_diskflags & GFS2_DIF_EXHASH) {
leaf = (struct gfs2_leaf *)bh->b_data;
be16_add_cpu(&leaf->lf_entries, 1);
@@ -1628,6 +1625,8 @@ int gfs2_dir_add(struct inode *inode, const struct qstr *name,
gfs2_trans_add_bh(ip->i_gl, bh, 1);
ip->i_entries++;
ip->i_inode.i_mtime = ip->i_inode.i_ctime = CURRENT_TIME;
+ if (S_ISDIR(nip->i_inode.i_mode))
+ inc_nlink(&ip->i_inode);
gfs2_dinode_out(ip, bh->b_data);
brelse(bh);
error = 0;
@@ -1672,8 +1671,9 @@ int gfs2_dir_add(struct inode *inode, const struct qstr *name,
* Returns: 0 on success, error code on failure
*/
-int gfs2_dir_del(struct gfs2_inode *dip, const struct qstr *name)
+int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry)
{
+ const struct qstr *name = &dentry->d_name;
struct gfs2_dirent *dent, *prev = NULL;
struct buffer_head *bh;
int error;
@@ -1714,6 +1714,8 @@ int gfs2_dir_del(struct gfs2_inode *dip, const struct qstr *name)
gfs2_trans_add_bh(dip->i_gl, bh, 1);
dip->i_entries--;
dip->i_inode.i_mtime = dip->i_inode.i_ctime = CURRENT_TIME;
+ if (S_ISDIR(dentry->d_inode->i_mode))
+ drop_nlink(&dip->i_inode);
gfs2_dinode_out(dip, bh->b_data);
brelse(bh);
mark_inode_dirty(&dip->i_inode);
@@ -1768,94 +1770,20 @@ int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
}
/**
- * foreach_leaf - call a function for each leaf in a directory
- * @dip: the directory
- * @lc: the function to call for each each
- * @data: private data to pass to it
- *
- * Returns: errno
- */
-
-static int foreach_leaf(struct gfs2_inode *dip, leaf_call_t lc, void *data)
-{
- struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
- struct buffer_head *bh;
- struct gfs2_leaf *leaf;
- u32 hsize, len;
- u32 ht_offset, lp_offset, ht_offset_cur = -1;
- u32 index = 0;
- __be64 *lp;
- u64 leaf_no;
- int error = 0;
-
- hsize = 1 << dip->i_depth;
- if (hsize * sizeof(u64) != i_size_read(&dip->i_inode)) {
- gfs2_consist_inode(dip);
- return -EIO;
- }
-
- lp = kmalloc(sdp->sd_hash_bsize, GFP_NOFS);
- if (!lp)
- return -ENOMEM;
-
- while (index < hsize) {
- lp_offset = index & (sdp->sd_hash_ptrs - 1);
- ht_offset = index - lp_offset;
-
- if (ht_offset_cur != ht_offset) {
- error = gfs2_dir_read_data(dip, (char *)lp,
- ht_offset * sizeof(__be64),
- sdp->sd_hash_bsize, 1);
- if (error != sdp->sd_hash_bsize) {
- if (error >= 0)
- error = -EIO;
- goto out;
- }
- ht_offset_cur = ht_offset;
- }
-
- leaf_no = be64_to_cpu(lp[lp_offset]);
- if (leaf_no) {
- error = get_leaf(dip, leaf_no, &bh);
- if (error)
- goto out;
- leaf = (struct gfs2_leaf *)bh->b_data;
- len = 1 << (dip->i_depth - be16_to_cpu(leaf->lf_depth));
- brelse(bh);
-
- error = lc(dip, index, len, leaf_no, data);
- if (error)
- goto out;
-
- index = (index & ~(len - 1)) + len;
- } else
- index++;
- }
-
- if (index != hsize) {
- gfs2_consist_inode(dip);
- error = -EIO;
- }
-
-out:
- kfree(lp);
-
- return error;
-}
-
-/**
* leaf_dealloc - Deallocate a directory leaf
* @dip: the directory
* @index: the hash table offset in the directory
* @len: the number of pointers to this leaf
* @leaf_no: the leaf number
- * @data: not used
+ * @leaf_bh: buffer_head for the starting leaf
+ * last_dealloc: 1 if this is the final dealloc for the leaf, else 0
*
* Returns: errno
*/
static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
- u64 leaf_no, void *data)
+ u64 leaf_no, struct buffer_head *leaf_bh,
+ int last_dealloc)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_leaf *tmp_leaf;
@@ -1887,14 +1815,18 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
goto out_qs;
/* Count the number of leaves */
+ bh = leaf_bh;
for (blk = leaf_no; blk; blk = nblk) {
- error = get_leaf(dip, blk, &bh);
- if (error)
- goto out_rlist;
+ if (blk != leaf_no) {
+ error = get_leaf(dip, blk, &bh);
+ if (error)
+ goto out_rlist;
+ }
tmp_leaf = (struct gfs2_leaf *)bh->b_data;
nblk = be64_to_cpu(tmp_leaf->lf_next);
- brelse(bh);
+ if (blk != leaf_no)
+ brelse(bh);
gfs2_rlist_add(sdp, &rlist, blk);
l_blocks++;
@@ -1918,13 +1850,18 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
if (error)
goto out_rg_gunlock;
+ bh = leaf_bh;
+
for (blk = leaf_no; blk; blk = nblk) {
- error = get_leaf(dip, blk, &bh);
- if (error)
- goto out_end_trans;
+ if (blk != leaf_no) {
+ error = get_leaf(dip, blk, &bh);
+ if (error)
+ goto out_end_trans;
+ }
tmp_leaf = (struct gfs2_leaf *)bh->b_data;
nblk = be64_to_cpu(tmp_leaf->lf_next);
- brelse(bh);
+ if (blk != leaf_no)
+ brelse(bh);
gfs2_free_meta(dip, blk, 1);
gfs2_add_inode_blocks(&dip->i_inode, -1);
@@ -1942,6 +1879,10 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
goto out_end_trans;
gfs2_trans_add_bh(dip->i_gl, dibh, 1);
+ /* On the last dealloc, make this a regular file in case we crash.
+ (We don't want to free these blocks a second time.) */
+ if (last_dealloc)
+ dip->i_inode.i_mode = S_IFREG;
gfs2_dinode_out(dip, dibh->b_data);
brelse(dibh);
@@ -1975,29 +1916,67 @@ int gfs2_dir_exhash_dealloc(struct gfs2_inode *dip)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct buffer_head *bh;
- int error;
+ struct gfs2_leaf *leaf;
+ u32 hsize, len;
+ u32 ht_offset, lp_offset, ht_offset_cur = -1;
+ u32 index = 0, next_index;
+ __be64 *lp;
+ u64 leaf_no;
+ int error = 0, last;
- /* Dealloc on-disk leaves to FREEMETA state */
- error = foreach_leaf(dip, leaf_dealloc, NULL);
- if (error)
- return error;
+ hsize = 1 << dip->i_depth;
+ if (hsize * sizeof(u64) != i_size_read(&dip->i_inode)) {
+ gfs2_consist_inode(dip);
+ return -EIO;
+ }
- /* Make this a regular file in case we crash.
- (We don't want to free these blocks a second time.) */
+ lp = kmalloc(sdp->sd_hash_bsize, GFP_NOFS);
+ if (!lp)
+ return -ENOMEM;
- error = gfs2_trans_begin(sdp, RES_DINODE, 0);
- if (error)
- return error;
+ while (index < hsize) {
+ lp_offset = index & (sdp->sd_hash_ptrs - 1);
+ ht_offset = index - lp_offset;
- error = gfs2_meta_inode_buffer(dip, &bh);
- if (!error) {
- gfs2_trans_add_bh(dip->i_gl, bh, 1);
- ((struct gfs2_dinode *)bh->b_data)->di_mode =
- cpu_to_be32(S_IFREG);
- brelse(bh);
+ if (ht_offset_cur != ht_offset) {
+ error = gfs2_dir_read_data(dip, (char *)lp,
+ ht_offset * sizeof(__be64),
+ sdp->sd_hash_bsize, 1);
+ if (error != sdp->sd_hash_bsize) {
+ if (error >= 0)
+ error = -EIO;
+ goto out;
+ }
+ ht_offset_cur = ht_offset;
+ }
+
+ leaf_no = be64_to_cpu(lp[lp_offset]);
+ if (leaf_no) {
+ error = get_leaf(dip, leaf_no, &bh);
+ if (error)
+ goto out;
+ leaf = (struct gfs2_leaf *)bh->b_data;
+ len = 1 << (dip->i_depth - be16_to_cpu(leaf->lf_depth));
+
+ next_index = (index & ~(len - 1)) + len;
+ last = ((next_index >= hsize) ? 1 : 0);
+ error = leaf_dealloc(dip, index, len, leaf_no, bh,
+ last);
+ brelse(bh);
+ if (error)
+ goto out;
+ index = next_index;
+ } else
+ index++;
}
- gfs2_trans_end(sdp);
+ if (index != hsize) {
+ gfs2_consist_inode(dip);
+ error = -EIO;
+ }
+
+out:
+ kfree(lp);
return error;
}
diff --git a/fs/gfs2/dir.h b/fs/gfs2/dir.h
index a98f644bd3d..e686af11bec 100644
--- a/fs/gfs2/dir.h
+++ b/fs/gfs2/dir.h
@@ -22,8 +22,8 @@ extern struct inode *gfs2_dir_search(struct inode *dir,
extern int gfs2_dir_check(struct inode *dir, const struct qstr *filename,
const struct gfs2_inode *ip);
extern int gfs2_dir_add(struct inode *inode, const struct qstr *filename,
- const struct gfs2_inode *ip, unsigned int type);
-extern int gfs2_dir_del(struct gfs2_inode *dip, const struct qstr *filename);
+ const struct gfs2_inode *ip);
+extern int gfs2_dir_del(struct gfs2_inode *dip, const struct dentry *dentry);
extern int gfs2_dir_read(struct inode *inode, u64 *offset, void *opaque,
filldir_t filldir);
extern int gfs2_dir_mvino(struct gfs2_inode *dip, const struct qstr *filename,
diff --git a/fs/gfs2/export.c b/fs/gfs2/export.c
index 9023db8184f..fe9945f2ff7 100644
--- a/fs/gfs2/export.c
+++ b/fs/gfs2/export.c
@@ -36,9 +36,13 @@ static int gfs2_encode_fh(struct dentry *dentry, __u32 *p, int *len,
struct super_block *sb = inode->i_sb;
struct gfs2_inode *ip = GFS2_I(inode);
- if (*len < GFS2_SMALL_FH_SIZE ||
- (connectable && *len < GFS2_LARGE_FH_SIZE))
+ if (connectable && (*len < GFS2_LARGE_FH_SIZE)) {
+ *len = GFS2_LARGE_FH_SIZE;
return 255;
+ } else if (*len < GFS2_SMALL_FH_SIZE) {
+ *len = GFS2_SMALL_FH_SIZE;
+ return 255;
+ }
fh[0] = cpu_to_be32(ip->i_no_formal_ino >> 32);
fh[1] = cpu_to_be32(ip->i_no_formal_ino & 0xFFFFFFFF);
@@ -135,7 +139,7 @@ static struct dentry *gfs2_get_dentry(struct super_block *sb,
struct gfs2_sbd *sdp = sb->s_fs_info;
struct inode *inode;
- inode = gfs2_ilookup(sb, inum->no_addr);
+ inode = gfs2_ilookup(sb, inum->no_addr, 0);
if (inode) {
if (GFS2_I(inode)->i_no_formal_ino != inum->no_formal_ino) {
iput(inode);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 7cfdcb91336..a9f5cbe45cd 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -221,7 +221,7 @@ static int do_gfs2_set_flags(struct file *filp, u32 reqflags, u32 mask)
goto out_drop_write;
error = -EACCES;
- if (!is_owner_or_cap(inode))
+ if (!inode_owner_or_capable(inode))
goto out;
error = 0;
@@ -448,15 +448,20 @@ static int gfs2_mmap(struct file *file, struct vm_area_struct *vma)
{
struct gfs2_inode *ip = GFS2_I(file->f_mapping->host);
- if (!(file->f_flags & O_NOATIME)) {
+ if (!(file->f_flags & O_NOATIME) &&
+ !IS_NOATIME(&ip->i_inode)) {
struct gfs2_holder i_gh;
int error;
- gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
+ gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
error = gfs2_glock_nq(&i_gh);
- file_accessed(file);
- if (error == 0)
- gfs2_glock_dq_uninit(&i_gh);
+ if (error == 0) {
+ file_accessed(file);
+ gfs2_glock_dq(&i_gh);
+ }
+ gfs2_holder_uninit(&i_gh);
+ if (error)
+ return error;
}
vma->vm_ops = &gfs2_vm_ops;
vma->vm_flags |= VM_CAN_NONLINEAR;
@@ -540,18 +545,10 @@ static int gfs2_close(struct inode *inode, struct file *file)
/**
* gfs2_fsync - sync the dirty data for a file (across the cluster)
* @file: the file that points to the dentry (we ignore this)
- * @dentry: the dentry that points to the inode to sync
- *
- * The VFS will flush "normal" data for us. We only need to worry
- * about metadata here. For journaled data, we just do a log flush
- * as we can't avoid it. Otherwise we can just bale out if datasync
- * is set. For stuffed inodes we must flush the log in order to
- * ensure that all data is on disk.
+ * @datasync: set if we can ignore timestamp changes
*
- * The call to write_inode_now() is there to write back metadata and
- * the inode itself. It does also try and write the data, but thats
- * (hopefully) a no-op due to the VFS having already called filemap_fdatawrite()
- * for us.
+ * The VFS will flush data for us. We only need to worry
+ * about metadata here.
*
* Returns: errno
*/
@@ -560,22 +557,20 @@ static int gfs2_fsync(struct file *file, int datasync)
{
struct inode *inode = file->f_mapping->host;
int sync_state = inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC);
- int ret = 0;
-
- if (gfs2_is_jdata(GFS2_I(inode))) {
- gfs2_log_flush(GFS2_SB(inode), GFS2_I(inode)->i_gl);
- return 0;
- }
+ struct gfs2_inode *ip = GFS2_I(inode);
+ int ret;
- if (sync_state != 0) {
- if (!datasync)
- ret = write_inode_now(inode, 0);
+ if (datasync)
+ sync_state &= ~I_DIRTY_SYNC;
- if (gfs2_is_stuffed(GFS2_I(inode)))
- gfs2_log_flush(GFS2_SB(inode), GFS2_I(inode)->i_gl);
+ if (sync_state) {
+ ret = sync_inode_metadata(inode, 1);
+ if (ret)
+ return ret;
+ gfs2_ail_flush(ip->i_gl);
}
- return ret;
+ return 0;
}
/**
@@ -612,66 +607,110 @@ static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov,
return generic_file_aio_write(iocb, iov, nr_segs, pos);
}
-static void empty_write_end(struct page *page, unsigned from,
- unsigned to)
+static int empty_write_end(struct page *page, unsigned from,
+ unsigned to, int mode)
{
- struct gfs2_inode *ip = GFS2_I(page->mapping->host);
+ struct inode *inode = page->mapping->host;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct buffer_head *bh;
+ unsigned offset, blksize = 1 << inode->i_blkbits;
+ pgoff_t end_index = i_size_read(inode) >> PAGE_CACHE_SHIFT;
- page_zero_new_buffers(page, from, to);
- flush_dcache_page(page);
+ zero_user(page, from, to-from);
mark_page_accessed(page);
- if (!gfs2_is_writeback(ip))
- gfs2_page_add_databufs(ip, page, from, to);
+ if (page->index < end_index || !(mode & FALLOC_FL_KEEP_SIZE)) {
+ if (!gfs2_is_writeback(ip))
+ gfs2_page_add_databufs(ip, page, from, to);
+
+ block_commit_write(page, from, to);
+ return 0;
+ }
+
+ offset = 0;
+ bh = page_buffers(page);
+ while (offset < to) {
+ if (offset >= from) {
+ set_buffer_uptodate(bh);
+ mark_buffer_dirty(bh);
+ clear_buffer_new(bh);
+ write_dirty_buffer(bh, WRITE);
+ }
+ offset += blksize;
+ bh = bh->b_this_page;
+ }
- block_commit_write(page, from, to);
+ offset = 0;
+ bh = page_buffers(page);
+ while (offset < to) {
+ if (offset >= from) {
+ wait_on_buffer(bh);
+ if (!buffer_uptodate(bh))
+ return -EIO;
+ }
+ offset += blksize;
+ bh = bh->b_this_page;
+ }
+ return 0;
}
-static int write_empty_blocks(struct page *page, unsigned from, unsigned to)
+static int needs_empty_write(sector_t block, struct inode *inode)
{
- unsigned start, end, next;
- struct buffer_head *bh, *head;
int error;
+ struct buffer_head bh_map = { .b_state = 0, .b_blocknr = 0 };
- if (!page_has_buffers(page)) {
- error = __block_write_begin(page, from, to - from, gfs2_block_map);
- if (unlikely(error))
- return error;
+ bh_map.b_size = 1 << inode->i_blkbits;
+ error = gfs2_block_map(inode, block, &bh_map, 0);
+ if (unlikely(error))
+ return error;
+ return !buffer_mapped(&bh_map);
+}
- empty_write_end(page, from, to);
- return 0;
- }
+static int write_empty_blocks(struct page *page, unsigned from, unsigned to,
+ int mode)
+{
+ struct inode *inode = page->mapping->host;
+ unsigned start, end, next, blksize;
+ sector_t block = page->index << (PAGE_CACHE_SHIFT - inode->i_blkbits);
+ int ret;
- bh = head = page_buffers(page);
+ blksize = 1 << inode->i_blkbits;
next = end = 0;
while (next < from) {
- next += bh->b_size;
- bh = bh->b_this_page;
+ next += blksize;
+ block++;
}
start = next;
do {
- next += bh->b_size;
- if (buffer_mapped(bh)) {
+ next += blksize;
+ ret = needs_empty_write(block, inode);
+ if (unlikely(ret < 0))
+ return ret;
+ if (ret == 0) {
if (end) {
- error = __block_write_begin(page, start, end - start,
- gfs2_block_map);
- if (unlikely(error))
- return error;
- empty_write_end(page, start, end);
+ ret = __block_write_begin(page, start, end - start,
+ gfs2_block_map);
+ if (unlikely(ret))
+ return ret;
+ ret = empty_write_end(page, start, end, mode);
+ if (unlikely(ret))
+ return ret;
end = 0;
}
start = next;
}
else
end = next;
- bh = bh->b_this_page;
+ block++;
} while (next < to);
if (end) {
- error = __block_write_begin(page, start, end - start, gfs2_block_map);
- if (unlikely(error))
- return error;
- empty_write_end(page, start, end);
+ ret = __block_write_begin(page, start, end - start, gfs2_block_map);
+ if (unlikely(ret))
+ return ret;
+ ret = empty_write_end(page, start, end, mode);
+ if (unlikely(ret))
+ return ret;
}
return 0;
@@ -720,7 +759,7 @@ static int fallocate_chunk(struct inode *inode, loff_t offset, loff_t len,
if (curr == end)
to = end_offset;
- error = write_empty_blocks(page, from, to);
+ error = write_empty_blocks(page, from, to, mode);
if (!error && offset + to > inode->i_size &&
!(mode & FALLOC_FL_KEEP_SIZE)) {
i_size_write(inode, offset + to);
@@ -777,6 +816,7 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
loff_t bytes, max_bytes;
struct gfs2_alloc *al;
int error;
+ loff_t bsize_mask = ~((loff_t)sdp->sd_sb.sb_bsize - 1);
loff_t next = (offset + len - 1) >> sdp->sd_sb.sb_bsize_shift;
next = (next + 1) << sdp->sd_sb.sb_bsize_shift;
@@ -784,13 +824,15 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset,
if (mode & ~FALLOC_FL_KEEP_SIZE)
return -EOPNOTSUPP;
- offset = (offset >> sdp->sd_sb.sb_bsize_shift) <<
- sdp->sd_sb.sb_bsize_shift;
+ offset &= bsize_mask;
len = next - offset;
bytes = sdp->sd_max_rg_data * sdp->sd_sb.sb_bsize / 2;
if (!bytes)
bytes = UINT_MAX;
+ bytes &= bsize_mask;
+ if (bytes == 0)
+ bytes = sdp->sd_sb.sb_bsize;
gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &ip->i_gh);
error = gfs2_glock_nq(&ip->i_gh);
@@ -821,6 +863,9 @@ retry:
if (error) {
if (error == -ENOSPC && bytes > sdp->sd_sb.sb_bsize) {
bytes >>= 1;
+ bytes &= bsize_mask;
+ if (bytes == 0)
+ bytes = sdp->sd_sb.sb_bsize;
goto retry;
}
goto out_qunlock;
@@ -976,8 +1021,10 @@ static void do_unflock(struct file *file, struct file_lock *fl)
mutex_lock(&fp->f_fl_mutex);
flock_lock_file_wait(file, fl);
- if (fl_gh->gh_gl)
- gfs2_glock_dq_uninit(fl_gh);
+ if (fl_gh->gh_gl) {
+ gfs2_glock_dq_wait(fl_gh);
+ gfs2_holder_uninit(fl_gh);
+ }
mutex_unlock(&fp->f_fl_mutex);
}
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 08a8beb152e..2792a790e50 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -26,6 +26,9 @@
#include <linux/freezer.h>
#include <linux/workqueue.h>
#include <linux/jiffies.h>
+#include <linux/rcupdate.h>
+#include <linux/rculist_bl.h>
+#include <linux/bit_spinlock.h>
#include "gfs2.h"
#include "incore.h"
@@ -41,10 +44,6 @@
#define CREATE_TRACE_POINTS
#include "trace_gfs2.h"
-struct gfs2_gl_hash_bucket {
- struct hlist_head hb_list;
-};
-
struct gfs2_glock_iter {
int hash; /* hash bucket index */
struct gfs2_sbd *sdp; /* incore superblock */
@@ -54,7 +53,6 @@ struct gfs2_glock_iter {
typedef void (*glock_examiner) (struct gfs2_glock * gl);
-static int gfs2_dump_lockstate(struct gfs2_sbd *sdp);
static int __dump_glock(struct seq_file *seq, const struct gfs2_glock *gl);
#define GLOCK_BUG_ON(gl,x) do { if (unlikely(x)) { __dump_glock(NULL, gl); BUG(); } } while(0)
static void do_xmote(struct gfs2_glock *gl, struct gfs2_holder *gh, unsigned int target);
@@ -70,57 +68,9 @@ static DEFINE_SPINLOCK(lru_lock);
#define GFS2_GL_HASH_SIZE (1 << GFS2_GL_HASH_SHIFT)
#define GFS2_GL_HASH_MASK (GFS2_GL_HASH_SIZE - 1)
-static struct gfs2_gl_hash_bucket gl_hash_table[GFS2_GL_HASH_SIZE];
+static struct hlist_bl_head gl_hash_table[GFS2_GL_HASH_SIZE];
static struct dentry *gfs2_root;
-/*
- * Despite what you might think, the numbers below are not arbitrary :-)
- * They are taken from the ipv4 routing hash code, which is well tested
- * and thus should be nearly optimal. Later on we might tweek the numbers
- * but for now this should be fine.
- *
- * The reason for putting the locks in a separate array from the list heads
- * is that we can have fewer locks than list heads and save memory. We use
- * the same hash function for both, but with a different hash mask.
- */
-#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
- defined(CONFIG_PROVE_LOCKING)
-
-#ifdef CONFIG_LOCKDEP
-# define GL_HASH_LOCK_SZ 256
-#else
-# if NR_CPUS >= 32
-# define GL_HASH_LOCK_SZ 4096
-# elif NR_CPUS >= 16
-# define GL_HASH_LOCK_SZ 2048
-# elif NR_CPUS >= 8
-# define GL_HASH_LOCK_SZ 1024
-# elif NR_CPUS >= 4
-# define GL_HASH_LOCK_SZ 512
-# else
-# define GL_HASH_LOCK_SZ 256
-# endif
-#endif
-
-/* We never want more locks than chains */
-#if GFS2_GL_HASH_SIZE < GL_HASH_LOCK_SZ
-# undef GL_HASH_LOCK_SZ
-# define GL_HASH_LOCK_SZ GFS2_GL_HASH_SIZE
-#endif
-
-static rwlock_t gl_hash_locks[GL_HASH_LOCK_SZ];
-
-static inline rwlock_t *gl_lock_addr(unsigned int x)
-{
- return &gl_hash_locks[x & (GL_HASH_LOCK_SZ-1)];
-}
-#else /* not SMP, so no spinlocks required */
-static inline rwlock_t *gl_lock_addr(unsigned int x)
-{
- return NULL;
-}
-#endif
-
/**
* gl_hash() - Turn glock number into hash bucket number
* @lock: The glock number
@@ -141,25 +91,33 @@ static unsigned int gl_hash(const struct gfs2_sbd *sdp,
return h;
}
-/**
- * glock_free() - Perform a few checks and then release struct gfs2_glock
- * @gl: The glock to release
- *
- * Also calls lock module to release its internal structure for this glock.
- *
- */
+static inline void spin_lock_bucket(unsigned int hash)
+{
+ hlist_bl_lock(&gl_hash_table[hash]);
+}
+
+static inline void spin_unlock_bucket(unsigned int hash)
+{
+ hlist_bl_unlock(&gl_hash_table[hash]);
+}
+
+static void gfs2_glock_dealloc(struct rcu_head *rcu)
+{
+ struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu);
+
+ if (gl->gl_ops->go_flags & GLOF_ASPACE)
+ kmem_cache_free(gfs2_glock_aspace_cachep, gl);
+ else
+ kmem_cache_free(gfs2_glock_cachep, gl);
+}
-static void glock_free(struct gfs2_glock *gl)
+void gfs2_glock_free(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_sbd;
- struct address_space *mapping = gfs2_glock2aspace(gl);
- struct kmem_cache *cachep = gfs2_glock_cachep;
- GLOCK_BUG_ON(gl, mapping && mapping->nrpages);
- trace_gfs2_glock_put(gl);
- if (mapping)
- cachep = gfs2_glock_aspace_cachep;
- sdp->sd_lockstruct.ls_ops->lm_put_lock(cachep, gl);
+ call_rcu(&gl->gl_rcu, gfs2_glock_dealloc);
+ if (atomic_dec_and_test(&sdp->sd_glock_disposal))
+ wake_up(&sdp->sd_glock_wait);
}
/**
@@ -194,28 +152,47 @@ static int demote_ok(const struct gfs2_glock *gl)
return 1;
}
-/**
- * gfs2_glock_schedule_for_reclaim - Add a glock to the reclaim list
- * @gl: the glock
- *
- */
-static void gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl)
+void gfs2_glock_add_to_lru(struct gfs2_glock *gl)
{
- int may_reclaim;
- may_reclaim = (demote_ok(gl) &&
- (atomic_read(&gl->gl_ref) == 1 ||
- (gl->gl_name.ln_type == LM_TYPE_INODE &&
- atomic_read(&gl->gl_ref) <= 2)));
spin_lock(&lru_lock);
- if (list_empty(&gl->gl_lru) && may_reclaim) {
- list_add_tail(&gl->gl_lru, &lru_list);
+
+ if (!list_empty(&gl->gl_lru))
+ list_del_init(&gl->gl_lru);
+ else
atomic_inc(&lru_count);
+
+ list_add_tail(&gl->gl_lru, &lru_list);
+ set_bit(GLF_LRU, &gl->gl_flags);
+ spin_unlock(&lru_lock);
+}
+
+static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
+{
+ spin_lock(&lru_lock);
+ if (!list_empty(&gl->gl_lru)) {
+ list_del_init(&gl->gl_lru);
+ atomic_dec(&lru_count);
+ clear_bit(GLF_LRU, &gl->gl_flags);
}
spin_unlock(&lru_lock);
}
/**
+ * __gfs2_glock_schedule_for_reclaim - Add a glock to the reclaim list
+ * @gl: the glock
+ *
+ * If the glock is demotable, then we add it (or move it) to the end
+ * of the glock LRU list.
+ */
+
+static void __gfs2_glock_schedule_for_reclaim(struct gfs2_glock *gl)
+{
+ if (demote_ok(gl))
+ gfs2_glock_add_to_lru(gl);
+}
+
+/**
* gfs2_glock_put_nolock() - Decrement reference count on glock
* @gl: The glock to put
*
@@ -227,7 +204,6 @@ void gfs2_glock_put_nolock(struct gfs2_glock *gl)
{
if (atomic_dec_and_test(&gl->gl_ref))
GLOCK_BUG_ON(gl, 1);
- gfs2_glock_schedule_for_reclaim(gl);
}
/**
@@ -236,30 +212,21 @@ void gfs2_glock_put_nolock(struct gfs2_glock *gl)
*
*/
-int gfs2_glock_put(struct gfs2_glock *gl)
+void gfs2_glock_put(struct gfs2_glock *gl)
{
- int rv = 0;
+ struct gfs2_sbd *sdp = gl->gl_sbd;
+ struct address_space *mapping = gfs2_glock2aspace(gl);
- write_lock(gl_lock_addr(gl->gl_hash));
- if (atomic_dec_and_lock(&gl->gl_ref, &lru_lock)) {
- hlist_del(&gl->gl_list);
- if (!list_empty(&gl->gl_lru)) {
- list_del_init(&gl->gl_lru);
- atomic_dec(&lru_count);
- }
- spin_unlock(&lru_lock);
- write_unlock(gl_lock_addr(gl->gl_hash));
+ if (atomic_dec_and_test(&gl->gl_ref)) {
+ spin_lock_bucket(gl->gl_hash);
+ hlist_bl_del_rcu(&gl->gl_list);
+ spin_unlock_bucket(gl->gl_hash);
+ gfs2_glock_remove_from_lru(gl);
GLOCK_BUG_ON(gl, !list_empty(&gl->gl_holders));
- glock_free(gl);
- rv = 1;
- goto out;
+ GLOCK_BUG_ON(gl, mapping && mapping->nrpages);
+ trace_gfs2_glock_put(gl);
+ sdp->sd_lockstruct.ls_ops->lm_put_lock(gl);
}
- spin_lock(&gl->gl_spin);
- gfs2_glock_schedule_for_reclaim(gl);
- spin_unlock(&gl->gl_spin);
- write_unlock(gl_lock_addr(gl->gl_hash));
-out:
- return rv;
}
/**
@@ -275,17 +242,15 @@ static struct gfs2_glock *search_bucket(unsigned int hash,
const struct lm_lockname *name)
{
struct gfs2_glock *gl;
- struct hlist_node *h;
+ struct hlist_bl_node *h;
- hlist_for_each_entry(gl, h, &gl_hash_table[hash].hb_list, gl_list) {
+ hlist_bl_for_each_entry_rcu(gl, h, &gl_hash_table[hash], gl_list) {
if (!lm_name_equal(&gl->gl_name, name))
continue;
if (gl->gl_sbd != sdp)
continue;
-
- atomic_inc(&gl->gl_ref);
-
- return gl;
+ if (atomic_inc_not_zero(&gl->gl_ref))
+ return gl;
}
return NULL;
@@ -576,11 +541,6 @@ __acquires(&gl->gl_spin)
clear_bit(GLF_INVALIDATE_IN_PROGRESS, &gl->gl_flags);
gfs2_glock_hold(gl);
- if (target != LM_ST_UNLOCKED && (gl->gl_state == LM_ST_SHARED ||
- gl->gl_state == LM_ST_DEFERRED) &&
- !(lck_flags & (LM_FLAG_TRY | LM_FLAG_TRY_1CB)))
- lck_flags |= LM_FLAG_TRY_1CB;
-
if (sdp->sd_lockstruct.ls_ops->lm_lock) {
/* lock_dlm */
ret = sdp->sd_lockstruct.ls_ops->lm_lock(gl, target, lck_flags);
@@ -682,7 +642,7 @@ static void delete_work_func(struct work_struct *work)
/* Note: Unsafe to dereference ip as we don't hold right refs/locks */
if (ip)
- inode = gfs2_ilookup(sdp->sd_vfs, no_addr);
+ inode = gfs2_ilookup(sdp->sd_vfs, no_addr, 1);
else
inode = gfs2_lookup_by_inum(sdp, no_addr, NULL, GFS2_BLKST_UNLINKED);
if (inode && !IS_ERR(inode)) {
@@ -743,10 +703,11 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
struct gfs2_glock *gl, *tmp;
unsigned int hash = gl_hash(sdp, &name);
struct address_space *mapping;
+ struct kmem_cache *cachep;
- read_lock(gl_lock_addr(hash));
+ rcu_read_lock();
gl = search_bucket(hash, sdp, &name);
- read_unlock(gl_lock_addr(hash));
+ rcu_read_unlock();
*glp = gl;
if (gl)
@@ -755,9 +716,10 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
return -ENOENT;
if (glops->go_flags & GLOF_ASPACE)
- gl = kmem_cache_alloc(gfs2_glock_aspace_cachep, GFP_KERNEL);
+ cachep = gfs2_glock_aspace_cachep;
else
- gl = kmem_cache_alloc(gfs2_glock_cachep, GFP_KERNEL);
+ cachep = gfs2_glock_cachep;
+ gl = kmem_cache_alloc(cachep, GFP_KERNEL);
if (!gl)
return -ENOMEM;
@@ -790,15 +752,16 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
mapping->writeback_index = 0;
}
- write_lock(gl_lock_addr(hash));
+ spin_lock_bucket(hash);
tmp = search_bucket(hash, sdp, &name);
if (tmp) {
- write_unlock(gl_lock_addr(hash));
- glock_free(gl);
+ spin_unlock_bucket(hash);
+ kmem_cache_free(cachep, gl);
+ atomic_dec(&sdp->sd_glock_disposal);
gl = tmp;
} else {
- hlist_add_head(&gl->gl_list, &gl_hash_table[hash].hb_list);
- write_unlock(gl_lock_addr(hash));
+ hlist_bl_add_head_rcu(&gl->gl_list, &gl_hash_table[hash]);
+ spin_unlock_bucket(hash);
}
*glp = gl;
@@ -1007,13 +970,13 @@ fail:
insert_pt = &gh2->gh_list;
}
set_bit(GLF_QUEUED, &gl->gl_flags);
+ trace_gfs2_glock_queue(gh, 1);
if (likely(insert_pt == NULL)) {
list_add_tail(&gh->gh_list, &gl->gl_holders);
if (unlikely(gh->gh_flags & LM_FLAG_PRIORITY))
goto do_cancel;
return;
}
- trace_gfs2_glock_queue(gh, 1);
list_add_tail(&gh->gh_list, insert_pt);
do_cancel:
gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
@@ -1056,6 +1019,9 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
return -EIO;
+ if (test_bit(GLF_LRU, &gl->gl_flags))
+ gfs2_glock_remove_from_lru(gl);
+
spin_lock(&gl->gl_spin);
add_to_queue(gh);
if ((LM_FLAG_NOEXP & gh->gh_flags) &&
@@ -1113,6 +1079,8 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
!test_bit(GLF_DEMOTE, &gl->gl_flags))
fast_path = 1;
}
+ if (!test_bit(GLF_LFLUSH, &gl->gl_flags))
+ __gfs2_glock_schedule_for_reclaim(gl);
trace_gfs2_glock_queue(gh, 0);
spin_unlock(&gl->gl_spin);
if (likely(fast_path))
@@ -1151,7 +1119,7 @@ void gfs2_glock_dq_uninit(struct gfs2_holder *gh)
* @number: the lock number
* @glops: the glock operations for the type of glock
* @state: the state to acquire the glock in
- * @flags: modifier flags for the aquisition
+ * @flags: modifier flags for the acquisition
* @gh: the struct gfs2_holder
*
* Returns: errno
@@ -1276,10 +1244,8 @@ int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs)
void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs)
{
- unsigned int x;
-
- for (x = 0; x < num_gh; x++)
- gfs2_glock_dq(&ghs[x]);
+ while (num_gh--)
+ gfs2_glock_dq(&ghs[num_gh]);
}
/**
@@ -1291,10 +1257,8 @@ void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs)
void gfs2_glock_dq_uninit_m(unsigned int num_gh, struct gfs2_holder *ghs)
{
- unsigned int x;
-
- for (x = 0; x < num_gh; x++)
- gfs2_glock_dq_uninit(&ghs[x]);
+ while (num_gh--)
+ gfs2_glock_dq_uninit(&ghs[num_gh]);
}
void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
@@ -1382,11 +1346,14 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
}
-static int gfs2_shrink_glock_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+static int gfs2_shrink_glock_memory(struct shrinker *shrink,
+ struct shrink_control *sc)
{
struct gfs2_glock *gl;
int may_demote;
int nr_skipped = 0;
+ int nr = sc->nr_to_scan;
+ gfp_t gfp_mask = sc->gfp_mask;
LIST_HEAD(skipped);
if (nr == 0)
@@ -1399,6 +1366,7 @@ static int gfs2_shrink_glock_memory(struct shrinker *shrink, int nr, gfp_t gfp_m
while(nr && !list_empty(&lru_list)) {
gl = list_entry(lru_list.next, struct gfs2_glock, gl_lru);
list_del_init(&gl->gl_lru);
+ clear_bit(GLF_LRU, &gl->gl_flags);
atomic_dec(&lru_count);
/* Test for being demotable */
@@ -1421,6 +1389,7 @@ static int gfs2_shrink_glock_memory(struct shrinker *shrink, int nr, gfp_t gfp_m
}
nr_skipped++;
list_add(&gl->gl_lru, &skipped);
+ set_bit(GLF_LRU, &gl->gl_flags);
}
list_splice(&skipped, &lru_list);
atomic_add(nr_skipped, &lru_count);
@@ -1440,42 +1409,30 @@ static struct shrinker glock_shrinker = {
* @sdp: the filesystem
* @bucket: the bucket
*
- * Returns: 1 if the bucket has entries
*/
-static int examine_bucket(glock_examiner examiner, struct gfs2_sbd *sdp,
+static void examine_bucket(glock_examiner examiner, const struct gfs2_sbd *sdp,
unsigned int hash)
{
- struct gfs2_glock *gl, *prev = NULL;
- int has_entries = 0;
- struct hlist_head *head = &gl_hash_table[hash].hb_list;
+ struct gfs2_glock *gl;
+ struct hlist_bl_head *head = &gl_hash_table[hash];
+ struct hlist_bl_node *pos;
- read_lock(gl_lock_addr(hash));
- /* Can't use hlist_for_each_entry - don't want prefetch here */
- if (hlist_empty(head))
- goto out;
- gl = list_entry(head->first, struct gfs2_glock, gl_list);
- while(1) {
- if (!sdp || gl->gl_sbd == sdp) {
- gfs2_glock_hold(gl);
- read_unlock(gl_lock_addr(hash));
- if (prev)
- gfs2_glock_put(prev);
- prev = gl;
+ rcu_read_lock();
+ hlist_bl_for_each_entry_rcu(gl, pos, head, gl_list) {
+ if ((gl->gl_sbd == sdp) && atomic_read(&gl->gl_ref))
examiner(gl);
- has_entries = 1;
- read_lock(gl_lock_addr(hash));
- }
- if (gl->gl_list.next == NULL)
- break;
- gl = list_entry(gl->gl_list.next, struct gfs2_glock, gl_list);
}
-out:
- read_unlock(gl_lock_addr(hash));
- if (prev)
- gfs2_glock_put(prev);
+ rcu_read_unlock();
cond_resched();
- return has_entries;
+}
+
+static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
+{
+ unsigned x;
+
+ for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
+ examine_bucket(examiner, sdp, x);
}
@@ -1505,12 +1462,7 @@ static void thaw_glock(struct gfs2_glock *gl)
static void clear_glock(struct gfs2_glock *gl)
{
- spin_lock(&lru_lock);
- if (!list_empty(&gl->gl_lru)) {
- list_del_init(&gl->gl_lru);
- atomic_dec(&lru_count);
- }
- spin_unlock(&lru_lock);
+ gfs2_glock_remove_from_lru(gl);
spin_lock(&gl->gl_spin);
if (gl->gl_state != LM_ST_UNLOCKED)
@@ -1529,10 +1481,21 @@ static void clear_glock(struct gfs2_glock *gl)
void gfs2_glock_thaw(struct gfs2_sbd *sdp)
{
- unsigned x;
+ glock_hash_walk(thaw_glock, sdp);
+}
- for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
- examine_bucket(thaw_glock, sdp, x);
+static int dump_glock(struct seq_file *seq, struct gfs2_glock *gl)
+{
+ int ret;
+ spin_lock(&gl->gl_spin);
+ ret = __dump_glock(seq, gl);
+ spin_unlock(&gl->gl_spin);
+ return ret;
+}
+
+static void dump_glock_func(struct gfs2_glock *gl)
+{
+ dump_glock(NULL, gl);
}
/**
@@ -1545,13 +1508,10 @@ void gfs2_glock_thaw(struct gfs2_sbd *sdp)
void gfs2_gl_hash_clear(struct gfs2_sbd *sdp)
{
- unsigned int x;
-
- for (x = 0; x < GFS2_GL_HASH_SIZE; x++)
- examine_bucket(clear_glock, sdp, x);
+ glock_hash_walk(clear_glock, sdp);
flush_workqueue(glock_workqueue);
wait_event(sdp->sd_glock_wait, atomic_read(&sdp->sd_glock_disposal) == 0);
- gfs2_dump_lockstate(sdp);
+ glock_hash_walk(dump_glock_func, sdp);
}
void gfs2_glock_finish_truncate(struct gfs2_inode *ip)
@@ -1637,9 +1597,11 @@ static int dump_holder(struct seq_file *seq, const struct gfs2_holder *gh)
return 0;
}
-static const char *gflags2str(char *buf, const unsigned long *gflags)
+static const char *gflags2str(char *buf, const struct gfs2_glock *gl)
{
+ const unsigned long *gflags = &gl->gl_flags;
char *p = buf;
+
if (test_bit(GLF_LOCK, gflags))
*p++ = 'l';
if (test_bit(GLF_DEMOTE, gflags))
@@ -1662,6 +1624,10 @@ static const char *gflags2str(char *buf, const unsigned long *gflags)
*p++ = 'F';
if (test_bit(GLF_QUEUED, gflags))
*p++ = 'q';
+ if (test_bit(GLF_LRU, gflags))
+ *p++ = 'L';
+ if (gl->gl_object)
+ *p++ = 'o';
*p = 0;
return buf;
}
@@ -1696,14 +1662,15 @@ static int __dump_glock(struct seq_file *seq, const struct gfs2_glock *gl)
dtime *= 1000000/HZ; /* demote time in uSec */
if (!test_bit(GLF_DEMOTE, &gl->gl_flags))
dtime = 0;
- gfs2_print_dbg(seq, "G: s:%s n:%u/%llx f:%s t:%s d:%s/%llu a:%d r:%d\n",
+ gfs2_print_dbg(seq, "G: s:%s n:%u/%llx f:%s t:%s d:%s/%llu a:%d v:%d r:%d\n",
state2str(gl->gl_state),
gl->gl_name.ln_type,
(unsigned long long)gl->gl_name.ln_number,
- gflags2str(gflags_buf, &gl->gl_flags),
+ gflags2str(gflags_buf, gl),
state2str(gl->gl_target),
state2str(gl->gl_demote_state), dtime,
atomic_read(&gl->gl_ail_count),
+ atomic_read(&gl->gl_revokes),
atomic_read(&gl->gl_ref));
list_for_each_entry(gh, &gl->gl_holders, gh_list) {
@@ -1717,73 +1684,22 @@ out:
return error;
}
-static int dump_glock(struct seq_file *seq, struct gfs2_glock *gl)
-{
- int ret;
- spin_lock(&gl->gl_spin);
- ret = __dump_glock(seq, gl);
- spin_unlock(&gl->gl_spin);
- return ret;
-}
-/**
- * gfs2_dump_lockstate - print out the current lockstate
- * @sdp: the filesystem
- * @ub: the buffer to copy the information into
- *
- * If @ub is NULL, dump the lockstate to the console.
- *
- */
-
-static int gfs2_dump_lockstate(struct gfs2_sbd *sdp)
-{
- struct gfs2_glock *gl;
- struct hlist_node *h;
- unsigned int x;
- int error = 0;
-
- for (x = 0; x < GFS2_GL_HASH_SIZE; x++) {
-
- read_lock(gl_lock_addr(x));
-
- hlist_for_each_entry(gl, h, &gl_hash_table[x].hb_list, gl_list) {
- if (gl->gl_sbd != sdp)
- continue;
-
- error = dump_glock(NULL, gl);
- if (error)
- break;
- }
-
- read_unlock(gl_lock_addr(x));
-
- if (error)
- break;
- }
-
-
- return error;
-}
int __init gfs2_glock_init(void)
{
unsigned i;
for(i = 0; i < GFS2_GL_HASH_SIZE; i++) {
- INIT_HLIST_HEAD(&gl_hash_table[i].hb_list);
+ INIT_HLIST_BL_HEAD(&gl_hash_table[i]);
}
-#ifdef GL_HASH_LOCK_SZ
- for(i = 0; i < GL_HASH_LOCK_SZ; i++) {
- rwlock_init(&gl_hash_locks[i]);
- }
-#endif
glock_workqueue = alloc_workqueue("glock_workqueue", WQ_MEM_RECLAIM |
- WQ_HIGHPRI | WQ_FREEZEABLE, 0);
+ WQ_HIGHPRI | WQ_FREEZABLE, 0);
if (IS_ERR(glock_workqueue))
return PTR_ERR(glock_workqueue);
gfs2_delete_workqueue = alloc_workqueue("delete_workqueue",
- WQ_MEM_RECLAIM | WQ_FREEZEABLE,
+ WQ_MEM_RECLAIM | WQ_FREEZABLE,
0);
if (IS_ERR(gfs2_delete_workqueue)) {
destroy_workqueue(glock_workqueue);
@@ -1802,62 +1718,54 @@ void gfs2_glock_exit(void)
destroy_workqueue(gfs2_delete_workqueue);
}
+static inline struct gfs2_glock *glock_hash_chain(unsigned hash)
+{
+ return hlist_bl_entry(hlist_bl_first_rcu(&gl_hash_table[hash]),
+ struct gfs2_glock, gl_list);
+}
+
+static inline struct gfs2_glock *glock_hash_next(struct gfs2_glock *gl)
+{
+ return hlist_bl_entry(rcu_dereference(gl->gl_list.next),
+ struct gfs2_glock, gl_list);
+}
+
static int gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
{
struct gfs2_glock *gl;
-restart:
- read_lock(gl_lock_addr(gi->hash));
- gl = gi->gl;
- if (gl) {
- gi->gl = hlist_entry(gl->gl_list.next,
- struct gfs2_glock, gl_list);
- } else {
- gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first,
- struct gfs2_glock, gl_list);
- }
- if (gi->gl)
- gfs2_glock_hold(gi->gl);
- read_unlock(gl_lock_addr(gi->hash));
- if (gl)
- gfs2_glock_put(gl);
- while (gi->gl == NULL) {
- gi->hash++;
- if (gi->hash >= GFS2_GL_HASH_SIZE)
- return 1;
- read_lock(gl_lock_addr(gi->hash));
- gi->gl = hlist_entry(gl_hash_table[gi->hash].hb_list.first,
- struct gfs2_glock, gl_list);
- if (gi->gl)
- gfs2_glock_hold(gi->gl);
- read_unlock(gl_lock_addr(gi->hash));
- }
-
- if (gi->sdp != gi->gl->gl_sbd)
- goto restart;
+ do {
+ gl = gi->gl;
+ if (gl) {
+ gi->gl = glock_hash_next(gl);
+ } else {
+ gi->gl = glock_hash_chain(gi->hash);
+ }
+ while (gi->gl == NULL) {
+ gi->hash++;
+ if (gi->hash >= GFS2_GL_HASH_SIZE) {
+ rcu_read_unlock();
+ return 1;
+ }
+ gi->gl = glock_hash_chain(gi->hash);
+ }
+ /* Skip entries for other sb and dead entries */
+ } while (gi->sdp != gi->gl->gl_sbd || atomic_read(&gi->gl->gl_ref) == 0);
return 0;
}
-static void gfs2_glock_iter_free(struct gfs2_glock_iter *gi)
-{
- if (gi->gl)
- gfs2_glock_put(gi->gl);
- gi->gl = NULL;
-}
-
static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
{
struct gfs2_glock_iter *gi = seq->private;
loff_t n = *pos;
gi->hash = 0;
+ rcu_read_lock();
do {
- if (gfs2_glock_iter_next(gi)) {
- gfs2_glock_iter_free(gi);
+ if (gfs2_glock_iter_next(gi))
return NULL;
- }
} while (n--);
return gi->gl;
@@ -1870,10 +1778,8 @@ static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr,
(*pos)++;
- if (gfs2_glock_iter_next(gi)) {
- gfs2_glock_iter_free(gi);
+ if (gfs2_glock_iter_next(gi))
return NULL;
- }
return gi->gl;
}
@@ -1881,7 +1787,10 @@ static void *gfs2_glock_seq_next(struct seq_file *seq, void *iter_ptr,
static void gfs2_glock_seq_stop(struct seq_file *seq, void *iter_ptr)
{
struct gfs2_glock_iter *gi = seq->private;
- gfs2_glock_iter_free(gi);
+
+ if (gi->gl)
+ rcu_read_unlock();
+ gi->gl = NULL;
}
static int gfs2_glock_seq_show(struct seq_file *seq, void *iter_ptr)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index 691851ceb61..6b2f757b928 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -118,7 +118,7 @@ struct lm_lockops {
int (*lm_mount) (struct gfs2_sbd *sdp, const char *fsname);
void (*lm_unmount) (struct gfs2_sbd *sdp);
void (*lm_withdraw) (struct gfs2_sbd *sdp);
- void (*lm_put_lock) (struct kmem_cache *cachep, struct gfs2_glock *gl);
+ void (*lm_put_lock) (struct gfs2_glock *gl);
int (*lm_lock) (struct gfs2_glock *gl, unsigned int req_state,
unsigned int flags);
void (*lm_cancel) (struct gfs2_glock *gl);
@@ -174,7 +174,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp,
int create, struct gfs2_glock **glp);
void gfs2_glock_hold(struct gfs2_glock *gl);
void gfs2_glock_put_nolock(struct gfs2_glock *gl);
-int gfs2_glock_put(struct gfs2_glock *gl);
+void gfs2_glock_put(struct gfs2_glock *gl);
void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
struct gfs2_holder *gh);
void gfs2_holder_reinit(unsigned int state, unsigned flags,
@@ -223,25 +223,21 @@ static inline int gfs2_glock_nq_init(struct gfs2_glock *gl,
return error;
}
-/* Lock Value Block functions */
-
-int gfs2_lvb_hold(struct gfs2_glock *gl);
-void gfs2_lvb_unhold(struct gfs2_glock *gl);
-
-void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state);
-void gfs2_glock_complete(struct gfs2_glock *gl, int ret);
-void gfs2_reclaim_glock(struct gfs2_sbd *sdp);
-void gfs2_gl_hash_clear(struct gfs2_sbd *sdp);
-void gfs2_glock_finish_truncate(struct gfs2_inode *ip);
-void gfs2_glock_thaw(struct gfs2_sbd *sdp);
-
-int __init gfs2_glock_init(void);
-void gfs2_glock_exit(void);
-
-int gfs2_create_debugfs_file(struct gfs2_sbd *sdp);
-void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp);
-int gfs2_register_debugfs(void);
-void gfs2_unregister_debugfs(void);
+extern void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state);
+extern void gfs2_glock_complete(struct gfs2_glock *gl, int ret);
+extern void gfs2_gl_hash_clear(struct gfs2_sbd *sdp);
+extern void gfs2_glock_finish_truncate(struct gfs2_inode *ip);
+extern void gfs2_glock_thaw(struct gfs2_sbd *sdp);
+extern void gfs2_glock_add_to_lru(struct gfs2_glock *gl);
+extern void gfs2_glock_free(struct gfs2_glock *gl);
+
+extern int __init gfs2_glock_init(void);
+extern void gfs2_glock_exit(void);
+
+extern int gfs2_create_debugfs_file(struct gfs2_sbd *sdp);
+extern void gfs2_delete_debugfs_file(struct gfs2_sbd *sdp);
+extern int gfs2_register_debugfs(void);
+extern void gfs2_unregister_debugfs(void);
extern const struct lm_lockops gfs2_dlm_ops;
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 263561bf1a5..8ef70f46473 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -28,18 +28,45 @@
#include "trans.h"
/**
- * ail_empty_gl - remove all buffers for a given lock from the AIL
+ * __gfs2_ail_flush - remove all buffers for a given lock from the AIL
* @gl: the glock
*
* None of the buffers should be dirty, locked, or pinned.
*/
-static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
+static void __gfs2_ail_flush(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_sbd;
struct list_head *head = &gl->gl_ail_list;
struct gfs2_bufdata *bd;
struct buffer_head *bh;
+
+ spin_lock(&sdp->sd_ail_lock);
+ while (!list_empty(head)) {
+ bd = list_entry(head->next, struct gfs2_bufdata,
+ bd_ail_gl_list);
+ bh = bd->bd_bh;
+ gfs2_remove_from_ail(bd);
+ spin_unlock(&sdp->sd_ail_lock);
+
+ bd->bd_bh = NULL;
+ bh->b_private = NULL;
+ bd->bd_blkno = bh->b_blocknr;
+ gfs2_log_lock(sdp);
+ gfs2_assert_withdraw(sdp, !buffer_busy(bh));
+ gfs2_trans_add_revoke(sdp, bd);
+ gfs2_log_unlock(sdp);
+
+ spin_lock(&sdp->sd_ail_lock);
+ }
+ gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
+ spin_unlock(&sdp->sd_ail_lock);
+}
+
+
+static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
+{
+ struct gfs2_sbd *sdp = gl->gl_sbd;
struct gfs2_trans tr;
memset(&tr, 0, sizeof(tr));
@@ -56,25 +83,29 @@ static void gfs2_ail_empty_gl(struct gfs2_glock *gl)
BUG_ON(current->journal_info);
current->journal_info = &tr;
- gfs2_log_lock(sdp);
- while (!list_empty(head)) {
- bd = list_entry(head->next, struct gfs2_bufdata,
- bd_ail_gl_list);
- bh = bd->bd_bh;
- gfs2_remove_from_ail(bd);
- bd->bd_bh = NULL;
- bh->b_private = NULL;
- bd->bd_blkno = bh->b_blocknr;
- gfs2_assert_withdraw(sdp, !buffer_busy(bh));
- gfs2_trans_add_revoke(sdp, bd);
- }
- gfs2_assert_withdraw(sdp, !atomic_read(&gl->gl_ail_count));
- gfs2_log_unlock(sdp);
+ __gfs2_ail_flush(gl);
gfs2_trans_end(sdp);
gfs2_log_flush(sdp, NULL);
}
+void gfs2_ail_flush(struct gfs2_glock *gl)
+{
+ struct gfs2_sbd *sdp = gl->gl_sbd;
+ unsigned int revokes = atomic_read(&gl->gl_ail_count);
+ int ret;
+
+ if (!revokes)
+ return;
+
+ ret = gfs2_trans_begin(sdp, 0, revokes);
+ if (ret)
+ return;
+ __gfs2_ail_flush(gl);
+ gfs2_trans_end(sdp);
+ gfs2_log_flush(sdp, NULL);
+}
+
/**
* rgrp_go_sync - sync out the metadata for this glock
* @gl: the glock
@@ -206,12 +237,134 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
static int inode_go_demote_ok(const struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_sbd;
+ struct gfs2_holder *gh;
+
if (sdp->sd_jindex == gl->gl_object || sdp->sd_rindex == gl->gl_object)
return 0;
+
+ if (!list_empty(&gl->gl_holders)) {
+ gh = list_entry(gl->gl_holders.next, struct gfs2_holder, gh_list);
+ if (gh->gh_list.next != &gl->gl_holders)
+ return 0;
+ }
+
return 1;
}
/**
+ * gfs2_set_nlink - Set the inode's link count based on on-disk info
+ * @inode: The inode in question
+ * @nlink: The link count
+ *
+ * If the link count has hit zero, it must never be raised, whatever the
+ * on-disk inode might say. When new struct inodes are created the link
+ * count is set to 1, so that we can safely use this test even when reading
+ * in on disk information for the first time.
+ */
+
+static void gfs2_set_nlink(struct inode *inode, u32 nlink)
+{
+ /*
+ * We will need to review setting the nlink count here in the
+ * light of the forthcoming ro bind mount work. This is a reminder
+ * to do that.
+ */
+ if ((inode->i_nlink != nlink) && (inode->i_nlink != 0)) {
+ if (nlink == 0)
+ clear_nlink(inode);
+ else
+ inode->i_nlink = nlink;
+ }
+}
+
+static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
+{
+ const struct gfs2_dinode *str = buf;
+ struct timespec atime;
+ u16 height, depth;
+
+ if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
+ goto corrupt;
+ ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino);
+ ip->i_inode.i_mode = be32_to_cpu(str->di_mode);
+ ip->i_inode.i_rdev = 0;
+ switch (ip->i_inode.i_mode & S_IFMT) {
+ case S_IFBLK:
+ case S_IFCHR:
+ ip->i_inode.i_rdev = MKDEV(be32_to_cpu(str->di_major),
+ be32_to_cpu(str->di_minor));
+ break;
+ };
+
+ ip->i_inode.i_uid = be32_to_cpu(str->di_uid);
+ ip->i_inode.i_gid = be32_to_cpu(str->di_gid);
+ gfs2_set_nlink(&ip->i_inode, be32_to_cpu(str->di_nlink));
+ i_size_write(&ip->i_inode, be64_to_cpu(str->di_size));
+ gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
+ atime.tv_sec = be64_to_cpu(str->di_atime);
+ atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
+ if (timespec_compare(&ip->i_inode.i_atime, &atime) < 0)
+ ip->i_inode.i_atime = atime;
+ ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
+ ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
+ ip->i_inode.i_ctime.tv_sec = be64_to_cpu(str->di_ctime);
+ ip->i_inode.i_ctime.tv_nsec = be32_to_cpu(str->di_ctime_nsec);
+
+ ip->i_goal = be64_to_cpu(str->di_goal_meta);
+ ip->i_generation = be64_to_cpu(str->di_generation);
+
+ ip->i_diskflags = be32_to_cpu(str->di_flags);
+ gfs2_set_inode_flags(&ip->i_inode);
+ height = be16_to_cpu(str->di_height);
+ if (unlikely(height > GFS2_MAX_META_HEIGHT))
+ goto corrupt;
+ ip->i_height = (u8)height;
+
+ depth = be16_to_cpu(str->di_depth);
+ if (unlikely(depth > GFS2_DIR_MAX_DEPTH))
+ goto corrupt;
+ ip->i_depth = (u8)depth;
+ ip->i_entries = be32_to_cpu(str->di_entries);
+
+ ip->i_eattr = be64_to_cpu(str->di_eattr);
+ if (S_ISREG(ip->i_inode.i_mode))
+ gfs2_set_aops(&ip->i_inode);
+
+ return 0;
+corrupt:
+ gfs2_consist_inode(ip);
+ return -EIO;
+}
+
+/**
+ * gfs2_inode_refresh - Refresh the incore copy of the dinode
+ * @ip: The GFS2 inode
+ *
+ * Returns: errno
+ */
+
+int gfs2_inode_refresh(struct gfs2_inode *ip)
+{
+ struct buffer_head *dibh;
+ int error;
+
+ error = gfs2_meta_inode_buffer(ip, &dibh);
+ if (error)
+ return error;
+
+ if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), dibh, GFS2_METATYPE_DI)) {
+ brelse(dibh);
+ return -EIO;
+ }
+
+ error = gfs2_dinode_in(ip, dibh->b_data);
+ brelse(dibh);
+ clear_bit(GIF_INVALID, &ip->i_flags);
+
+ return error;
+}
+
+/**
* inode_go_lock - operation done after an inode lock is locked by a process
* @gl: the glock
* @flags:
@@ -272,19 +425,6 @@ static int inode_go_dump(struct seq_file *seq, const struct gfs2_glock *gl)
}
/**
- * rgrp_go_demote_ok - Check to see if it's ok to unlock a RG's glock
- * @gl: the glock
- *
- * Returns: 1 if it's ok
- */
-
-static int rgrp_go_demote_ok(const struct gfs2_glock *gl)
-{
- const struct address_space *mapping = (const struct address_space *)(gl + 1);
- return !mapping->nrpages;
-}
-
-/**
* rgrp_go_lock - operation done after an rgrp lock is locked by
* a first holder on this node.
* @gl: the glock
@@ -383,6 +523,10 @@ static int trans_go_demote_ok(const struct gfs2_glock *gl)
static void iopen_go_callback(struct gfs2_glock *gl)
{
struct gfs2_inode *ip = (struct gfs2_inode *)gl->gl_object;
+ struct gfs2_sbd *sdp = gl->gl_sbd;
+
+ if (sdp->sd_vfs->s_flags & MS_RDONLY)
+ return;
if (gl->gl_demote_state == LM_ST_UNLOCKED &&
gl->gl_state == LM_ST_SHARED && ip) {
@@ -410,7 +554,6 @@ const struct gfs2_glock_operations gfs2_inode_glops = {
const struct gfs2_glock_operations gfs2_rgrp_glops = {
.go_xmote_th = rgrp_go_sync,
.go_inval = rgrp_go_inval,
- .go_demote_ok = rgrp_go_demote_ok,
.go_lock = rgrp_go_lock,
.go_unlock = rgrp_go_unlock,
.go_dump = gfs2_rgrp_dump,
diff --git a/fs/gfs2/glops.h b/fs/gfs2/glops.h
index b3aa2e3210f..6fce409b5a5 100644
--- a/fs/gfs2/glops.h
+++ b/fs/gfs2/glops.h
@@ -23,4 +23,6 @@ extern const struct gfs2_glock_operations gfs2_quota_glops;
extern const struct gfs2_glock_operations gfs2_journal_glops;
extern const struct gfs2_glock_operations *gfs2_glops_list[];
+extern void gfs2_ail_flush(struct gfs2_glock *gl);
+
#endif /* __GLOPS_DOT_H__ */
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index a79790c0627..0a064e91ac7 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -15,10 +15,11 @@
#include <linux/workqueue.h>
#include <linux/dlm.h>
#include <linux/buffer_head.h>
+#include <linux/rcupdate.h>
+#include <linux/rculist_bl.h>
#define DIO_WAIT 0x00000010
#define DIO_METADATA 0x00000020
-#define DIO_ALL 0x00000100
struct gfs2_log_operations;
struct gfs2_log_element;
@@ -198,10 +199,12 @@ enum {
GLF_INITIAL = 10,
GLF_FROZEN = 11,
GLF_QUEUED = 12,
+ GLF_LRU = 13,
+ GLF_OBJECT = 14, /* Used only for tracing */
};
struct gfs2_glock {
- struct hlist_node gl_list;
+ struct hlist_bl_node gl_list;
unsigned long gl_flags; /* GLF_... */
struct lm_lockname gl_name;
atomic_t gl_ref;
@@ -232,8 +235,10 @@ struct gfs2_glock {
struct list_head gl_ail_list;
atomic_t gl_ail_count;
+ atomic_t gl_revokes;
struct delayed_work gl_work;
struct work_struct gl_delete;
+ struct rcu_head gl_rcu;
};
#define GFS2_MIN_LVB_SIZE 32 /* Min size of LVB that gfs2 supports */
@@ -314,6 +319,7 @@ enum {
QDF_USER = 0,
QDF_CHANGE = 1,
QDF_LOCKED = 2,
+ QDF_REFRESH = 3,
};
struct gfs2_quota_data {
@@ -370,8 +376,6 @@ struct gfs2_ail {
unsigned int ai_first;
struct list_head ai_ail1_list;
struct list_head ai_ail2_list;
-
- u64 ai_sync_gen;
};
struct gfs2_journal_extent {
@@ -484,7 +488,6 @@ struct gfs2_sb_host {
char sb_lockproto[GFS2_LOCKNAME_LEN];
char sb_locktable[GFS2_LOCKNAME_LEN];
- u8 sb_uuid[16];
};
/*
@@ -647,9 +650,9 @@ struct gfs2_sbd {
unsigned int sd_log_flush_head;
u64 sd_log_flush_wrapped;
+ spinlock_t sd_ail_lock;
struct list_head sd_ail1_list;
struct list_head sd_ail2_list;
- u64 sd_ail_sync_gen;
/* Replay stuff */
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index 7aa7d4f8984..03e0c529063 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -1,23 +1,25 @@
/*
* Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
- * Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
+ * Copyright (C) 2004-2011 Red Hat, Inc. All rights reserved.
*
* This copyrighted material is made available to anyone wishing to use,
* modify, copy, or redistribute it subject to the terms and conditions
* of the GNU General Public License version 2.
*/
-#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
+#include <linux/namei.h>
+#include <linux/mm.h>
+#include <linux/xattr.h>
#include <linux/posix_acl.h>
-#include <linux/sort.h>
#include <linux/gfs2_ondisk.h>
#include <linux/crc32.h>
+#include <linux/fiemap.h>
#include <linux/security.h>
-#include <linux/time.h>
+#include <asm/uaccess.h>
#include "gfs2.h"
#include "incore.h"
@@ -26,51 +28,70 @@
#include "dir.h"
#include "xattr.h"
#include "glock.h"
-#include "glops.h"
#include "inode.h"
-#include "log.h"
#include "meta_io.h"
#include "quota.h"
#include "rgrp.h"
#include "trans.h"
#include "util.h"
+#include "super.h"
+#include "glops.h"
-struct gfs2_inum_range_host {
- u64 ir_start;
- u64 ir_length;
+struct gfs2_skip_data {
+ u64 no_addr;
+ int skipped;
+ int non_block;
};
static int iget_test(struct inode *inode, void *opaque)
{
struct gfs2_inode *ip = GFS2_I(inode);
- u64 *no_addr = opaque;
+ struct gfs2_skip_data *data = opaque;
- if (ip->i_no_addr == *no_addr)
+ if (ip->i_no_addr == data->no_addr) {
+ if (data->non_block &&
+ inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE)) {
+ data->skipped = 1;
+ return 0;
+ }
return 1;
-
+ }
return 0;
}
static int iget_set(struct inode *inode, void *opaque)
{
struct gfs2_inode *ip = GFS2_I(inode);
- u64 *no_addr = opaque;
+ struct gfs2_skip_data *data = opaque;
- inode->i_ino = (unsigned long)*no_addr;
- ip->i_no_addr = *no_addr;
+ if (data->skipped)
+ return -ENOENT;
+ inode->i_ino = (unsigned long)(data->no_addr);
+ ip->i_no_addr = data->no_addr;
return 0;
}
-struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr)
+struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr, int non_block)
{
unsigned long hash = (unsigned long)no_addr;
- return ilookup5(sb, hash, iget_test, &no_addr);
+ struct gfs2_skip_data data;
+
+ data.no_addr = no_addr;
+ data.skipped = 0;
+ data.non_block = non_block;
+ return ilookup5(sb, hash, iget_test, &data);
}
-static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr)
+static struct inode *gfs2_iget(struct super_block *sb, u64 no_addr,
+ int non_block)
{
+ struct gfs2_skip_data data;
unsigned long hash = (unsigned long)no_addr;
- return iget5_locked(sb, hash, iget_test, iget_set, &no_addr);
+
+ data.no_addr = no_addr;
+ data.skipped = 0;
+ data.non_block = non_block;
+ return iget5_locked(sb, hash, iget_test, iget_set, &data);
}
/**
@@ -111,19 +132,20 @@ static void gfs2_set_iop(struct inode *inode)
* @sb: The super block
* @no_addr: The inode number
* @type: The type of the inode
+ * non_block: Can we block on inodes that are being freed?
*
* Returns: A VFS inode, or an error
*/
struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
- u64 no_addr, u64 no_formal_ino)
+ u64 no_addr, u64 no_formal_ino, int non_block)
{
struct inode *inode;
struct gfs2_inode *ip;
struct gfs2_glock *io_gl = NULL;
int error;
- inode = gfs2_iget(sb, no_addr);
+ inode = gfs2_iget(sb, no_addr, non_block);
ip = GFS2_I(inode);
if (!inode)
@@ -185,11 +207,12 @@ struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
{
struct super_block *sb = sdp->sd_vfs;
struct gfs2_holder i_gh;
- struct inode *inode;
+ struct inode *inode = NULL;
int error;
+ /* Must not read in block until block type is verified */
error = gfs2_glock_nq_num(sdp, no_addr, &gfs2_inode_glops,
- LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+ LM_ST_EXCLUSIVE, GL_SKIP, &i_gh);
if (error)
return ERR_PTR(error);
@@ -197,7 +220,7 @@ struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
if (error)
goto fail;
- inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0);
+ inode = gfs2_inode_lookup(sb, DT_UNKNOWN, no_addr, 0, 1);
if (IS_ERR(inode))
goto fail;
@@ -222,203 +245,6 @@ fail_iput:
goto fail;
}
-static int gfs2_dinode_in(struct gfs2_inode *ip, const void *buf)
-{
- const struct gfs2_dinode *str = buf;
- struct timespec atime;
- u16 height, depth;
-
- if (unlikely(ip->i_no_addr != be64_to_cpu(str->di_num.no_addr)))
- goto corrupt;
- ip->i_no_formal_ino = be64_to_cpu(str->di_num.no_formal_ino);
- ip->i_inode.i_mode = be32_to_cpu(str->di_mode);
- ip->i_inode.i_rdev = 0;
- switch (ip->i_inode.i_mode & S_IFMT) {
- case S_IFBLK:
- case S_IFCHR:
- ip->i_inode.i_rdev = MKDEV(be32_to_cpu(str->di_major),
- be32_to_cpu(str->di_minor));
- break;
- };
-
- ip->i_inode.i_uid = be32_to_cpu(str->di_uid);
- ip->i_inode.i_gid = be32_to_cpu(str->di_gid);
- /*
- * We will need to review setting the nlink count here in the
- * light of the forthcoming ro bind mount work. This is a reminder
- * to do that.
- */
- ip->i_inode.i_nlink = be32_to_cpu(str->di_nlink);
- i_size_write(&ip->i_inode, be64_to_cpu(str->di_size));
- gfs2_set_inode_blocks(&ip->i_inode, be64_to_cpu(str->di_blocks));
- atime.tv_sec = be64_to_cpu(str->di_atime);
- atime.tv_nsec = be32_to_cpu(str->di_atime_nsec);
- if (timespec_compare(&ip->i_inode.i_atime, &atime) < 0)
- ip->i_inode.i_atime = atime;
- ip->i_inode.i_mtime.tv_sec = be64_to_cpu(str->di_mtime);
- ip->i_inode.i_mtime.tv_nsec = be32_to_cpu(str->di_mtime_nsec);
- ip->i_inode.i_ctime.tv_sec = be64_to_cpu(str->di_ctime);
- ip->i_inode.i_ctime.tv_nsec = be32_to_cpu(str->di_ctime_nsec);
-
- ip->i_goal = be64_to_cpu(str->di_goal_meta);
- ip->i_generation = be64_to_cpu(str->di_generation);
-
- ip->i_diskflags = be32_to_cpu(str->di_flags);
- gfs2_set_inode_flags(&ip->i_inode);
- height = be16_to_cpu(str->di_height);
- if (unlikely(height > GFS2_MAX_META_HEIGHT))
- goto corrupt;
- ip->i_height = (u8)height;
-
- depth = be16_to_cpu(str->di_depth);
- if (unlikely(depth > GFS2_DIR_MAX_DEPTH))
- goto corrupt;
- ip->i_depth = (u8)depth;
- ip->i_entries = be32_to_cpu(str->di_entries);
-
- ip->i_eattr = be64_to_cpu(str->di_eattr);
- if (S_ISREG(ip->i_inode.i_mode))
- gfs2_set_aops(&ip->i_inode);
-
- return 0;
-corrupt:
- if (gfs2_consist_inode(ip))
- gfs2_dinode_print(ip);
- return -EIO;
-}
-
-/**
- * gfs2_inode_refresh - Refresh the incore copy of the dinode
- * @ip: The GFS2 inode
- *
- * Returns: errno
- */
-
-int gfs2_inode_refresh(struct gfs2_inode *ip)
-{
- struct buffer_head *dibh;
- int error;
-
- error = gfs2_meta_inode_buffer(ip, &dibh);
- if (error)
- return error;
-
- if (gfs2_metatype_check(GFS2_SB(&ip->i_inode), dibh, GFS2_METATYPE_DI)) {
- brelse(dibh);
- return -EIO;
- }
-
- error = gfs2_dinode_in(ip, dibh->b_data);
- brelse(dibh);
- clear_bit(GIF_INVALID, &ip->i_flags);
-
- return error;
-}
-
-int gfs2_dinode_dealloc(struct gfs2_inode *ip)
-{
- struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
- struct gfs2_alloc *al;
- struct gfs2_rgrpd *rgd;
- int error;
-
- if (gfs2_get_inode_blocks(&ip->i_inode) != 1) {
- if (gfs2_consist_inode(ip))
- gfs2_dinode_print(ip);
- return -EIO;
- }
-
- al = gfs2_alloc_get(ip);
- if (!al)
- return -ENOMEM;
-
- error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
- if (error)
- goto out;
-
- error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
- if (error)
- goto out_qs;
-
- rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
- if (!rgd) {
- gfs2_consist_inode(ip);
- error = -EIO;
- goto out_rindex_relse;
- }
-
- error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0,
- &al->al_rgd_gh);
- if (error)
- goto out_rindex_relse;
-
- error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA, 1);
- if (error)
- goto out_rg_gunlock;
-
- set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
- set_bit(GLF_LFLUSH, &ip->i_gl->gl_flags);
-
- gfs2_free_di(rgd, ip);
-
- gfs2_trans_end(sdp);
-
-out_rg_gunlock:
- gfs2_glock_dq_uninit(&al->al_rgd_gh);
-out_rindex_relse:
- gfs2_glock_dq_uninit(&al->al_ri_gh);
-out_qs:
- gfs2_quota_unhold(ip);
-out:
- gfs2_alloc_put(ip);
- return error;
-}
-
-/**
- * gfs2_change_nlink - Change nlink count on inode
- * @ip: The GFS2 inode
- * @diff: The change in the nlink count required
- *
- * Returns: errno
- */
-int gfs2_change_nlink(struct gfs2_inode *ip, int diff)
-{
- struct buffer_head *dibh;
- u32 nlink;
- int error;
-
- BUG_ON(diff != 1 && diff != -1);
- nlink = ip->i_inode.i_nlink + diff;
-
- /* If we are reducing the nlink count, but the new value ends up being
- bigger than the old one, we must have underflowed. */
- if (diff < 0 && nlink > ip->i_inode.i_nlink) {
- if (gfs2_consist_inode(ip))
- gfs2_dinode_print(ip);
- return -EIO;
- }
-
- error = gfs2_meta_inode_buffer(ip, &dibh);
- if (error)
- return error;
-
- if (diff > 0)
- inc_nlink(&ip->i_inode);
- else
- drop_nlink(&ip->i_inode);
-
- ip->i_inode.i_ctime = CURRENT_TIME;
-
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
- gfs2_dinode_out(ip, dibh->b_data);
- brelse(dibh);
- mark_inode_dirty(&ip->i_inode);
-
- if (ip->i_inode.i_nlink == 0)
- gfs2_unlink_di(&ip->i_inode); /* mark inode unlinked */
-
- return error;
-}
struct inode *gfs2_lookup_simple(struct inode *dip, const char *name)
{
@@ -517,7 +343,7 @@ static int create_ok(struct gfs2_inode *dip, const struct qstr *name,
/* Don't create entries in an unlinked directory */
if (!dip->i_inode.i_nlink)
- return -EPERM;
+ return -ENOENT;
error = gfs2_dir_check(&dip->i_inode, name, NULL);
switch (error) {
@@ -587,21 +413,44 @@ out:
return error;
}
+static void gfs2_init_dir(struct buffer_head *dibh,
+ const struct gfs2_inode *parent)
+{
+ struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
+ struct gfs2_dirent *dent = (struct gfs2_dirent *)(di+1);
+
+ gfs2_qstr2dirent(&gfs2_qdot, GFS2_DIRENT_SIZE(gfs2_qdot.len), dent);
+ dent->de_inum = di->di_num; /* already GFS2 endian */
+ dent->de_type = cpu_to_be16(DT_DIR);
+
+ dent = (struct gfs2_dirent *)((char*)dent + GFS2_DIRENT_SIZE(1));
+ gfs2_qstr2dirent(&gfs2_qdotdot, dibh->b_size - GFS2_DIRENT_SIZE(1) - sizeof(struct gfs2_dinode), dent);
+ gfs2_inum_out(parent, dent);
+ dent->de_type = cpu_to_be16(DT_DIR);
+
+}
+
/**
* init_dinode - Fill in a new dinode structure
- * @dip: the directory this inode is being created in
+ * @dip: The directory this inode is being created in
* @gl: The glock covering the new inode
- * @inum: the inode number
- * @mode: the file permissions
- * @uid:
- * @gid:
+ * @inum: The inode number
+ * @mode: The file permissions
+ * @uid: The uid of the new inode
+ * @gid: The gid of the new inode
+ * @generation: The generation number of the new inode
+ * @dev: The device number (if a device node)
+ * @symname: The symlink destination (if a symlink)
+ * @size: The inode size (ignored for directories)
+ * @bhp: The buffer head (returned to caller)
*
*/
static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
const struct gfs2_inum_host *inum, unsigned int mode,
unsigned int uid, unsigned int gid,
- const u64 *generation, dev_t dev, struct buffer_head **bhp)
+ const u64 *generation, dev_t dev, const char *symname,
+ unsigned size, struct buffer_head **bhp)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_dinode *di;
@@ -620,7 +469,7 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
di->di_uid = cpu_to_be32(uid);
di->di_gid = cpu_to_be32(gid);
di->di_nlink = 0;
- di->di_size = 0;
+ di->di_size = cpu_to_be64(size);
di->di_blocks = cpu_to_be64(1);
di->di_atime = di->di_mtime = di->di_ctime = cpu_to_be64(tv.tv_sec);
di->di_major = cpu_to_be32(MAJOR(dev));
@@ -628,16 +477,6 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
di->di_goal_meta = di->di_goal_data = cpu_to_be64(inum->no_addr);
di->di_generation = cpu_to_be64(*generation);
di->di_flags = 0;
-
- if (S_ISREG(mode)) {
- if ((dip->i_diskflags & GFS2_DIF_INHERIT_JDATA) ||
- gfs2_tune_get(sdp, gt_new_files_jdata))
- di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
- } else if (S_ISDIR(mode)) {
- di->di_flags |= cpu_to_be32(dip->i_diskflags &
- GFS2_DIF_INHERIT_JDATA);
- }
-
di->__pad1 = 0;
di->di_payload_format = cpu_to_be32(S_ISDIR(mode) ? GFS2_FORMAT_DE : 0);
di->di_height = 0;
@@ -651,7 +490,26 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
di->di_mtime_nsec = cpu_to_be32(tv.tv_nsec);
di->di_ctime_nsec = cpu_to_be32(tv.tv_nsec);
memset(&di->di_reserved, 0, sizeof(di->di_reserved));
-
+
+ switch(mode & S_IFMT) {
+ case S_IFREG:
+ if ((dip->i_diskflags & GFS2_DIF_INHERIT_JDATA) ||
+ gfs2_tune_get(sdp, gt_new_files_jdata))
+ di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
+ break;
+ case S_IFDIR:
+ di->di_flags |= cpu_to_be32(dip->i_diskflags &
+ GFS2_DIF_INHERIT_JDATA);
+ di->di_flags |= cpu_to_be32(GFS2_DIF_JDATA);
+ di->di_size = cpu_to_be64(sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode));
+ di->di_entries = cpu_to_be32(2);
+ gfs2_init_dir(dibh, dip);
+ break;
+ case S_IFLNK:
+ memcpy(dibh->b_data + sizeof(struct gfs2_dinode), symname, size);
+ break;
+ }
+
set_buffer_uptodate(dibh);
*bhp = dibh;
@@ -659,7 +517,8 @@ static void init_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
static int make_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
unsigned int mode, const struct gfs2_inum_host *inum,
- const u64 *generation, dev_t dev, struct buffer_head **bhp)
+ const u64 *generation, dev_t dev, const char *symname,
+ unsigned int size, struct buffer_head **bhp)
{
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
unsigned int uid, gid;
@@ -681,7 +540,7 @@ static int make_dinode(struct gfs2_inode *dip, struct gfs2_glock *gl,
if (error)
goto out_quota;
- init_dinode(dip, gl, inum, mode, uid, gid, generation, dev, bhp);
+ init_dinode(dip, gl, inum, mode, uid, gid, generation, dev, symname, size, bhp);
gfs2_quota_change(dip, +1, uid, gid);
gfs2_trans_end(sdp);
@@ -735,14 +594,16 @@ static int link_dinode(struct gfs2_inode *dip, const struct qstr *name,
goto fail_quota_locks;
}
- error = gfs2_dir_add(&dip->i_inode, name, ip, IF2DT(ip->i_inode.i_mode));
+ error = gfs2_dir_add(&dip->i_inode, name, ip);
if (error)
goto fail_end_trans;
error = gfs2_meta_inode_buffer(ip, &dibh);
if (error)
goto fail_end_trans;
- ip->i_inode.i_nlink = 1;
+ inc_nlink(&ip->i_inode);
+ if (S_ISDIR(ip->i_inode.i_mode))
+ inc_nlink(&ip->i_inode);
gfs2_trans_add_bh(ip->i_gl, dibh, 1);
gfs2_dinode_out(ip, dibh->b_data);
brelse(dibh);
@@ -763,14 +624,15 @@ fail:
return error;
}
-static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip)
+static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip,
+ const struct qstr *qstr)
{
int err;
size_t len;
void *value;
char *name;
- err = security_inode_init_security(&ip->i_inode, &dip->i_inode,
+ err = security_inode_init_security(&ip->i_inode, &dip->i_inode, qstr,
&name, &value, &len);
if (err) {
@@ -788,27 +650,25 @@ static int gfs2_security_init(struct gfs2_inode *dip, struct gfs2_inode *ip)
}
/**
- * gfs2_createi - Create a new inode
- * @ghs: An array of two holders
- * @name: The name of the new file
- * @mode: the permissions on the new inode
+ * gfs2_create_inode - Create a new inode
+ * @dir: The parent directory
+ * @dentry: The new dentry
+ * @mode: The permissions on the new inode
+ * @dev: For device nodes, this is the device number
+ * @symname: For symlinks, this is the link destination
+ * @size: The initial size of the inode (ignored for directories)
*
- * @ghs[0] is an initialized holder for the directory
- * @ghs[1] is the holder for the inode lock
- *
- * If the return value is not NULL, the glocks on both the directory and the new
- * file are held. A transaction has been started and an inplace reservation
- * is held, as well.
- *
- * Returns: An inode
+ * Returns: 0 on success, or error code
*/
-struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
- unsigned int mode, dev_t dev)
+static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
+ unsigned int mode, dev_t dev, const char *symname,
+ unsigned int size)
{
+ const struct qstr *name = &dentry->d_name;
+ struct gfs2_holder ghs[2];
struct inode *inode = NULL;
- struct gfs2_inode *dip = ghs->gh_gl->gl_object;
- struct inode *dir = &dip->i_inode;
+ struct gfs2_inode *dip = GFS2_I(dir);
struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
struct gfs2_inum_host inum = { .no_addr = 0, .no_formal_ino = 0 };
int error;
@@ -816,10 +676,9 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
struct buffer_head *bh = NULL;
if (!name->len || name->len > GFS2_FNAMESIZE)
- return ERR_PTR(-ENAMETOOLONG);
+ return -ENAMETOOLONG;
- gfs2_holder_reinit(LM_ST_EXCLUSIVE, 0, ghs);
- error = gfs2_glock_nq(ghs);
+ error = gfs2_glock_nq_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
if (error)
goto fail;
@@ -837,12 +696,12 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
if (error)
goto fail_gunlock;
- error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev, &bh);
+ error = make_dinode(dip, ghs[1].gh_gl, mode, &inum, &generation, dev, symname, size, &bh);
if (error)
goto fail_gunlock2;
inode = gfs2_inode_lookup(dir->i_sb, IF2DT(mode), inum.no_addr,
- inum.no_formal_ino);
+ inum.no_formal_ino, 0);
if (IS_ERR(inode))
goto fail_gunlock2;
@@ -854,7 +713,7 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
if (error)
goto fail_gunlock2;
- error = gfs2_security_init(dip, GFS2_I(inode));
+ error = gfs2_security_init(dip, GFS2_I(inode), name);
if (error)
goto fail_gunlock2;
@@ -864,18 +723,852 @@ struct inode *gfs2_createi(struct gfs2_holder *ghs, const struct qstr *name,
if (bh)
brelse(bh);
- return inode;
+
+ gfs2_trans_end(sdp);
+ if (dip->i_alloc->al_rgd)
+ gfs2_inplace_release(dip);
+ gfs2_quota_unlock(dip);
+ gfs2_alloc_put(dip);
+ gfs2_glock_dq_uninit_m(2, ghs);
+ mark_inode_dirty(inode);
+ d_instantiate(dentry, inode);
+ return 0;
fail_gunlock2:
gfs2_glock_dq_uninit(ghs + 1);
if (inode && !IS_ERR(inode))
iput(inode);
fail_gunlock:
- gfs2_glock_dq(ghs);
+ gfs2_glock_dq_uninit(ghs);
fail:
if (bh)
brelse(bh);
- return ERR_PTR(error);
+ return error;
+}
+
+/**
+ * gfs2_create - Create a file
+ * @dir: The directory in which to create the file
+ * @dentry: The dentry of the new file
+ * @mode: The mode of the new file
+ *
+ * Returns: errno
+ */
+
+static int gfs2_create(struct inode *dir, struct dentry *dentry,
+ int mode, struct nameidata *nd)
+{
+ struct inode *inode;
+ int ret;
+
+ for (;;) {
+ ret = gfs2_create_inode(dir, dentry, S_IFREG | mode, 0, NULL, 0);
+ if (ret != -EEXIST || (nd && (nd->flags & LOOKUP_EXCL)))
+ return ret;
+
+ inode = gfs2_lookupi(dir, &dentry->d_name, 0);
+ if (inode) {
+ if (!IS_ERR(inode))
+ break;
+ return PTR_ERR(inode);
+ }
+ }
+
+ d_instantiate(dentry, inode);
+ return 0;
+}
+
+/**
+ * gfs2_lookup - Look up a filename in a directory and return its inode
+ * @dir: The directory inode
+ * @dentry: The dentry of the new inode
+ * @nd: passed from Linux VFS, ignored by us
+ *
+ * Called by the VFS layer. Lock dir and call gfs2_lookupi()
+ *
+ * Returns: errno
+ */
+
+static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
+ struct nameidata *nd)
+{
+ struct inode *inode = NULL;
+
+ inode = gfs2_lookupi(dir, &dentry->d_name, 0);
+ if (inode && IS_ERR(inode))
+ return ERR_CAST(inode);
+
+ if (inode) {
+ struct gfs2_glock *gl = GFS2_I(inode)->i_gl;
+ struct gfs2_holder gh;
+ int error;
+ error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
+ if (error) {
+ iput(inode);
+ return ERR_PTR(error);
+ }
+ gfs2_glock_dq_uninit(&gh);
+ return d_splice_alias(inode, dentry);
+ }
+ d_add(dentry, inode);
+
+ return NULL;
+}
+
+/**
+ * gfs2_link - Link to a file
+ * @old_dentry: The inode to link
+ * @dir: Add link to this directory
+ * @dentry: The name of the link
+ *
+ * Link the inode in "old_dentry" into the directory "dir" with the
+ * name in "dentry".
+ *
+ * Returns: errno
+ */
+
+static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
+ struct dentry *dentry)
+{
+ struct gfs2_inode *dip = GFS2_I(dir);
+ struct gfs2_sbd *sdp = GFS2_SB(dir);
+ struct inode *inode = old_dentry->d_inode;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder ghs[2];
+ struct buffer_head *dibh;
+ int alloc_required;
+ int error;
+
+ if (S_ISDIR(inode->i_mode))
+ return -EPERM;
+
+ gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
+ gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
+
+ error = gfs2_glock_nq(ghs); /* parent */
+ if (error)
+ goto out_parent;
+
+ error = gfs2_glock_nq(ghs + 1); /* child */
+ if (error)
+ goto out_child;
+
+ error = -ENOENT;
+ if (inode->i_nlink == 0)
+ goto out_gunlock;
+
+ error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC, 0);
+ if (error)
+ goto out_gunlock;
+
+ error = gfs2_dir_check(dir, &dentry->d_name, NULL);
+ switch (error) {
+ case -ENOENT:
+ break;
+ case 0:
+ error = -EEXIST;
+ default:
+ goto out_gunlock;
+ }
+
+ error = -EINVAL;
+ if (!dip->i_inode.i_nlink)
+ goto out_gunlock;
+ error = -EFBIG;
+ if (dip->i_entries == (u32)-1)
+ goto out_gunlock;
+ error = -EPERM;
+ if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+ goto out_gunlock;
+ error = -EINVAL;
+ if (!ip->i_inode.i_nlink)
+ goto out_gunlock;
+ error = -EMLINK;
+ if (ip->i_inode.i_nlink == (u32)-1)
+ goto out_gunlock;
+
+ alloc_required = error = gfs2_diradd_alloc_required(dir, &dentry->d_name);
+ if (error < 0)
+ goto out_gunlock;
+ error = 0;
+
+ if (alloc_required) {
+ struct gfs2_alloc *al = gfs2_alloc_get(dip);
+ if (!al) {
+ error = -ENOMEM;
+ goto out_gunlock;
+ }
+
+ error = gfs2_quota_lock_check(dip);
+ if (error)
+ goto out_alloc;
+
+ al->al_requested = sdp->sd_max_dirres;
+
+ error = gfs2_inplace_reserve(dip);
+ if (error)
+ goto out_gunlock_q;
+
+ error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
+ gfs2_rg_blocks(al) +
+ 2 * RES_DINODE + RES_STATFS +
+ RES_QUOTA, 0);
+ if (error)
+ goto out_ipres;
+ } else {
+ error = gfs2_trans_begin(sdp, 2 * RES_DINODE + RES_LEAF, 0);
+ if (error)
+ goto out_ipres;
+ }
+
+ error = gfs2_meta_inode_buffer(ip, &dibh);
+ if (error)
+ goto out_end_trans;
+
+ error = gfs2_dir_add(dir, &dentry->d_name, ip);
+ if (error)
+ goto out_brelse;
+
+ gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ inc_nlink(&ip->i_inode);
+ ip->i_inode.i_ctime = CURRENT_TIME;
+ gfs2_dinode_out(ip, dibh->b_data);
+ mark_inode_dirty(&ip->i_inode);
+
+out_brelse:
+ brelse(dibh);
+out_end_trans:
+ gfs2_trans_end(sdp);
+out_ipres:
+ if (alloc_required)
+ gfs2_inplace_release(dip);
+out_gunlock_q:
+ if (alloc_required)
+ gfs2_quota_unlock(dip);
+out_alloc:
+ if (alloc_required)
+ gfs2_alloc_put(dip);
+out_gunlock:
+ gfs2_glock_dq(ghs + 1);
+out_child:
+ gfs2_glock_dq(ghs);
+out_parent:
+ gfs2_holder_uninit(ghs);
+ gfs2_holder_uninit(ghs + 1);
+ if (!error) {
+ ihold(inode);
+ d_instantiate(dentry, inode);
+ mark_inode_dirty(inode);
+ }
+ return error;
+}
+
+/*
+ * gfs2_unlink_ok - check to see that a inode is still in a directory
+ * @dip: the directory
+ * @name: the name of the file
+ * @ip: the inode
+ *
+ * Assumes that the lock on (at least) @dip is held.
+ *
+ * Returns: 0 if the parent/child relationship is correct, errno if it isn't
+ */
+
+static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
+ const struct gfs2_inode *ip)
+{
+ int error;
+
+ if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
+ return -EPERM;
+
+ if ((dip->i_inode.i_mode & S_ISVTX) &&
+ dip->i_inode.i_uid != current_fsuid() &&
+ ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER))
+ return -EPERM;
+
+ if (IS_APPEND(&dip->i_inode))
+ return -EPERM;
+
+ error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC, 0);
+ if (error)
+ return error;
+
+ error = gfs2_dir_check(&dip->i_inode, name, ip);
+ if (error)
+ return error;
+
+ return 0;
+}
+
+/**
+ * gfs2_unlink_inode - Removes an inode from its parent dir and unlinks it
+ * @dip: The parent directory
+ * @name: The name of the entry in the parent directory
+ * @bh: The inode buffer for the inode to be removed
+ * @inode: The inode to be removed
+ *
+ * Called with all the locks and in a transaction. This will only be
+ * called for a directory after it has been checked to ensure it is empty.
+ *
+ * Returns: 0 on success, or an error
+ */
+
+static int gfs2_unlink_inode(struct gfs2_inode *dip,
+ const struct dentry *dentry,
+ struct buffer_head *bh)
+{
+ struct inode *inode = dentry->d_inode;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ int error;
+
+ error = gfs2_dir_del(dip, dentry);
+ if (error)
+ return error;
+
+ ip->i_entries = 0;
+ inode->i_ctime = CURRENT_TIME;
+ if (S_ISDIR(inode->i_mode))
+ clear_nlink(inode);
+ else
+ drop_nlink(inode);
+ gfs2_trans_add_bh(ip->i_gl, bh, 1);
+ gfs2_dinode_out(ip, bh->b_data);
+ mark_inode_dirty(inode);
+ if (inode->i_nlink == 0)
+ gfs2_unlink_di(inode);
+ return 0;
+}
+
+
+/**
+ * gfs2_unlink - Unlink an inode (this does rmdir as well)
+ * @dir: The inode of the directory containing the inode to unlink
+ * @dentry: The file itself
+ *
+ * This routine uses the type of the inode as a flag to figure out
+ * whether this is an unlink or an rmdir.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
+{
+ struct gfs2_inode *dip = GFS2_I(dir);
+ struct gfs2_sbd *sdp = GFS2_SB(dir);
+ struct inode *inode = dentry->d_inode;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct buffer_head *bh;
+ struct gfs2_holder ghs[3];
+ struct gfs2_rgrpd *rgd;
+ struct gfs2_holder ri_gh;
+ int error;
+
+ error = gfs2_rindex_hold(sdp, &ri_gh);
+ if (error)
+ return error;
+
+ gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
+ gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
+
+ rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
+ gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
+
+
+ error = gfs2_glock_nq(ghs); /* parent */
+ if (error)
+ goto out_parent;
+
+ error = gfs2_glock_nq(ghs + 1); /* child */
+ if (error)
+ goto out_child;
+
+ error = -ENOENT;
+ if (inode->i_nlink == 0)
+ goto out_rgrp;
+
+ if (S_ISDIR(inode->i_mode)) {
+ error = -ENOTEMPTY;
+ if (ip->i_entries > 2 || inode->i_nlink > 2)
+ goto out_rgrp;
+ }
+
+ error = gfs2_glock_nq(ghs + 2); /* rgrp */
+ if (error)
+ goto out_rgrp;
+
+ error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
+ if (error)
+ goto out_gunlock;
+
+ error = gfs2_trans_begin(sdp, 2*RES_DINODE + 3*RES_LEAF + RES_RG_BIT, 0);
+ if (error)
+ goto out_gunlock;
+
+ error = gfs2_meta_inode_buffer(ip, &bh);
+ if (error)
+ goto out_end_trans;
+
+ error = gfs2_unlink_inode(dip, dentry, bh);
+ brelse(bh);
+
+out_end_trans:
+ gfs2_trans_end(sdp);
+out_gunlock:
+ gfs2_glock_dq(ghs + 2);
+out_rgrp:
+ gfs2_holder_uninit(ghs + 2);
+ gfs2_glock_dq(ghs + 1);
+out_child:
+ gfs2_holder_uninit(ghs + 1);
+ gfs2_glock_dq(ghs);
+out_parent:
+ gfs2_holder_uninit(ghs);
+ gfs2_glock_dq_uninit(&ri_gh);
+ return error;
+}
+
+/**
+ * gfs2_symlink - Create a symlink
+ * @dir: The directory to create the symlink in
+ * @dentry: The dentry to put the symlink in
+ * @symname: The thing which the link points to
+ *
+ * Returns: errno
+ */
+
+static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
+ const char *symname)
+{
+ struct gfs2_sbd *sdp = GFS2_SB(dir);
+ unsigned int size;
+
+ size = strlen(symname);
+ if (size > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode) - 1)
+ return -ENAMETOOLONG;
+
+ return gfs2_create_inode(dir, dentry, S_IFLNK | S_IRWXUGO, 0, symname, size);
+}
+
+/**
+ * gfs2_mkdir - Make a directory
+ * @dir: The parent directory of the new one
+ * @dentry: The dentry of the new directory
+ * @mode: The mode of the new directory
+ *
+ * Returns: errno
+ */
+
+static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+{
+ return gfs2_create_inode(dir, dentry, S_IFDIR | mode, 0, NULL, 0);
+}
+
+/**
+ * gfs2_mknod - Make a special file
+ * @dir: The directory in which the special file will reside
+ * @dentry: The dentry of the special file
+ * @mode: The mode of the special file
+ * @dev: The device specification of the special file
+ *
+ */
+
+static int gfs2_mknod(struct inode *dir, struct dentry *dentry, int mode,
+ dev_t dev)
+{
+ return gfs2_create_inode(dir, dentry, mode, dev, NULL, 0);
+}
+
+/*
+ * gfs2_ok_to_move - check if it's ok to move a directory to another directory
+ * @this: move this
+ * @to: to here
+ *
+ * Follow @to back to the root and make sure we don't encounter @this
+ * Assumes we already hold the rename lock.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
+{
+ struct inode *dir = &to->i_inode;
+ struct super_block *sb = dir->i_sb;
+ struct inode *tmp;
+ int error = 0;
+
+ igrab(dir);
+
+ for (;;) {
+ if (dir == &this->i_inode) {
+ error = -EINVAL;
+ break;
+ }
+ if (dir == sb->s_root->d_inode) {
+ error = 0;
+ break;
+ }
+
+ tmp = gfs2_lookupi(dir, &gfs2_qdotdot, 1);
+ if (IS_ERR(tmp)) {
+ error = PTR_ERR(tmp);
+ break;
+ }
+
+ iput(dir);
+ dir = tmp;
+ }
+
+ iput(dir);
+
+ return error;
+}
+
+/**
+ * gfs2_rename - Rename a file
+ * @odir: Parent directory of old file name
+ * @odentry: The old dentry of the file
+ * @ndir: Parent directory of new file name
+ * @ndentry: The new dentry of the file
+ *
+ * Returns: errno
+ */
+
+static int gfs2_rename(struct inode *odir, struct dentry *odentry,
+ struct inode *ndir, struct dentry *ndentry)
+{
+ struct gfs2_inode *odip = GFS2_I(odir);
+ struct gfs2_inode *ndip = GFS2_I(ndir);
+ struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
+ struct gfs2_inode *nip = NULL;
+ struct gfs2_sbd *sdp = GFS2_SB(odir);
+ struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, }, ri_gh;
+ struct gfs2_rgrpd *nrgd;
+ unsigned int num_gh;
+ int dir_rename = 0;
+ int alloc_required = 0;
+ unsigned int x;
+ int error;
+
+ if (ndentry->d_inode) {
+ nip = GFS2_I(ndentry->d_inode);
+ if (ip == nip)
+ return 0;
+ }
+
+ error = gfs2_rindex_hold(sdp, &ri_gh);
+ if (error)
+ return error;
+
+ if (odip != ndip) {
+ error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE,
+ 0, &r_gh);
+ if (error)
+ goto out;
+
+ if (S_ISDIR(ip->i_inode.i_mode)) {
+ dir_rename = 1;
+ /* don't move a dirctory into it's subdir */
+ error = gfs2_ok_to_move(ip, ndip);
+ if (error)
+ goto out_gunlock_r;
+ }
+ }
+
+ num_gh = 1;
+ gfs2_holder_init(odip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
+ if (odip != ndip) {
+ gfs2_holder_init(ndip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
+ num_gh++;
+ }
+ gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
+ num_gh++;
+
+ if (nip) {
+ gfs2_holder_init(nip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
+ num_gh++;
+ /* grab the resource lock for unlink flag twiddling
+ * this is the case of the target file already existing
+ * so we unlink before doing the rename
+ */
+ nrgd = gfs2_blk2rgrpd(sdp, nip->i_no_addr);
+ if (nrgd)
+ gfs2_holder_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh++);
+ }
+
+ for (x = 0; x < num_gh; x++) {
+ error = gfs2_glock_nq(ghs + x);
+ if (error)
+ goto out_gunlock;
+ }
+
+ error = -ENOENT;
+ if (ip->i_inode.i_nlink == 0)
+ goto out_gunlock;
+
+ /* Check out the old directory */
+
+ error = gfs2_unlink_ok(odip, &odentry->d_name, ip);
+ if (error)
+ goto out_gunlock;
+
+ /* Check out the new directory */
+
+ if (nip) {
+ error = gfs2_unlink_ok(ndip, &ndentry->d_name, nip);
+ if (error)
+ goto out_gunlock;
+
+ if (nip->i_inode.i_nlink == 0) {
+ error = -EAGAIN;
+ goto out_gunlock;
+ }
+
+ if (S_ISDIR(nip->i_inode.i_mode)) {
+ if (nip->i_entries < 2) {
+ gfs2_consist_inode(nip);
+ error = -EIO;
+ goto out_gunlock;
+ }
+ if (nip->i_entries > 2) {
+ error = -ENOTEMPTY;
+ goto out_gunlock;
+ }
+ }
+ } else {
+ error = gfs2_permission(ndir, MAY_WRITE | MAY_EXEC, 0);
+ if (error)
+ goto out_gunlock;
+
+ error = gfs2_dir_check(ndir, &ndentry->d_name, NULL);
+ switch (error) {
+ case -ENOENT:
+ error = 0;
+ break;
+ case 0:
+ error = -EEXIST;
+ default:
+ goto out_gunlock;
+ };
+
+ if (odip != ndip) {
+ if (!ndip->i_inode.i_nlink) {
+ error = -ENOENT;
+ goto out_gunlock;
+ }
+ if (ndip->i_entries == (u32)-1) {
+ error = -EFBIG;
+ goto out_gunlock;
+ }
+ if (S_ISDIR(ip->i_inode.i_mode) &&
+ ndip->i_inode.i_nlink == (u32)-1) {
+ error = -EMLINK;
+ goto out_gunlock;
+ }
+ }
+ }
+
+ /* Check out the dir to be renamed */
+
+ if (dir_rename) {
+ error = gfs2_permission(odentry->d_inode, MAY_WRITE, 0);
+ if (error)
+ goto out_gunlock;
+ }
+
+ if (nip == NULL)
+ alloc_required = gfs2_diradd_alloc_required(ndir, &ndentry->d_name);
+ error = alloc_required;
+ if (error < 0)
+ goto out_gunlock;
+ error = 0;
+
+ if (alloc_required) {
+ struct gfs2_alloc *al = gfs2_alloc_get(ndip);
+ if (!al) {
+ error = -ENOMEM;
+ goto out_gunlock;
+ }
+
+ error = gfs2_quota_lock_check(ndip);
+ if (error)
+ goto out_alloc;
+
+ al->al_requested = sdp->sd_max_dirres;
+
+ error = gfs2_inplace_reserve_ri(ndip);
+ if (error)
+ goto out_gunlock_q;
+
+ error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
+ gfs2_rg_blocks(al) +
+ 4 * RES_DINODE + 4 * RES_LEAF +
+ RES_STATFS + RES_QUOTA + 4, 0);
+ if (error)
+ goto out_ipreserv;
+ } else {
+ error = gfs2_trans_begin(sdp, 4 * RES_DINODE +
+ 5 * RES_LEAF + 4, 0);
+ if (error)
+ goto out_gunlock;
+ }
+
+ /* Remove the target file, if it exists */
+
+ if (nip) {
+ struct buffer_head *bh;
+ error = gfs2_meta_inode_buffer(nip, &bh);
+ if (error)
+ goto out_end_trans;
+ error = gfs2_unlink_inode(ndip, ndentry, bh);
+ brelse(bh);
+ }
+
+ if (dir_rename) {
+ error = gfs2_dir_mvino(ip, &gfs2_qdotdot, ndip, DT_DIR);
+ if (error)
+ goto out_end_trans;
+ } else {
+ struct buffer_head *dibh;
+ error = gfs2_meta_inode_buffer(ip, &dibh);
+ if (error)
+ goto out_end_trans;
+ ip->i_inode.i_ctime = CURRENT_TIME;
+ gfs2_trans_add_bh(ip->i_gl, dibh, 1);
+ gfs2_dinode_out(ip, dibh->b_data);
+ brelse(dibh);
+ }
+
+ error = gfs2_dir_del(odip, odentry);
+ if (error)
+ goto out_end_trans;
+
+ error = gfs2_dir_add(ndir, &ndentry->d_name, ip);
+ if (error)
+ goto out_end_trans;
+
+out_end_trans:
+ gfs2_trans_end(sdp);
+out_ipreserv:
+ if (alloc_required)
+ gfs2_inplace_release(ndip);
+out_gunlock_q:
+ if (alloc_required)
+ gfs2_quota_unlock(ndip);
+out_alloc:
+ if (alloc_required)
+ gfs2_alloc_put(ndip);
+out_gunlock:
+ while (x--) {
+ gfs2_glock_dq(ghs + x);
+ gfs2_holder_uninit(ghs + x);
+ }
+out_gunlock_r:
+ if (r_gh.gh_gl)
+ gfs2_glock_dq_uninit(&r_gh);
+out:
+ gfs2_glock_dq_uninit(&ri_gh);
+ return error;
+}
+
+/**
+ * gfs2_follow_link - Follow a symbolic link
+ * @dentry: The dentry of the link
+ * @nd: Data that we pass to vfs_follow_link()
+ *
+ * This can handle symlinks of any size.
+ *
+ * Returns: 0 on success or error code
+ */
+
+static void *gfs2_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+ struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
+ struct gfs2_holder i_gh;
+ struct buffer_head *dibh;
+ unsigned int size;
+ char *buf;
+ int error;
+
+ gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
+ error = gfs2_glock_nq(&i_gh);
+ if (error) {
+ gfs2_holder_uninit(&i_gh);
+ nd_set_link(nd, ERR_PTR(error));
+ return NULL;
+ }
+
+ size = (unsigned int)i_size_read(&ip->i_inode);
+ if (size == 0) {
+ gfs2_consist_inode(ip);
+ buf = ERR_PTR(-EIO);
+ goto out;
+ }
+
+ error = gfs2_meta_inode_buffer(ip, &dibh);
+ if (error) {
+ buf = ERR_PTR(error);
+ goto out;
+ }
+
+ buf = kzalloc(size + 1, GFP_NOFS);
+ if (!buf)
+ buf = ERR_PTR(-ENOMEM);
+ else
+ memcpy(buf, dibh->b_data + sizeof(struct gfs2_dinode), size);
+ brelse(dibh);
+out:
+ gfs2_glock_dq_uninit(&i_gh);
+ nd_set_link(nd, buf);
+ return NULL;
+}
+
+static void gfs2_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
+{
+ char *s = nd_get_link(nd);
+ if (!IS_ERR(s))
+ kfree(s);
+}
+
+/**
+ * gfs2_permission -
+ * @inode: The inode
+ * @mask: The mask to be tested
+ * @flags: Indicates whether this is an RCU path walk or not
+ *
+ * This may be called from the VFS directly, or from within GFS2 with the
+ * inode locked, so we look to see if the glock is already locked and only
+ * lock the glock if its not already been done.
+ *
+ * Returns: errno
+ */
+
+int gfs2_permission(struct inode *inode, int mask, unsigned int flags)
+{
+ struct gfs2_inode *ip;
+ struct gfs2_holder i_gh;
+ int error;
+ int unlock = 0;
+
+
+ ip = GFS2_I(inode);
+ if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
+ if (flags & IPERM_FLAG_RCU)
+ return -ECHILD;
+ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
+ if (error)
+ return error;
+ unlock = 1;
+ }
+
+ if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode))
+ error = -EACCES;
+ else
+ error = generic_permission(inode, mask, flags, gfs2_check_acl);
+ if (unlock)
+ gfs2_glock_dq_uninit(&i_gh);
+
+ return error;
}
static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
@@ -901,8 +1594,6 @@ static int __gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
* @ip:
* @attr:
*
- * Called with a reference on the vnode.
- *
* Returns: errno
*/
@@ -922,60 +1613,280 @@ int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr)
return error;
}
-void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf)
-{
- struct gfs2_dinode *str = buf;
-
- str->di_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
- str->di_header.mh_type = cpu_to_be32(GFS2_METATYPE_DI);
- str->di_header.mh_format = cpu_to_be32(GFS2_FORMAT_DI);
- str->di_num.no_addr = cpu_to_be64(ip->i_no_addr);
- str->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
- str->di_mode = cpu_to_be32(ip->i_inode.i_mode);
- str->di_uid = cpu_to_be32(ip->i_inode.i_uid);
- str->di_gid = cpu_to_be32(ip->i_inode.i_gid);
- str->di_nlink = cpu_to_be32(ip->i_inode.i_nlink);
- str->di_size = cpu_to_be64(i_size_read(&ip->i_inode));
- str->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
- str->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
- str->di_mtime = cpu_to_be64(ip->i_inode.i_mtime.tv_sec);
- str->di_ctime = cpu_to_be64(ip->i_inode.i_ctime.tv_sec);
-
- str->di_goal_meta = cpu_to_be64(ip->i_goal);
- str->di_goal_data = cpu_to_be64(ip->i_goal);
- str->di_generation = cpu_to_be64(ip->i_generation);
-
- str->di_flags = cpu_to_be32(ip->i_diskflags);
- str->di_height = cpu_to_be16(ip->i_height);
- str->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) &&
- !(ip->i_diskflags & GFS2_DIF_EXHASH) ?
- GFS2_FORMAT_DE : 0);
- str->di_depth = cpu_to_be16(ip->i_depth);
- str->di_entries = cpu_to_be32(ip->i_entries);
-
- str->di_eattr = cpu_to_be64(ip->i_eattr);
- str->di_atime_nsec = cpu_to_be32(ip->i_inode.i_atime.tv_nsec);
- str->di_mtime_nsec = cpu_to_be32(ip->i_inode.i_mtime.tv_nsec);
- str->di_ctime_nsec = cpu_to_be32(ip->i_inode.i_ctime.tv_nsec);
-}
-
-void gfs2_dinode_print(const struct gfs2_inode *ip)
-{
- printk(KERN_INFO " no_formal_ino = %llu\n",
- (unsigned long long)ip->i_no_formal_ino);
- printk(KERN_INFO " no_addr = %llu\n",
- (unsigned long long)ip->i_no_addr);
- printk(KERN_INFO " i_size = %llu\n",
- (unsigned long long)i_size_read(&ip->i_inode));
- printk(KERN_INFO " blocks = %llu\n",
- (unsigned long long)gfs2_get_inode_blocks(&ip->i_inode));
- printk(KERN_INFO " i_goal = %llu\n",
- (unsigned long long)ip->i_goal);
- printk(KERN_INFO " i_diskflags = 0x%.8X\n", ip->i_diskflags);
- printk(KERN_INFO " i_height = %u\n", ip->i_height);
- printk(KERN_INFO " i_depth = %u\n", ip->i_depth);
- printk(KERN_INFO " i_entries = %u\n", ip->i_entries);
- printk(KERN_INFO " i_eattr = %llu\n",
- (unsigned long long)ip->i_eattr);
+static int setattr_chown(struct inode *inode, struct iattr *attr)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_sbd *sdp = GFS2_SB(inode);
+ u32 ouid, ogid, nuid, ngid;
+ int error;
+
+ ouid = inode->i_uid;
+ ogid = inode->i_gid;
+ nuid = attr->ia_uid;
+ ngid = attr->ia_gid;
+
+ if (!(attr->ia_valid & ATTR_UID) || ouid == nuid)
+ ouid = nuid = NO_QUOTA_CHANGE;
+ if (!(attr->ia_valid & ATTR_GID) || ogid == ngid)
+ ogid = ngid = NO_QUOTA_CHANGE;
+
+ if (!gfs2_alloc_get(ip))
+ return -ENOMEM;
+
+ error = gfs2_quota_lock(ip, nuid, ngid);
+ if (error)
+ goto out_alloc;
+
+ if (ouid != NO_QUOTA_CHANGE || ogid != NO_QUOTA_CHANGE) {
+ error = gfs2_quota_check(ip, nuid, ngid);
+ if (error)
+ goto out_gunlock_q;
+ }
+
+ error = gfs2_trans_begin(sdp, RES_DINODE + 2 * RES_QUOTA, 0);
+ if (error)
+ goto out_gunlock_q;
+
+ error = gfs2_setattr_simple(ip, attr);
+ if (error)
+ goto out_end_trans;
+
+ if (ouid != NO_QUOTA_CHANGE || ogid != NO_QUOTA_CHANGE) {
+ u64 blocks = gfs2_get_inode_blocks(&ip->i_inode);
+ gfs2_quota_change(ip, -blocks, ouid, ogid);
+ gfs2_quota_change(ip, blocks, nuid, ngid);
+ }
+
+out_end_trans:
+ gfs2_trans_end(sdp);
+out_gunlock_q:
+ gfs2_quota_unlock(ip);
+out_alloc:
+ gfs2_alloc_put(ip);
+ return error;
}
+/**
+ * gfs2_setattr - Change attributes on an inode
+ * @dentry: The dentry which is changing
+ * @attr: The structure describing the change
+ *
+ * The VFS layer wants to change one or more of an inodes attributes. Write
+ * that change out to disk.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_setattr(struct dentry *dentry, struct iattr *attr)
+{
+ struct inode *inode = dentry->d_inode;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder i_gh;
+ int error;
+
+ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
+ if (error)
+ return error;
+
+ error = -EPERM;
+ if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
+ goto out;
+
+ error = inode_change_ok(inode, attr);
+ if (error)
+ goto out;
+
+ if (attr->ia_valid & ATTR_SIZE)
+ error = gfs2_setattr_size(inode, attr->ia_size);
+ else if (attr->ia_valid & (ATTR_UID | ATTR_GID))
+ error = setattr_chown(inode, attr);
+ else if ((attr->ia_valid & ATTR_MODE) && IS_POSIXACL(inode))
+ error = gfs2_acl_chmod(ip, attr);
+ else
+ error = gfs2_setattr_simple(ip, attr);
+
+out:
+ gfs2_glock_dq_uninit(&i_gh);
+ if (!error)
+ mark_inode_dirty(inode);
+ return error;
+}
+
+/**
+ * gfs2_getattr - Read out an inode's attributes
+ * @mnt: The vfsmount the inode is being accessed from
+ * @dentry: The dentry to stat
+ * @stat: The inode's stats
+ *
+ * This may be called from the VFS directly, or from within GFS2 with the
+ * inode locked, so we look to see if the glock is already locked and only
+ * lock the glock if its not already been done. Note that its the NFS
+ * readdirplus operation which causes this to be called (from filldir)
+ * with the glock already held.
+ *
+ * Returns: errno
+ */
+
+static int gfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
+ struct kstat *stat)
+{
+ struct inode *inode = dentry->d_inode;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ int error;
+ int unlock = 0;
+
+ if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
+ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
+ if (error)
+ return error;
+ unlock = 1;
+ }
+
+ generic_fillattr(inode, stat);
+ if (unlock)
+ gfs2_glock_dq_uninit(&gh);
+
+ return 0;
+}
+
+static int gfs2_setxattr(struct dentry *dentry, const char *name,
+ const void *data, size_t size, int flags)
+{
+ struct inode *inode = dentry->d_inode;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ int ret;
+
+ gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+ ret = gfs2_glock_nq(&gh);
+ if (ret == 0) {
+ ret = generic_setxattr(dentry, name, data, size, flags);
+ gfs2_glock_dq(&gh);
+ }
+ gfs2_holder_uninit(&gh);
+ return ret;
+}
+
+static ssize_t gfs2_getxattr(struct dentry *dentry, const char *name,
+ void *data, size_t size)
+{
+ struct inode *inode = dentry->d_inode;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ int ret;
+
+ gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
+ ret = gfs2_glock_nq(&gh);
+ if (ret == 0) {
+ ret = generic_getxattr(dentry, name, data, size);
+ gfs2_glock_dq(&gh);
+ }
+ gfs2_holder_uninit(&gh);
+ return ret;
+}
+
+static int gfs2_removexattr(struct dentry *dentry, const char *name)
+{
+ struct inode *inode = dentry->d_inode;
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ int ret;
+
+ gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+ ret = gfs2_glock_nq(&gh);
+ if (ret == 0) {
+ ret = generic_removexattr(dentry, name);
+ gfs2_glock_dq(&gh);
+ }
+ gfs2_holder_uninit(&gh);
+ return ret;
+}
+
+static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+ u64 start, u64 len)
+{
+ struct gfs2_inode *ip = GFS2_I(inode);
+ struct gfs2_holder gh;
+ int ret;
+
+ ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
+ if (ret)
+ return ret;
+
+ mutex_lock(&inode->i_mutex);
+
+ ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
+ if (ret)
+ goto out;
+
+ if (gfs2_is_stuffed(ip)) {
+ u64 phys = ip->i_no_addr << inode->i_blkbits;
+ u64 size = i_size_read(inode);
+ u32 flags = FIEMAP_EXTENT_LAST|FIEMAP_EXTENT_NOT_ALIGNED|
+ FIEMAP_EXTENT_DATA_INLINE;
+ phys += sizeof(struct gfs2_dinode);
+ phys += start;
+ if (start + len > size)
+ len = size - start;
+ if (start < size)
+ ret = fiemap_fill_next_extent(fieinfo, start, phys,
+ len, flags);
+ if (ret == 1)
+ ret = 0;
+ } else {
+ ret = __generic_block_fiemap(inode, fieinfo, start, len,
+ gfs2_block_map);
+ }
+
+ gfs2_glock_dq_uninit(&gh);
+out:
+ mutex_unlock(&inode->i_mutex);
+ return ret;
+}
+
+const struct inode_operations gfs2_file_iops = {
+ .permission = gfs2_permission,
+ .setattr = gfs2_setattr,
+ .getattr = gfs2_getattr,
+ .setxattr = gfs2_setxattr,
+ .getxattr = gfs2_getxattr,
+ .listxattr = gfs2_listxattr,
+ .removexattr = gfs2_removexattr,
+ .fiemap = gfs2_fiemap,
+};
+
+const struct inode_operations gfs2_dir_iops = {
+ .create = gfs2_create,
+ .lookup = gfs2_lookup,
+ .link = gfs2_link,
+ .unlink = gfs2_unlink,
+ .symlink = gfs2_symlink,
+ .mkdir = gfs2_mkdir,
+ .rmdir = gfs2_unlink,
+ .mknod = gfs2_mknod,
+ .rename = gfs2_rename,
+ .permission = gfs2_permission,
+ .setattr = gfs2_setattr,
+ .getattr = gfs2_getattr,
+ .setxattr = gfs2_setxattr,
+ .getxattr = gfs2_getxattr,
+ .listxattr = gfs2_listxattr,
+ .removexattr = gfs2_removexattr,
+ .fiemap = gfs2_fiemap,
+};
+
+const struct inode_operations gfs2_symlink_iops = {
+ .readlink = generic_readlink,
+ .follow_link = gfs2_follow_link,
+ .put_link = gfs2_put_link,
+ .permission = gfs2_permission,
+ .setattr = gfs2_setattr,
+ .getattr = gfs2_getattr,
+ .setxattr = gfs2_setxattr,
+ .getxattr = gfs2_getxattr,
+ .listxattr = gfs2_listxattr,
+ .removexattr = gfs2_removexattr,
+ .fiemap = gfs2_fiemap,
+};
+
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index 3e00a66e7cb..31606076f70 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -97,26 +97,21 @@ err:
}
extern struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned type,
- u64 no_addr, u64 no_formal_ino);
+ u64 no_addr, u64 no_formal_ino,
+ int non_block);
extern struct inode *gfs2_lookup_by_inum(struct gfs2_sbd *sdp, u64 no_addr,
u64 *no_formal_ino,
unsigned int blktype);
-extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr);
+extern struct inode *gfs2_ilookup(struct super_block *sb, u64 no_addr, int nonblock);
extern int gfs2_inode_refresh(struct gfs2_inode *ip);
-extern int gfs2_dinode_dealloc(struct gfs2_inode *inode);
-extern int gfs2_change_nlink(struct gfs2_inode *ip, int diff);
extern struct inode *gfs2_lookupi(struct inode *dir, const struct qstr *name,
int is_root);
-extern struct inode *gfs2_createi(struct gfs2_holder *ghs,
- const struct qstr *name,
- unsigned int mode, dev_t dev);
extern int gfs2_permission(struct inode *inode, int mask, unsigned int flags);
extern int gfs2_setattr_simple(struct gfs2_inode *ip, struct iattr *attr);
extern struct inode *gfs2_lookup_simple(struct inode *dip, const char *name);
extern void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf);
-extern void gfs2_dinode_print(const struct gfs2_inode *ip);
extern const struct inode_operations gfs2_file_iops;
extern const struct inode_operations gfs2_dir_iops;
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 6e493aee28f..98c80d8c2a6 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -22,7 +22,6 @@ static void gdlm_ast(void *arg)
{
struct gfs2_glock *gl = arg;
unsigned ret = gl->gl_state;
- struct gfs2_sbd *sdp = gl->gl_sbd;
BUG_ON(gl->gl_lksb.sb_flags & DLM_SBF_DEMOTED);
@@ -31,12 +30,7 @@ static void gdlm_ast(void *arg)
switch (gl->gl_lksb.sb_status) {
case -DLM_EUNLOCK: /* Unlocked, so glock can be freed */
- if (gl->gl_ops->go_flags & GLOF_ASPACE)
- kmem_cache_free(gfs2_glock_aspace_cachep, gl);
- else
- kmem_cache_free(gfs2_glock_cachep, gl);
- if (atomic_dec_and_test(&sdp->sd_glock_disposal))
- wake_up(&sdp->sd_glock_wait);
+ gfs2_glock_free(gl);
return;
case -DLM_ECANCEL: /* Cancel while getting lock */
ret |= LM_OUT_CANCELED;
@@ -164,16 +158,14 @@ static int gdlm_lock(struct gfs2_glock *gl, unsigned int req_state,
GDLM_STRNAME_BYTES - 1, 0, gdlm_ast, gl, gdlm_bast);
}
-static void gdlm_put_lock(struct kmem_cache *cachep, struct gfs2_glock *gl)
+static void gdlm_put_lock(struct gfs2_glock *gl)
{
struct gfs2_sbd *sdp = gl->gl_sbd;
struct lm_lockstruct *ls = &sdp->sd_lockstruct;
int error;
if (gl->gl_lksb.sb_lkid == 0) {
- kmem_cache_free(cachep, gl);
- if (atomic_dec_and_test(&sdp->sd_glock_disposal))
- wake_up(&sdp->sd_glock_wait);
+ gfs2_glock_free(gl);
return;
}
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index eb01f3575e1..903115f2bb3 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -18,6 +18,7 @@
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/bio.h>
+#include <linux/writeback.h>
#include "gfs2.h"
#include "incore.h"
@@ -67,7 +68,7 @@ unsigned int gfs2_struct2blk(struct gfs2_sbd *sdp, unsigned int nstruct,
* @mapping: The associated mapping (maybe NULL)
* @bd: The gfs2_bufdata to remove
*
- * The log lock _must_ be held when calling this function
+ * The ail lock _must_ be held when calling this function
*
*/
@@ -83,55 +84,97 @@ void gfs2_remove_from_ail(struct gfs2_bufdata *bd)
/**
* gfs2_ail1_start_one - Start I/O on a part of the AIL
* @sdp: the filesystem
- * @tr: the part of the AIL
+ * @wbc: The writeback control structure
+ * @ai: The ail structure
*
*/
-static void gfs2_ail1_start_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
-__releases(&sdp->sd_log_lock)
-__acquires(&sdp->sd_log_lock)
+static int gfs2_ail1_start_one(struct gfs2_sbd *sdp,
+ struct writeback_control *wbc,
+ struct gfs2_ail *ai)
+__releases(&sdp->sd_ail_lock)
+__acquires(&sdp->sd_ail_lock)
{
+ struct gfs2_glock *gl = NULL;
+ struct address_space *mapping;
struct gfs2_bufdata *bd, *s;
struct buffer_head *bh;
- int retry;
- do {
- retry = 0;
+ list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list, bd_ail_st_list) {
+ bh = bd->bd_bh;
- list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
- bd_ail_st_list) {
- bh = bd->bd_bh;
+ gfs2_assert(sdp, bd->bd_ail == ai);
- gfs2_assert(sdp, bd->bd_ail == ai);
+ if (!buffer_busy(bh)) {
+ if (!buffer_uptodate(bh))
+ gfs2_io_error_bh(sdp, bh);
+ list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
+ continue;
+ }
- if (!buffer_busy(bh)) {
- if (!buffer_uptodate(bh))
- gfs2_io_error_bh(sdp, bh);
- list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
- continue;
- }
+ if (!buffer_dirty(bh))
+ continue;
+ if (gl == bd->bd_gl)
+ continue;
+ gl = bd->bd_gl;
+ list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+ mapping = bh->b_page->mapping;
+ if (!mapping)
+ continue;
+ spin_unlock(&sdp->sd_ail_lock);
+ generic_writepages(mapping, wbc);
+ spin_lock(&sdp->sd_ail_lock);
+ if (wbc->nr_to_write <= 0)
+ break;
+ return 1;
+ }
- if (!buffer_dirty(bh))
- continue;
+ return 0;
+}
- list_move(&bd->bd_ail_st_list, &ai->ai_ail1_list);
- get_bh(bh);
- gfs2_log_unlock(sdp);
- lock_buffer(bh);
- if (test_clear_buffer_dirty(bh)) {
- bh->b_end_io = end_buffer_write_sync;
- submit_bh(WRITE_SYNC_PLUG, bh);
- } else {
- unlock_buffer(bh);
- brelse(bh);
- }
- gfs2_log_lock(sdp);
+/**
+ * gfs2_ail1_flush - start writeback of some ail1 entries
+ * @sdp: The super block
+ * @wbc: The writeback control structure
+ *
+ * Writes back some ail1 entries, according to the limits in the
+ * writeback control structure
+ */
- retry = 1;
+void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc)
+{
+ struct list_head *head = &sdp->sd_ail1_list;
+ struct gfs2_ail *ai;
+
+ trace_gfs2_ail_flush(sdp, wbc, 1);
+ spin_lock(&sdp->sd_ail_lock);
+restart:
+ list_for_each_entry_reverse(ai, head, ai_list) {
+ if (wbc->nr_to_write <= 0)
break;
- }
- } while (retry);
+ if (gfs2_ail1_start_one(sdp, wbc, ai))
+ goto restart;
+ }
+ spin_unlock(&sdp->sd_ail_lock);
+ trace_gfs2_ail_flush(sdp, wbc, 0);
+}
+
+/**
+ * gfs2_ail1_start - start writeback of all ail1 entries
+ * @sdp: The superblock
+ */
+
+static void gfs2_ail1_start(struct gfs2_sbd *sdp)
+{
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_NONE,
+ .nr_to_write = LONG_MAX,
+ .range_start = 0,
+ .range_end = LLONG_MAX,
+ };
+
+ return gfs2_ail1_flush(sdp, &wbc);
}
/**
@@ -141,7 +184,7 @@ __acquires(&sdp->sd_log_lock)
*
*/
-static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int flags)
+static void gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
{
struct gfs2_bufdata *bd, *s;
struct buffer_head *bh;
@@ -149,76 +192,63 @@ static int gfs2_ail1_empty_one(struct gfs2_sbd *sdp, struct gfs2_ail *ai, int fl
list_for_each_entry_safe_reverse(bd, s, &ai->ai_ail1_list,
bd_ail_st_list) {
bh = bd->bd_bh;
-
gfs2_assert(sdp, bd->bd_ail == ai);
-
- if (buffer_busy(bh)) {
- if (flags & DIO_ALL)
- continue;
- else
- break;
- }
-
+ if (buffer_busy(bh))
+ continue;
if (!buffer_uptodate(bh))
gfs2_io_error_bh(sdp, bh);
-
list_move(&bd->bd_ail_st_list, &ai->ai_ail2_list);
}
- return list_empty(&ai->ai_ail1_list);
}
-static void gfs2_ail1_start(struct gfs2_sbd *sdp)
-{
- struct list_head *head;
- u64 sync_gen;
- struct gfs2_ail *ai;
- int done = 0;
-
- gfs2_log_lock(sdp);
- head = &sdp->sd_ail1_list;
- if (list_empty(head)) {
- gfs2_log_unlock(sdp);
- return;
- }
- sync_gen = sdp->sd_ail_sync_gen++;
-
- while(!done) {
- done = 1;
- list_for_each_entry_reverse(ai, head, ai_list) {
- if (ai->ai_sync_gen >= sync_gen)
- continue;
- ai->ai_sync_gen = sync_gen;
- gfs2_ail1_start_one(sdp, ai); /* This may drop log lock */
- done = 0;
- break;
- }
- }
-
- gfs2_log_unlock(sdp);
-}
+/**
+ * gfs2_ail1_empty - Try to empty the ail1 lists
+ * @sdp: The superblock
+ *
+ * Tries to empty the ail1 lists, starting with the oldest first
+ */
-static int gfs2_ail1_empty(struct gfs2_sbd *sdp, int flags)
+static int gfs2_ail1_empty(struct gfs2_sbd *sdp)
{
struct gfs2_ail *ai, *s;
int ret;
- gfs2_log_lock(sdp);
-
+ spin_lock(&sdp->sd_ail_lock);
list_for_each_entry_safe_reverse(ai, s, &sdp->sd_ail1_list, ai_list) {
- if (gfs2_ail1_empty_one(sdp, ai, flags))
+ gfs2_ail1_empty_one(sdp, ai);
+ if (list_empty(&ai->ai_ail1_list))
list_move(&ai->ai_list, &sdp->sd_ail2_list);
- else if (!(flags & DIO_ALL))
+ else
break;
}
-
ret = list_empty(&sdp->sd_ail1_list);
-
- gfs2_log_unlock(sdp);
+ spin_unlock(&sdp->sd_ail_lock);
return ret;
}
+static void gfs2_ail1_wait(struct gfs2_sbd *sdp)
+{
+ struct gfs2_ail *ai;
+ struct gfs2_bufdata *bd;
+ struct buffer_head *bh;
+
+ spin_lock(&sdp->sd_ail_lock);
+ list_for_each_entry_reverse(ai, &sdp->sd_ail1_list, ai_list) {
+ list_for_each_entry(bd, &ai->ai_ail1_list, bd_ail_st_list) {
+ bh = bd->bd_bh;
+ if (!buffer_locked(bh))
+ continue;
+ get_bh(bh);
+ spin_unlock(&sdp->sd_ail_lock);
+ wait_on_buffer(bh);
+ brelse(bh);
+ return;
+ }
+ }
+ spin_unlock(&sdp->sd_ail_lock);
+}
/**
* gfs2_ail2_empty_one - Check whether or not a trans in the AIL has been synced
@@ -247,7 +277,7 @@ static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
int wrap = (new_tail < old_tail);
int a, b, rm;
- gfs2_log_lock(sdp);
+ spin_lock(&sdp->sd_ail_lock);
list_for_each_entry_safe(ai, safe, &sdp->sd_ail2_list, ai_list) {
a = (old_tail <= ai->ai_first);
@@ -263,7 +293,7 @@ static void ail2_empty(struct gfs2_sbd *sdp, unsigned int new_tail)
kfree(ai);
}
- gfs2_log_unlock(sdp);
+ spin_unlock(&sdp->sd_ail_lock);
}
/**
@@ -421,7 +451,7 @@ static unsigned int current_tail(struct gfs2_sbd *sdp)
struct gfs2_ail *ai;
unsigned int tail;
- gfs2_log_lock(sdp);
+ spin_lock(&sdp->sd_ail_lock);
if (list_empty(&sdp->sd_ail1_list)) {
tail = sdp->sd_log_head;
@@ -430,7 +460,7 @@ static unsigned int current_tail(struct gfs2_sbd *sdp)
tail = ai->ai_first;
}
- gfs2_log_unlock(sdp);
+ spin_unlock(&sdp->sd_ail_lock);
return tail;
}
@@ -574,7 +604,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags, int pull)
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
- gfs2_ail1_empty(sdp, 0);
+ gfs2_ail1_empty(sdp);
tail = current_tail(sdp);
lh = (struct gfs2_log_header *)bh->b_data;
@@ -647,7 +677,7 @@ static void gfs2_ordered_write(struct gfs2_sbd *sdp)
lock_buffer(bh);
if (buffer_mapped(bh) && test_clear_buffer_dirty(bh)) {
bh->b_end_io = end_buffer_write_sync;
- submit_bh(WRITE_SYNC_PLUG, bh);
+ submit_bh(WRITE_SYNC, bh);
} else {
unlock_buffer(bh);
brelse(bh);
@@ -743,10 +773,12 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl)
sdp->sd_log_commited_databuf = 0;
sdp->sd_log_commited_revoke = 0;
+ spin_lock(&sdp->sd_ail_lock);
if (!list_empty(&ai->ai_ail1_list)) {
list_add(&ai->ai_list, &sdp->sd_ail1_list);
ai = NULL;
}
+ spin_unlock(&sdp->sd_ail_lock);
gfs2_log_unlock(sdp);
trace_gfs2_log_flush(sdp, 0);
up_write(&sdp->sd_log_flush_lock);
@@ -867,9 +899,9 @@ void gfs2_meta_syncfs(struct gfs2_sbd *sdp)
gfs2_log_flush(sdp, NULL);
for (;;) {
gfs2_ail1_start(sdp);
- if (gfs2_ail1_empty(sdp, DIO_ALL))
+ gfs2_ail1_wait(sdp);
+ if (gfs2_ail1_empty(sdp))
break;
- msleep(10);
}
}
@@ -903,20 +935,20 @@ int gfs2_logd(void *data)
preflush = atomic_read(&sdp->sd_log_pinned);
if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
- gfs2_ail1_empty(sdp, DIO_ALL);
+ gfs2_ail1_empty(sdp);
gfs2_log_flush(sdp, NULL);
- gfs2_ail1_empty(sdp, DIO_ALL);
}
if (gfs2_ail_flush_reqd(sdp)) {
gfs2_ail1_start(sdp);
- io_schedule();
- gfs2_ail1_empty(sdp, 0);
+ gfs2_ail1_wait(sdp);
+ gfs2_ail1_empty(sdp);
gfs2_log_flush(sdp, NULL);
- gfs2_ail1_empty(sdp, DIO_ALL);
}
- wake_up(&sdp->sd_log_waitq);
+ if (!gfs2_ail_flush_reqd(sdp))
+ wake_up(&sdp->sd_log_waitq);
+
t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
if (freezing(current))
refrigerator();
diff --git a/fs/gfs2/log.h b/fs/gfs2/log.h
index 0d007f92023..ab0621698b7 100644
--- a/fs/gfs2/log.h
+++ b/fs/gfs2/log.h
@@ -12,6 +12,7 @@
#include <linux/list.h>
#include <linux/spinlock.h>
+#include <linux/writeback.h>
#include "incore.h"
/**
@@ -59,6 +60,7 @@ extern struct buffer_head *gfs2_log_fake_buf(struct gfs2_sbd *sdp,
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);
+extern void gfs2_ail1_flush(struct gfs2_sbd *sdp, struct writeback_control *wbc);
extern void gfs2_log_shutdown(struct gfs2_sbd *sdp);
extern void gfs2_meta_syncfs(struct gfs2_sbd *sdp);
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index bf33f822058..05bbb124699 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -40,7 +40,7 @@ static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
{
struct gfs2_bufdata *bd;
- gfs2_assert_withdraw(sdp, test_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags));
+ BUG_ON(!current->journal_info);
clear_buffer_dirty(bh);
if (test_set_buffer_pinned(bh))
@@ -51,8 +51,10 @@ static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
/* If this buffer is in the AIL and it has already been written
* to in-place disk block, remove it from the AIL.
*/
+ spin_lock(&sdp->sd_ail_lock);
if (bd->bd_ail)
list_move(&bd->bd_ail_st_list, &bd->bd_ail->ai_ail2_list);
+ spin_unlock(&sdp->sd_ail_lock);
get_bh(bh);
atomic_inc(&sdp->sd_log_pinned);
trace_gfs2_pin(bd, 1);
@@ -63,6 +65,7 @@ static void gfs2_pin(struct gfs2_sbd *sdp, struct buffer_head *bh)
* @sdp: the filesystem the buffer belongs to
* @bh: The buffer to unpin
* @ai:
+ * @flags: The inode dirty flags
*
*/
@@ -71,16 +74,14 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
{
struct gfs2_bufdata *bd = bh->b_private;
- gfs2_assert_withdraw(sdp, buffer_uptodate(bh));
-
- if (!buffer_pinned(bh))
- gfs2_assert_withdraw(sdp, 0);
+ BUG_ON(!buffer_uptodate(bh));
+ BUG_ON(!buffer_pinned(bh));
lock_buffer(bh);
mark_buffer_dirty(bh);
clear_buffer_pinned(bh);
- gfs2_log_lock(sdp);
+ spin_lock(&sdp->sd_ail_lock);
if (bd->bd_ail) {
list_del(&bd->bd_ail_st_list);
brelse(bh);
@@ -91,9 +92,10 @@ static void gfs2_unpin(struct gfs2_sbd *sdp, struct buffer_head *bh,
}
bd->bd_ail = ai;
list_add(&bd->bd_ail_st_list, &ai->ai_ail1_list);
+ spin_unlock(&sdp->sd_ail_lock);
+
clear_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
trace_gfs2_pin(bd, 0);
- gfs2_log_unlock(sdp);
unlock_buffer(bh);
atomic_dec(&sdp->sd_log_pinned);
}
@@ -200,7 +202,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
}
gfs2_log_unlock(sdp);
- submit_bh(WRITE_SYNC_PLUG, bh);
+ submit_bh(WRITE_SYNC, bh);
gfs2_log_lock(sdp);
n = 0;
@@ -210,7 +212,7 @@ static void buf_lo_before_commit(struct gfs2_sbd *sdp)
gfs2_log_unlock(sdp);
lock_buffer(bd2->bd_bh);
bh = gfs2_log_fake_buf(sdp, bd2->bd_bh);
- submit_bh(WRITE_SYNC_PLUG, bh);
+ submit_bh(WRITE_SYNC, bh);
gfs2_log_lock(sdp);
if (++n >= num)
break;
@@ -318,12 +320,16 @@ static void buf_lo_after_scan(struct gfs2_jdesc *jd, int error, int pass)
static void revoke_lo_add(struct gfs2_sbd *sdp, struct gfs2_log_element *le)
{
+ struct gfs2_bufdata *bd = container_of(le, struct gfs2_bufdata, bd_le);
+ struct gfs2_glock *gl = bd->bd_gl;
struct gfs2_trans *tr;
tr = current->journal_info;
tr->tr_touched = 1;
tr->tr_num_revoke++;
sdp->sd_log_num_revoke++;
+ atomic_inc(&gl->gl_revokes);
+ set_bit(GLF_LFLUSH, &gl->gl_flags);
list_add(&le->le_list, &sdp->sd_log_le_revoke);
}
@@ -346,13 +352,11 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
ld->ld_data1 = cpu_to_be32(sdp->sd_log_num_revoke);
offset = sizeof(struct gfs2_log_descriptor);
- while (!list_empty(head)) {
- bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list);
- list_del_init(&bd->bd_le.le_list);
+ list_for_each_entry(bd, head, bd_le.le_list) {
sdp->sd_log_num_revoke--;
if (offset + sizeof(u64) > sdp->sd_sb.sb_bsize) {
- submit_bh(WRITE_SYNC_PLUG, bh);
+ submit_bh(WRITE_SYNC, bh);
bh = gfs2_log_get_buf(sdp);
mh = (struct gfs2_meta_header *)bh->b_data;
@@ -363,13 +367,27 @@ static void revoke_lo_before_commit(struct gfs2_sbd *sdp)
}
*(__be64 *)(bh->b_data + offset) = cpu_to_be64(bd->bd_blkno);
- kmem_cache_free(gfs2_bufdata_cachep, bd);
-
offset += sizeof(u64);
}
gfs2_assert_withdraw(sdp, !sdp->sd_log_num_revoke);
- submit_bh(WRITE_SYNC_PLUG, bh);
+ submit_bh(WRITE_SYNC, bh);
+}
+
+static void revoke_lo_after_commit(struct gfs2_sbd *sdp, struct gfs2_ail *ai)
+{
+ struct list_head *head = &sdp->sd_log_le_revoke;
+ struct gfs2_bufdata *bd;
+ struct gfs2_glock *gl;
+
+ while (!list_empty(head)) {
+ bd = list_entry(head->next, struct gfs2_bufdata, bd_le.le_list);
+ list_del_init(&bd->bd_le.le_list);
+ gl = bd->bd_gl;
+ atomic_dec(&gl->gl_revokes);
+ clear_bit(GLF_LFLUSH, &gl->gl_flags);
+ kmem_cache_free(gfs2_bufdata_cachep, bd);
+ }
}
static void revoke_lo_before_scan(struct gfs2_jdesc *jd,
@@ -571,7 +589,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
ptr = bh_log_ptr(bh);
get_bh(bh);
- submit_bh(WRITE_SYNC_PLUG, bh);
+ submit_bh(WRITE_SYNC, bh);
gfs2_log_lock(sdp);
while(!list_empty(list)) {
bd = list_entry(list->next, struct gfs2_bufdata, bd_le.le_list);
@@ -597,7 +615,7 @@ static void gfs2_write_blocks(struct gfs2_sbd *sdp, struct buffer_head *bh,
} else {
bh1 = gfs2_log_fake_buf(sdp, bd->bd_bh);
}
- submit_bh(WRITE_SYNC_PLUG, bh1);
+ submit_bh(WRITE_SYNC, bh1);
gfs2_log_lock(sdp);
ptr += 2;
}
@@ -745,6 +763,7 @@ const struct gfs2_log_operations gfs2_buf_lops = {
const struct gfs2_log_operations gfs2_revoke_lops = {
.lo_add = revoke_lo_add,
.lo_before_commit = revoke_lo_before_commit,
+ .lo_after_commit = revoke_lo_after_commit,
.lo_before_scan = revoke_lo_before_scan,
.lo_scan_elements = revoke_lo_scan_elements,
.lo_after_scan = revoke_lo_after_scan,
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index ebef7ab6e17..c2b34cd2abe 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -14,6 +14,8 @@
#include <linux/module.h>
#include <linux/init.h>
#include <linux/gfs2_ondisk.h>
+#include <linux/rcupdate.h>
+#include <linux/rculist_bl.h>
#include <asm/atomic.h>
#include "gfs2.h"
@@ -45,12 +47,13 @@ static void gfs2_init_glock_once(void *foo)
{
struct gfs2_glock *gl = foo;
- INIT_HLIST_NODE(&gl->gl_list);
+ INIT_HLIST_BL_NODE(&gl->gl_list);
spin_lock_init(&gl->gl_spin);
INIT_LIST_HEAD(&gl->gl_holders);
INIT_LIST_HEAD(&gl->gl_lru);
INIT_LIST_HEAD(&gl->gl_ail_list);
atomic_set(&gl->gl_ail_count, 0);
+ atomic_set(&gl->gl_revokes, 0);
}
static void gfs2_init_gl_aspace_once(void *foo)
@@ -59,14 +62,7 @@ static void gfs2_init_gl_aspace_once(void *foo)
struct address_space *mapping = (struct address_space *)(gl + 1);
gfs2_init_glock_once(gl);
- memset(mapping, 0, sizeof(*mapping));
- INIT_RADIX_TREE(&mapping->page_tree, GFP_ATOMIC);
- spin_lock_init(&mapping->tree_lock);
- spin_lock_init(&mapping->i_mmap_lock);
- INIT_LIST_HEAD(&mapping->private_list);
- spin_lock_init(&mapping->private_lock);
- INIT_RAW_PRIO_TREE_ROOT(&mapping->i_mmap);
- INIT_LIST_HEAD(&mapping->i_mmap_nonlinear);
+ address_space_init_once(mapping);
}
/**
@@ -144,13 +140,13 @@ static int __init init_gfs2_fs(void)
error = -ENOMEM;
gfs_recovery_wq = alloc_workqueue("gfs_recovery",
- WQ_MEM_RECLAIM | WQ_FREEZEABLE, 0);
+ WQ_MEM_RECLAIM | WQ_FREEZABLE, 0);
if (!gfs_recovery_wq)
goto fail_wq;
gfs2_register_debugfs();
- printk("GFS2 (built %s %s) installed\n", __DATE__, __TIME__);
+ printk("GFS2 installed\n");
return 0;
@@ -198,6 +194,8 @@ static void __exit exit_gfs2_fs(void)
unregister_filesystem(&gfs2meta_fs_type);
destroy_workqueue(gfs_recovery_wq);
+ rcu_barrier();
+
kmem_cache_destroy(gfs2_quotad_cachep);
kmem_cache_destroy(gfs2_rgrpd_cachep);
kmem_cache_destroy(gfs2_bufdata_cachep);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 939739c7b3f..747238cd9f9 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -31,13 +31,14 @@
#include "rgrp.h"
#include "trans.h"
#include "util.h"
+#include "trace_gfs2.h"
static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wbc)
{
struct buffer_head *bh, *head;
int nr_underway = 0;
int write_op = REQ_META |
- (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC_PLUG : WRITE);
+ (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
BUG_ON(!PageLocked(page));
BUG_ON(!page_has_buffers(page));
@@ -94,7 +95,6 @@ static int gfs2_aspace_writepage(struct page *page, struct writeback_control *wb
const struct address_space_operations gfs2_meta_aops = {
.writepage = gfs2_aspace_writepage,
.releasepage = gfs2_releasepage,
- .sync_page = block_sync_page,
};
/**
@@ -311,6 +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)) {
+ trace_gfs2_pin(bd, 0);
atomic_dec(&sdp->sd_log_pinned);
list_del_init(&bd->bd_le.le_list);
if (meta) {
@@ -326,6 +327,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int
brelse(bh);
}
if (bd) {
+ spin_lock(&sdp->sd_ail_lock);
if (bd->bd_ail) {
gfs2_remove_from_ail(bd);
bh->b_private = NULL;
@@ -333,6 +335,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, struct gfs2_trans *tr, int
bd->bd_blkno = bh->b_blocknr;
gfs2_trans_add_revoke(sdp, bd);
}
+ spin_unlock(&sdp->sd_ail_lock);
}
clear_buffer_dirty(bh);
clear_buffer_uptodate(bh);
diff --git a/fs/gfs2/meta_io.h b/fs/gfs2/meta_io.h
index 6a1d9ba1641..22c52659313 100644
--- a/fs/gfs2/meta_io.h
+++ b/fs/gfs2/meta_io.h
@@ -77,8 +77,6 @@ struct buffer_head *gfs2_meta_ra(struct gfs2_glock *gl, u64 dblock, u32 extlen);
#define buffer_busy(bh) \
((bh)->b_state & ((1ul << BH_Dirty) | (1ul << BH_Lock) | (1ul << BH_Pinned)))
-#define buffer_in_io(bh) \
-((bh)->b_state & ((1ul << BH_Dirty) | (1ul << BH_Lock)))
#endif /* __DIO_DOT_H__ */
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 777927ce6f7..8ac9ae189b5 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -99,6 +99,7 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
init_waitqueue_head(&sdp->sd_log_waitq);
init_waitqueue_head(&sdp->sd_logd_waitq);
+ spin_lock_init(&sdp->sd_ail_lock);
INIT_LIST_HEAD(&sdp->sd_ail1_list);
INIT_LIST_HEAD(&sdp->sd_ail2_list);
@@ -125,8 +126,10 @@ static struct gfs2_sbd *init_sbd(struct super_block *sb)
* changed.
*/
-static int gfs2_check_sb(struct gfs2_sbd *sdp, struct gfs2_sb_host *sb, int silent)
+static int gfs2_check_sb(struct gfs2_sbd *sdp, int silent)
{
+ struct gfs2_sb_host *sb = &sdp->sd_sb;
+
if (sb->sb_magic != GFS2_MAGIC ||
sb->sb_type != GFS2_METATYPE_SB) {
if (!silent)
@@ -156,8 +159,10 @@ static void end_bio_io_page(struct bio *bio, int error)
unlock_page(page);
}
-static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
+static void gfs2_sb_in(struct gfs2_sbd *sdp, const void *buf)
{
+ struct gfs2_sb_host *sb = &sdp->sd_sb;
+ struct super_block *s = sdp->sd_vfs;
const struct gfs2_sb *str = buf;
sb->sb_magic = be32_to_cpu(str->sb_header.mh_magic);
@@ -174,7 +179,7 @@ static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
- memcpy(sb->sb_uuid, str->sb_uuid, 16);
+ memcpy(s->s_uuid, str->sb_uuid, 16);
}
/**
@@ -196,7 +201,7 @@ static void gfs2_sb_in(struct gfs2_sb_host *sb, const void *buf)
* Returns: 0 on success or error
*/
-static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector)
+static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector, int silent)
{
struct super_block *sb = sdp->sd_vfs;
struct gfs2_sb *p;
@@ -226,10 +231,10 @@ static int gfs2_read_super(struct gfs2_sbd *sdp, sector_t sector)
return -EIO;
}
p = kmap(page);
- gfs2_sb_in(&sdp->sd_sb, p);
+ gfs2_sb_in(sdp, p);
kunmap(page);
__free_page(page);
- return 0;
+ return gfs2_check_sb(sdp, silent);
}
/**
@@ -246,17 +251,13 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
unsigned int x;
int error;
- error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
+ error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift, silent);
if (error) {
if (!silent)
fs_err(sdp, "can't read superblock\n");
return error;
}
- error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
- if (error)
- return error;
-
sdp->sd_fsb2bb_shift = sdp->sd_sb.sb_bsize_shift -
GFS2_BASIC_BLOCK_SHIFT;
sdp->sd_fsb2bb = 1 << sdp->sd_fsb2bb_shift;
@@ -339,14 +340,10 @@ static int init_names(struct gfs2_sbd *sdp, int silent)
/* Try to autodetect */
if (!proto[0] || !table[0]) {
- error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift);
+ error = gfs2_read_super(sdp, GFS2_SB_ADDR >> sdp->sd_fsb2bb_shift, silent);
if (error)
return error;
- error = gfs2_check_sb(sdp, &sdp->sd_sb, silent);
- if (error)
- goto out;
-
if (!proto[0])
proto = sdp->sd_sb.sb_lockproto;
if (!table[0])
@@ -363,7 +360,6 @@ static int init_names(struct gfs2_sbd *sdp, int silent)
while ((table = strchr(table, '/')))
*table = '_';
-out:
return error;
}
@@ -429,7 +425,7 @@ 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);
+ inode = gfs2_inode_lookup(sb, DT_DIR, no_addr, 0, 0);
if (IS_ERR(inode)) {
fs_err(sdp, "can't read in %s inode: %ld\n", name, PTR_ERR(inode));
return PTR_ERR(inode);
@@ -928,17 +924,9 @@ static const match_table_t nolock_tokens = {
{ Opt_err, NULL },
};
-static void nolock_put_lock(struct kmem_cache *cachep, struct gfs2_glock *gl)
-{
- struct gfs2_sbd *sdp = gl->gl_sbd;
- kmem_cache_free(cachep, gl);
- if (atomic_dec_and_test(&sdp->sd_glock_disposal))
- wake_up(&sdp->sd_glock_wait);
-}
-
static const struct lm_lockops nolock_ops = {
.lm_proto_name = "lock_nolock",
- .lm_put_lock = nolock_put_lock,
+ .lm_put_lock = gfs2_glock_free,
.lm_tokens = &nolock_tokens,
};
@@ -1126,8 +1114,7 @@ static int fill_super(struct super_block *sb, struct gfs2_args *args, int silent
if (sdp->sd_args.ar_statfs_quantum) {
sdp->sd_tune.gt_statfs_slow = 0;
sdp->sd_tune.gt_statfs_quantum = sdp->sd_args.ar_statfs_quantum;
- }
- else {
+ } else {
sdp->sd_tune.gt_statfs_slow = 1;
sdp->sd_tune.gt_statfs_quantum = 30;
}
diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c
deleted file mode 100644
index d8b26ac2e20..00000000000
--- a/fs/gfs2/ops_inode.c
+++ /dev/null
@@ -1,1344 +0,0 @@
-/*
- * Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
- * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
- *
- * This copyrighted material is made available to anyone wishing to use,
- * modify, copy, or redistribute it subject to the terms and conditions
- * of the GNU General Public License version 2.
- */
-
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/completion.h>
-#include <linux/buffer_head.h>
-#include <linux/namei.h>
-#include <linux/mm.h>
-#include <linux/xattr.h>
-#include <linux/posix_acl.h>
-#include <linux/gfs2_ondisk.h>
-#include <linux/crc32.h>
-#include <linux/fiemap.h>
-#include <asm/uaccess.h>
-
-#include "gfs2.h"
-#include "incore.h"
-#include "acl.h"
-#include "bmap.h"
-#include "dir.h"
-#include "xattr.h"
-#include "glock.h"
-#include "inode.h"
-#include "meta_io.h"
-#include "quota.h"
-#include "rgrp.h"
-#include "trans.h"
-#include "util.h"
-#include "super.h"
-
-/**
- * gfs2_create - Create a file
- * @dir: The directory in which to create the file
- * @dentry: The dentry of the new file
- * @mode: The mode of the new file
- *
- * Returns: errno
- */
-
-static int gfs2_create(struct inode *dir, struct dentry *dentry,
- int mode, struct nameidata *nd)
-{
- struct gfs2_inode *dip = GFS2_I(dir);
- struct gfs2_sbd *sdp = GFS2_SB(dir);
- struct gfs2_holder ghs[2];
- struct inode *inode;
-
- gfs2_holder_init(dip->i_gl, 0, 0, ghs);
-
- for (;;) {
- inode = gfs2_createi(ghs, &dentry->d_name, S_IFREG | mode, 0);
- if (!IS_ERR(inode)) {
- gfs2_trans_end(sdp);
- if (dip->i_alloc->al_rgd)
- gfs2_inplace_release(dip);
- gfs2_quota_unlock(dip);
- gfs2_alloc_put(dip);
- gfs2_glock_dq_uninit_m(2, ghs);
- mark_inode_dirty(inode);
- break;
- } else if (PTR_ERR(inode) != -EEXIST ||
- (nd && nd->flags & LOOKUP_EXCL)) {
- gfs2_holder_uninit(ghs);
- return PTR_ERR(inode);
- }
-
- inode = gfs2_lookupi(dir, &dentry->d_name, 0);
- if (inode) {
- if (!IS_ERR(inode)) {
- gfs2_holder_uninit(ghs);
- break;
- } else {
- gfs2_holder_uninit(ghs);
- return PTR_ERR(inode);
- }
- }
- }
-
- d_instantiate(dentry, inode);
-
- return 0;
-}
-
-/**
- * gfs2_lookup - Look up a filename in a directory and return its inode
- * @dir: The directory inode
- * @dentry: The dentry of the new inode
- * @nd: passed from Linux VFS, ignored by us
- *
- * Called by the VFS layer. Lock dir and call gfs2_lookupi()
- *
- * Returns: errno
- */
-
-static struct dentry *gfs2_lookup(struct inode *dir, struct dentry *dentry,
- struct nameidata *nd)
-{
- struct inode *inode = NULL;
-
- inode = gfs2_lookupi(dir, &dentry->d_name, 0);
- if (inode && IS_ERR(inode))
- return ERR_CAST(inode);
-
- if (inode) {
- struct gfs2_glock *gl = GFS2_I(inode)->i_gl;
- struct gfs2_holder gh;
- int error;
- error = gfs2_glock_nq_init(gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
- if (error) {
- iput(inode);
- return ERR_PTR(error);
- }
- gfs2_glock_dq_uninit(&gh);
- return d_splice_alias(inode, dentry);
- }
- d_add(dentry, inode);
-
- return NULL;
-}
-
-/**
- * gfs2_link - Link to a file
- * @old_dentry: The inode to link
- * @dir: Add link to this directory
- * @dentry: The name of the link
- *
- * Link the inode in "old_dentry" into the directory "dir" with the
- * name in "dentry".
- *
- * Returns: errno
- */
-
-static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
- struct dentry *dentry)
-{
- struct gfs2_inode *dip = GFS2_I(dir);
- struct gfs2_sbd *sdp = GFS2_SB(dir);
- struct inode *inode = old_dentry->d_inode;
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_holder ghs[2];
- int alloc_required;
- int error;
-
- if (S_ISDIR(inode->i_mode))
- return -EPERM;
-
- gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
- gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
-
- error = gfs2_glock_nq(ghs); /* parent */
- if (error)
- goto out_parent;
-
- error = gfs2_glock_nq(ghs + 1); /* child */
- if (error)
- goto out_child;
-
- error = gfs2_permission(dir, MAY_WRITE | MAY_EXEC, 0);
- if (error)
- goto out_gunlock;
-
- error = gfs2_dir_check(dir, &dentry->d_name, NULL);
- switch (error) {
- case -ENOENT:
- break;
- case 0:
- error = -EEXIST;
- default:
- goto out_gunlock;
- }
-
- error = -EINVAL;
- if (!dip->i_inode.i_nlink)
- goto out_gunlock;
- error = -EFBIG;
- if (dip->i_entries == (u32)-1)
- goto out_gunlock;
- error = -EPERM;
- if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
- goto out_gunlock;
- error = -EINVAL;
- if (!ip->i_inode.i_nlink)
- goto out_gunlock;
- error = -EMLINK;
- if (ip->i_inode.i_nlink == (u32)-1)
- goto out_gunlock;
-
- alloc_required = error = gfs2_diradd_alloc_required(dir, &dentry->d_name);
- if (error < 0)
- goto out_gunlock;
- error = 0;
-
- if (alloc_required) {
- struct gfs2_alloc *al = gfs2_alloc_get(dip);
- if (!al) {
- error = -ENOMEM;
- goto out_gunlock;
- }
-
- error = gfs2_quota_lock_check(dip);
- if (error)
- goto out_alloc;
-
- al->al_requested = sdp->sd_max_dirres;
-
- error = gfs2_inplace_reserve(dip);
- if (error)
- goto out_gunlock_q;
-
- error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
- gfs2_rg_blocks(al) +
- 2 * RES_DINODE + RES_STATFS +
- RES_QUOTA, 0);
- if (error)
- goto out_ipres;
- } else {
- error = gfs2_trans_begin(sdp, 2 * RES_DINODE + RES_LEAF, 0);
- if (error)
- goto out_ipres;
- }
-
- error = gfs2_dir_add(dir, &dentry->d_name, ip, IF2DT(inode->i_mode));
- if (error)
- goto out_end_trans;
-
- error = gfs2_change_nlink(ip, +1);
-
-out_end_trans:
- gfs2_trans_end(sdp);
-out_ipres:
- if (alloc_required)
- gfs2_inplace_release(dip);
-out_gunlock_q:
- if (alloc_required)
- gfs2_quota_unlock(dip);
-out_alloc:
- if (alloc_required)
- gfs2_alloc_put(dip);
-out_gunlock:
- gfs2_glock_dq(ghs + 1);
-out_child:
- gfs2_glock_dq(ghs);
-out_parent:
- gfs2_holder_uninit(ghs);
- gfs2_holder_uninit(ghs + 1);
- if (!error) {
- ihold(inode);
- d_instantiate(dentry, inode);
- mark_inode_dirty(inode);
- }
- return error;
-}
-
-/*
- * gfs2_unlink_ok - check to see that a inode is still in a directory
- * @dip: the directory
- * @name: the name of the file
- * @ip: the inode
- *
- * Assumes that the lock on (at least) @dip is held.
- *
- * Returns: 0 if the parent/child relationship is correct, errno if it isn't
- */
-
-static int gfs2_unlink_ok(struct gfs2_inode *dip, const struct qstr *name,
- const struct gfs2_inode *ip)
-{
- int error;
-
- if (IS_IMMUTABLE(&ip->i_inode) || IS_APPEND(&ip->i_inode))
- return -EPERM;
-
- if ((dip->i_inode.i_mode & S_ISVTX) &&
- dip->i_inode.i_uid != current_fsuid() &&
- ip->i_inode.i_uid != current_fsuid() && !capable(CAP_FOWNER))
- return -EPERM;
-
- if (IS_APPEND(&dip->i_inode))
- return -EPERM;
-
- error = gfs2_permission(&dip->i_inode, MAY_WRITE | MAY_EXEC, 0);
- if (error)
- return error;
-
- error = gfs2_dir_check(&dip->i_inode, name, ip);
- if (error)
- return error;
-
- return 0;
-}
-
-/**
- * gfs2_unlink - Unlink a file
- * @dir: The inode of the directory containing the file to unlink
- * @dentry: The file itself
- *
- * Unlink a file. Call gfs2_unlinki()
- *
- * Returns: errno
- */
-
-static int gfs2_unlink(struct inode *dir, struct dentry *dentry)
-{
- struct gfs2_inode *dip = GFS2_I(dir);
- struct gfs2_sbd *sdp = GFS2_SB(dir);
- struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
- struct gfs2_holder ghs[3];
- struct gfs2_rgrpd *rgd;
- struct gfs2_holder ri_gh;
- int error;
-
- error = gfs2_rindex_hold(sdp, &ri_gh);
- if (error)
- return error;
-
- gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
- gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
-
- rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
- gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
-
-
- error = gfs2_glock_nq(ghs); /* parent */
- if (error)
- goto out_parent;
-
- error = gfs2_glock_nq(ghs + 1); /* child */
- if (error)
- goto out_child;
-
- error = gfs2_glock_nq(ghs + 2); /* rgrp */
- if (error)
- goto out_rgrp;
-
- error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
- if (error)
- goto out_gunlock;
-
- error = gfs2_trans_begin(sdp, 2*RES_DINODE + RES_LEAF + RES_RG_BIT, 0);
- if (error)
- goto out_gunlock;
-
- error = gfs2_dir_del(dip, &dentry->d_name);
- if (error)
- goto out_end_trans;
-
- error = gfs2_change_nlink(ip, -1);
-
-out_end_trans:
- gfs2_trans_end(sdp);
-out_gunlock:
- gfs2_glock_dq(ghs + 2);
-out_rgrp:
- gfs2_holder_uninit(ghs + 2);
- gfs2_glock_dq(ghs + 1);
-out_child:
- gfs2_holder_uninit(ghs + 1);
- gfs2_glock_dq(ghs);
-out_parent:
- gfs2_holder_uninit(ghs);
- gfs2_glock_dq_uninit(&ri_gh);
- return error;
-}
-
-/**
- * gfs2_symlink - Create a symlink
- * @dir: The directory to create the symlink in
- * @dentry: The dentry to put the symlink in
- * @symname: The thing which the link points to
- *
- * Returns: errno
- */
-
-static int gfs2_symlink(struct inode *dir, struct dentry *dentry,
- const char *symname)
-{
- struct gfs2_inode *dip = GFS2_I(dir), *ip;
- struct gfs2_sbd *sdp = GFS2_SB(dir);
- struct gfs2_holder ghs[2];
- struct inode *inode;
- struct buffer_head *dibh;
- int size;
- int error;
-
- /* Must be stuffed with a null terminator for gfs2_follow_link() */
- size = strlen(symname);
- if (size > sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode) - 1)
- return -ENAMETOOLONG;
-
- gfs2_holder_init(dip->i_gl, 0, 0, ghs);
-
- inode = gfs2_createi(ghs, &dentry->d_name, S_IFLNK | S_IRWXUGO, 0);
- if (IS_ERR(inode)) {
- gfs2_holder_uninit(ghs);
- return PTR_ERR(inode);
- }
-
- ip = ghs[1].gh_gl->gl_object;
-
- i_size_write(inode, size);
-
- error = gfs2_meta_inode_buffer(ip, &dibh);
-
- if (!gfs2_assert_withdraw(sdp, !error)) {
- gfs2_dinode_out(ip, dibh->b_data);
- memcpy(dibh->b_data + sizeof(struct gfs2_dinode), symname,
- size);
- brelse(dibh);
- }
-
- gfs2_trans_end(sdp);
- if (dip->i_alloc->al_rgd)
- gfs2_inplace_release(dip);
- gfs2_quota_unlock(dip);
- gfs2_alloc_put(dip);
-
- gfs2_glock_dq_uninit_m(2, ghs);
-
- d_instantiate(dentry, inode);
- mark_inode_dirty(inode);
-
- return 0;
-}
-
-/**
- * gfs2_mkdir - Make a directory
- * @dir: The parent directory of the new one
- * @dentry: The dentry of the new directory
- * @mode: The mode of the new directory
- *
- * Returns: errno
- */
-
-static int gfs2_mkdir(struct inode *dir, struct dentry *dentry, int mode)
-{
- struct gfs2_inode *dip = GFS2_I(dir), *ip;
- struct gfs2_sbd *sdp = GFS2_SB(dir);
- struct gfs2_holder ghs[2];
- struct inode *inode;
- struct buffer_head *dibh;
- int error;
-
- gfs2_holder_init(dip->i_gl, 0, 0, ghs);
-
- inode = gfs2_createi(ghs, &dentry->d_name, S_IFDIR | mode, 0);
- if (IS_ERR(inode)) {
- gfs2_holder_uninit(ghs);
- return PTR_ERR(inode);
- }
-
- ip = ghs[1].gh_gl->gl_object;
-
- ip->i_inode.i_nlink = 2;
- i_size_write(inode, sdp->sd_sb.sb_bsize - sizeof(struct gfs2_dinode));
- ip->i_diskflags |= GFS2_DIF_JDATA;
- ip->i_entries = 2;
-
- error = gfs2_meta_inode_buffer(ip, &dibh);
-
- if (!gfs2_assert_withdraw(sdp, !error)) {
- struct gfs2_dinode *di = (struct gfs2_dinode *)dibh->b_data;
- struct gfs2_dirent *dent = (struct gfs2_dirent *)(di+1);
-
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
- gfs2_qstr2dirent(&gfs2_qdot, GFS2_DIRENT_SIZE(gfs2_qdot.len), dent);
- dent->de_inum = di->di_num; /* already GFS2 endian */
- dent->de_type = cpu_to_be16(DT_DIR);
- di->di_entries = cpu_to_be32(1);
-
- dent = (struct gfs2_dirent *)((char*)dent + GFS2_DIRENT_SIZE(1));
- gfs2_qstr2dirent(&gfs2_qdotdot, dibh->b_size - GFS2_DIRENT_SIZE(1) - sizeof(struct gfs2_dinode), dent);
-
- gfs2_inum_out(dip, dent);
- dent->de_type = cpu_to_be16(DT_DIR);
-
- gfs2_dinode_out(ip, di);
-
- brelse(dibh);
- }
-
- error = gfs2_change_nlink(dip, +1);
- gfs2_assert_withdraw(sdp, !error); /* dip already pinned */
-
- gfs2_trans_end(sdp);
- if (dip->i_alloc->al_rgd)
- gfs2_inplace_release(dip);
- gfs2_quota_unlock(dip);
- gfs2_alloc_put(dip);
-
- gfs2_glock_dq_uninit_m(2, ghs);
-
- d_instantiate(dentry, inode);
- mark_inode_dirty(inode);
-
- return 0;
-}
-
-/**
- * gfs2_rmdiri - Remove a directory
- * @dip: The parent directory of the directory to be removed
- * @name: The name of the directory to be removed
- * @ip: The GFS2 inode of the directory to be removed
- *
- * Assumes Glocks on dip and ip are held
- *
- * Returns: errno
- */
-
-static int gfs2_rmdiri(struct gfs2_inode *dip, const struct qstr *name,
- struct gfs2_inode *ip)
-{
- int error;
-
- if (ip->i_entries != 2) {
- if (gfs2_consist_inode(ip))
- gfs2_dinode_print(ip);
- return -EIO;
- }
-
- error = gfs2_dir_del(dip, name);
- if (error)
- return error;
-
- error = gfs2_change_nlink(dip, -1);
- if (error)
- return error;
-
- error = gfs2_dir_del(ip, &gfs2_qdot);
- if (error)
- return error;
-
- error = gfs2_dir_del(ip, &gfs2_qdotdot);
- if (error)
- return error;
-
- /* It looks odd, but it really should be done twice */
- error = gfs2_change_nlink(ip, -1);
- if (error)
- return error;
-
- error = gfs2_change_nlink(ip, -1);
- if (error)
- return error;
-
- return error;
-}
-
-/**
- * gfs2_rmdir - Remove a directory
- * @dir: The parent directory of the directory to be removed
- * @dentry: The dentry of the directory to remove
- *
- * Remove a directory. Call gfs2_rmdiri()
- *
- * Returns: errno
- */
-
-static int gfs2_rmdir(struct inode *dir, struct dentry *dentry)
-{
- struct gfs2_inode *dip = GFS2_I(dir);
- struct gfs2_sbd *sdp = GFS2_SB(dir);
- struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
- struct gfs2_holder ghs[3];
- struct gfs2_rgrpd *rgd;
- struct gfs2_holder ri_gh;
- int error;
-
- error = gfs2_rindex_hold(sdp, &ri_gh);
- if (error)
- return error;
- gfs2_holder_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
- gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + 1);
-
- rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
- gfs2_holder_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + 2);
-
- error = gfs2_glock_nq(ghs); /* parent */
- if (error)
- goto out_parent;
-
- error = gfs2_glock_nq(ghs + 1); /* child */
- if (error)
- goto out_child;
-
- error = gfs2_glock_nq(ghs + 2); /* rgrp */
- if (error)
- goto out_rgrp;
-
- error = gfs2_unlink_ok(dip, &dentry->d_name, ip);
- if (error)
- goto out_gunlock;
-
- if (ip->i_entries < 2) {
- if (gfs2_consist_inode(ip))
- gfs2_dinode_print(ip);
- error = -EIO;
- goto out_gunlock;
- }
- if (ip->i_entries > 2) {
- error = -ENOTEMPTY;
- goto out_gunlock;
- }
-
- error = gfs2_trans_begin(sdp, 2 * RES_DINODE + 3 * RES_LEAF + RES_RG_BIT, 0);
- if (error)
- goto out_gunlock;
-
- error = gfs2_rmdiri(dip, &dentry->d_name, ip);
-
- gfs2_trans_end(sdp);
-
-out_gunlock:
- gfs2_glock_dq(ghs + 2);
-out_rgrp:
- gfs2_holder_uninit(ghs + 2);
- gfs2_glock_dq(ghs + 1);
-out_child:
- gfs2_holder_uninit(ghs + 1);
- gfs2_glock_dq(ghs);
-out_parent:
- gfs2_holder_uninit(ghs);
- gfs2_glock_dq_uninit(&ri_gh);
- return error;
-}
-
-/**
- * gfs2_mknod - Make a special file
- * @dir: The directory in which the special file will reside
- * @dentry: The dentry of the special file
- * @mode: The mode of the special file
- * @rdev: The device specification of the special file
- *
- */
-
-static int gfs2_mknod(struct inode *dir, struct dentry *dentry, int mode,
- dev_t dev)
-{
- struct gfs2_inode *dip = GFS2_I(dir);
- struct gfs2_sbd *sdp = GFS2_SB(dir);
- struct gfs2_holder ghs[2];
- struct inode *inode;
-
- gfs2_holder_init(dip->i_gl, 0, 0, ghs);
-
- inode = gfs2_createi(ghs, &dentry->d_name, mode, dev);
- if (IS_ERR(inode)) {
- gfs2_holder_uninit(ghs);
- return PTR_ERR(inode);
- }
-
- gfs2_trans_end(sdp);
- if (dip->i_alloc->al_rgd)
- gfs2_inplace_release(dip);
- gfs2_quota_unlock(dip);
- gfs2_alloc_put(dip);
-
- gfs2_glock_dq_uninit_m(2, ghs);
-
- d_instantiate(dentry, inode);
- mark_inode_dirty(inode);
-
- return 0;
-}
-
-/*
- * gfs2_ok_to_move - check if it's ok to move a directory to another directory
- * @this: move this
- * @to: to here
- *
- * Follow @to back to the root and make sure we don't encounter @this
- * Assumes we already hold the rename lock.
- *
- * Returns: errno
- */
-
-static int gfs2_ok_to_move(struct gfs2_inode *this, struct gfs2_inode *to)
-{
- struct inode *dir = &to->i_inode;
- struct super_block *sb = dir->i_sb;
- struct inode *tmp;
- int error = 0;
-
- igrab(dir);
-
- for (;;) {
- if (dir == &this->i_inode) {
- error = -EINVAL;
- break;
- }
- if (dir == sb->s_root->d_inode) {
- error = 0;
- break;
- }
-
- tmp = gfs2_lookupi(dir, &gfs2_qdotdot, 1);
- if (IS_ERR(tmp)) {
- error = PTR_ERR(tmp);
- break;
- }
-
- iput(dir);
- dir = tmp;
- }
-
- iput(dir);
-
- return error;
-}
-
-/**
- * gfs2_rename - Rename a file
- * @odir: Parent directory of old file name
- * @odentry: The old dentry of the file
- * @ndir: Parent directory of new file name
- * @ndentry: The new dentry of the file
- *
- * Returns: errno
- */
-
-static int gfs2_rename(struct inode *odir, struct dentry *odentry,
- struct inode *ndir, struct dentry *ndentry)
-{
- struct gfs2_inode *odip = GFS2_I(odir);
- struct gfs2_inode *ndip = GFS2_I(ndir);
- struct gfs2_inode *ip = GFS2_I(odentry->d_inode);
- struct gfs2_inode *nip = NULL;
- struct gfs2_sbd *sdp = GFS2_SB(odir);
- struct gfs2_holder ghs[5], r_gh = { .gh_gl = NULL, }, ri_gh;
- struct gfs2_rgrpd *nrgd;
- unsigned int num_gh;
- int dir_rename = 0;
- int alloc_required = 0;
- unsigned int x;
- int error;
-
- if (ndentry->d_inode) {
- nip = GFS2_I(ndentry->d_inode);
- if (ip == nip)
- return 0;
- }
-
- error = gfs2_rindex_hold(sdp, &ri_gh);
- if (error)
- return error;
-
- if (odip != ndip) {
- error = gfs2_glock_nq_init(sdp->sd_rename_gl, LM_ST_EXCLUSIVE,
- 0, &r_gh);
- if (error)
- goto out;
-
- if (S_ISDIR(ip->i_inode.i_mode)) {
- dir_rename = 1;
- /* don't move a dirctory into it's subdir */
- error = gfs2_ok_to_move(ip, ndip);
- if (error)
- goto out_gunlock_r;
- }
- }
-
- num_gh = 1;
- gfs2_holder_init(odip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
- if (odip != ndip) {
- gfs2_holder_init(ndip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
- num_gh++;
- }
- gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
- num_gh++;
-
- if (nip) {
- gfs2_holder_init(nip->i_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh);
- num_gh++;
- /* grab the resource lock for unlink flag twiddling
- * this is the case of the target file already existing
- * so we unlink before doing the rename
- */
- nrgd = gfs2_blk2rgrpd(sdp, nip->i_no_addr);
- if (nrgd)
- gfs2_holder_init(nrgd->rd_gl, LM_ST_EXCLUSIVE, 0, ghs + num_gh++);
- }
-
- for (x = 0; x < num_gh; x++) {
- error = gfs2_glock_nq(ghs + x);
- if (error)
- goto out_gunlock;
- }
-
- /* Check out the old directory */
-
- error = gfs2_unlink_ok(odip, &odentry->d_name, ip);
- if (error)
- goto out_gunlock;
-
- /* Check out the new directory */
-
- if (nip) {
- error = gfs2_unlink_ok(ndip, &ndentry->d_name, nip);
- if (error)
- goto out_gunlock;
-
- if (S_ISDIR(nip->i_inode.i_mode)) {
- if (nip->i_entries < 2) {
- if (gfs2_consist_inode(nip))
- gfs2_dinode_print(nip);
- error = -EIO;
- goto out_gunlock;
- }
- if (nip->i_entries > 2) {
- error = -ENOTEMPTY;
- goto out_gunlock;
- }
- }
- } else {
- error = gfs2_permission(ndir, MAY_WRITE | MAY_EXEC, 0);
- if (error)
- goto out_gunlock;
-
- error = gfs2_dir_check(ndir, &ndentry->d_name, NULL);
- switch (error) {
- case -ENOENT:
- error = 0;
- break;
- case 0:
- error = -EEXIST;
- default:
- goto out_gunlock;
- };
-
- if (odip != ndip) {
- if (!ndip->i_inode.i_nlink) {
- error = -EINVAL;
- goto out_gunlock;
- }
- if (ndip->i_entries == (u32)-1) {
- error = -EFBIG;
- goto out_gunlock;
- }
- if (S_ISDIR(ip->i_inode.i_mode) &&
- ndip->i_inode.i_nlink == (u32)-1) {
- error = -EMLINK;
- goto out_gunlock;
- }
- }
- }
-
- /* Check out the dir to be renamed */
-
- if (dir_rename) {
- error = gfs2_permission(odentry->d_inode, MAY_WRITE, 0);
- if (error)
- goto out_gunlock;
- }
-
- if (nip == NULL)
- alloc_required = gfs2_diradd_alloc_required(ndir, &ndentry->d_name);
- error = alloc_required;
- if (error < 0)
- goto out_gunlock;
- error = 0;
-
- if (alloc_required) {
- struct gfs2_alloc *al = gfs2_alloc_get(ndip);
- if (!al) {
- error = -ENOMEM;
- goto out_gunlock;
- }
-
- error = gfs2_quota_lock_check(ndip);
- if (error)
- goto out_alloc;
-
- al->al_requested = sdp->sd_max_dirres;
-
- error = gfs2_inplace_reserve_ri(ndip);
- if (error)
- goto out_gunlock_q;
-
- error = gfs2_trans_begin(sdp, sdp->sd_max_dirres +
- gfs2_rg_blocks(al) +
- 4 * RES_DINODE + 4 * RES_LEAF +
- RES_STATFS + RES_QUOTA + 4, 0);
- if (error)
- goto out_ipreserv;
- } else {
- error = gfs2_trans_begin(sdp, 4 * RES_DINODE +
- 5 * RES_LEAF + 4, 0);
- if (error)
- goto out_gunlock;
- }
-
- /* Remove the target file, if it exists */
-
- if (nip) {
- if (S_ISDIR(nip->i_inode.i_mode))
- error = gfs2_rmdiri(ndip, &ndentry->d_name, nip);
- else {
- error = gfs2_dir_del(ndip, &ndentry->d_name);
- if (error)
- goto out_end_trans;
- error = gfs2_change_nlink(nip, -1);
- }
- if (error)
- goto out_end_trans;
- }
-
- if (dir_rename) {
- error = gfs2_change_nlink(ndip, +1);
- if (error)
- goto out_end_trans;
- error = gfs2_change_nlink(odip, -1);
- if (error)
- goto out_end_trans;
-
- error = gfs2_dir_mvino(ip, &gfs2_qdotdot, ndip, DT_DIR);
- if (error)
- goto out_end_trans;
- } else {
- struct buffer_head *dibh;
- error = gfs2_meta_inode_buffer(ip, &dibh);
- if (error)
- goto out_end_trans;
- ip->i_inode.i_ctime = CURRENT_TIME;
- gfs2_trans_add_bh(ip->i_gl, dibh, 1);
- gfs2_dinode_out(ip, dibh->b_data);
- brelse(dibh);
- }
-
- error = gfs2_dir_del(odip, &odentry->d_name);
- if (error)
- goto out_end_trans;
-
- error = gfs2_dir_add(ndir, &ndentry->d_name, ip, IF2DT(ip->i_inode.i_mode));
- if (error)
- goto out_end_trans;
-
-out_end_trans:
- gfs2_trans_end(sdp);
-out_ipreserv:
- if (alloc_required)
- gfs2_inplace_release(ndip);
-out_gunlock_q:
- if (alloc_required)
- gfs2_quota_unlock(ndip);
-out_alloc:
- if (alloc_required)
- gfs2_alloc_put(ndip);
-out_gunlock:
- while (x--) {
- gfs2_glock_dq(ghs + x);
- gfs2_holder_uninit(ghs + x);
- }
-out_gunlock_r:
- if (r_gh.gh_gl)
- gfs2_glock_dq_uninit(&r_gh);
-out:
- gfs2_glock_dq_uninit(&ri_gh);
- return error;
-}
-
-/**
- * gfs2_follow_link - Follow a symbolic link
- * @dentry: The dentry of the link
- * @nd: Data that we pass to vfs_follow_link()
- *
- * This can handle symlinks of any size.
- *
- * Returns: 0 on success or error code
- */
-
-static void *gfs2_follow_link(struct dentry *dentry, struct nameidata *nd)
-{
- struct gfs2_inode *ip = GFS2_I(dentry->d_inode);
- struct gfs2_holder i_gh;
- struct buffer_head *dibh;
- unsigned int x, size;
- char *buf;
- int error;
-
- gfs2_holder_init(ip->i_gl, LM_ST_SHARED, 0, &i_gh);
- error = gfs2_glock_nq(&i_gh);
- if (error) {
- gfs2_holder_uninit(&i_gh);
- nd_set_link(nd, ERR_PTR(error));
- return NULL;
- }
-
- size = (unsigned int)i_size_read(&ip->i_inode);
- if (size == 0) {
- gfs2_consist_inode(ip);
- buf = ERR_PTR(-EIO);
- goto out;
- }
-
- error = gfs2_meta_inode_buffer(ip, &dibh);
- if (error) {
- buf = ERR_PTR(error);
- goto out;
- }
-
- x = size + 1;
- buf = kmalloc(x, GFP_NOFS);
- if (!buf)
- buf = ERR_PTR(-ENOMEM);
- else
- memcpy(buf, dibh->b_data + sizeof(struct gfs2_dinode), x);
- brelse(dibh);
-out:
- gfs2_glock_dq_uninit(&i_gh);
- nd_set_link(nd, buf);
- return NULL;
-}
-
-static void gfs2_put_link(struct dentry *dentry, struct nameidata *nd, void *p)
-{
- char *s = nd_get_link(nd);
- if (!IS_ERR(s))
- kfree(s);
-}
-
-/**
- * gfs2_permission -
- * @inode:
- * @mask:
- * @nd: passed from Linux VFS, ignored by us
- *
- * This may be called from the VFS directly, or from within GFS2 with the
- * inode locked, so we look to see if the glock is already locked and only
- * lock the glock if its not already been done.
- *
- * Returns: errno
- */
-
-int gfs2_permission(struct inode *inode, int mask, unsigned int flags)
-{
- struct gfs2_inode *ip;
- struct gfs2_holder i_gh;
- int error;
- int unlock = 0;
-
- if (flags & IPERM_FLAG_RCU)
- return -ECHILD;
-
- ip = GFS2_I(inode);
- if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
- error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &i_gh);
- if (error)
- return error;
- unlock = 1;
- }
-
- if ((mask & MAY_WRITE) && IS_IMMUTABLE(inode))
- error = -EACCES;
- else
- error = generic_permission(inode, mask, flags, gfs2_check_acl);
- if (unlock)
- gfs2_glock_dq_uninit(&i_gh);
-
- return error;
-}
-
-static int setattr_chown(struct inode *inode, struct iattr *attr)
-{
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_sbd *sdp = GFS2_SB(inode);
- u32 ouid, ogid, nuid, ngid;
- int error;
-
- ouid = inode->i_uid;
- ogid = inode->i_gid;
- nuid = attr->ia_uid;
- ngid = attr->ia_gid;
-
- if (!(attr->ia_valid & ATTR_UID) || ouid == nuid)
- ouid = nuid = NO_QUOTA_CHANGE;
- if (!(attr->ia_valid & ATTR_GID) || ogid == ngid)
- ogid = ngid = NO_QUOTA_CHANGE;
-
- if (!gfs2_alloc_get(ip))
- return -ENOMEM;
-
- error = gfs2_quota_lock(ip, nuid, ngid);
- if (error)
- goto out_alloc;
-
- if (ouid != NO_QUOTA_CHANGE || ogid != NO_QUOTA_CHANGE) {
- error = gfs2_quota_check(ip, nuid, ngid);
- if (error)
- goto out_gunlock_q;
- }
-
- error = gfs2_trans_begin(sdp, RES_DINODE + 2 * RES_QUOTA, 0);
- if (error)
- goto out_gunlock_q;
-
- error = gfs2_setattr_simple(ip, attr);
- if (error)
- goto out_end_trans;
-
- if (ouid != NO_QUOTA_CHANGE || ogid != NO_QUOTA_CHANGE) {
- u64 blocks = gfs2_get_inode_blocks(&ip->i_inode);
- gfs2_quota_change(ip, -blocks, ouid, ogid);
- gfs2_quota_change(ip, blocks, nuid, ngid);
- }
-
-out_end_trans:
- gfs2_trans_end(sdp);
-out_gunlock_q:
- gfs2_quota_unlock(ip);
-out_alloc:
- gfs2_alloc_put(ip);
- return error;
-}
-
-/**
- * gfs2_setattr - Change attributes on an inode
- * @dentry: The dentry which is changing
- * @attr: The structure describing the change
- *
- * The VFS layer wants to change one or more of an inodes attributes. Write
- * that change out to disk.
- *
- * Returns: errno
- */
-
-static int gfs2_setattr(struct dentry *dentry, struct iattr *attr)
-{
- struct inode *inode = dentry->d_inode;
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_holder i_gh;
- int error;
-
- error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &i_gh);
- if (error)
- return error;
-
- error = -EPERM;
- if (IS_IMMUTABLE(inode) || IS_APPEND(inode))
- goto out;
-
- error = inode_change_ok(inode, attr);
- if (error)
- goto out;
-
- if (attr->ia_valid & ATTR_SIZE)
- error = gfs2_setattr_size(inode, attr->ia_size);
- else if (attr->ia_valid & (ATTR_UID | ATTR_GID))
- error = setattr_chown(inode, attr);
- else if ((attr->ia_valid & ATTR_MODE) && IS_POSIXACL(inode))
- error = gfs2_acl_chmod(ip, attr);
- else
- error = gfs2_setattr_simple(ip, attr);
-
-out:
- gfs2_glock_dq_uninit(&i_gh);
- if (!error)
- mark_inode_dirty(inode);
- return error;
-}
-
-/**
- * gfs2_getattr - Read out an inode's attributes
- * @mnt: The vfsmount the inode is being accessed from
- * @dentry: The dentry to stat
- * @stat: The inode's stats
- *
- * This may be called from the VFS directly, or from within GFS2 with the
- * inode locked, so we look to see if the glock is already locked and only
- * lock the glock if its not already been done. Note that its the NFS
- * readdirplus operation which causes this to be called (from filldir)
- * with the glock already held.
- *
- * Returns: errno
- */
-
-static int gfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
- struct kstat *stat)
-{
- struct inode *inode = dentry->d_inode;
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_holder gh;
- int error;
- int unlock = 0;
-
- if (gfs2_glock_is_locked_by_me(ip->i_gl) == NULL) {
- error = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
- if (error)
- return error;
- unlock = 1;
- }
-
- generic_fillattr(inode, stat);
- if (unlock)
- gfs2_glock_dq_uninit(&gh);
-
- return 0;
-}
-
-static int gfs2_setxattr(struct dentry *dentry, const char *name,
- const void *data, size_t size, int flags)
-{
- struct inode *inode = dentry->d_inode;
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_holder gh;
- int ret;
-
- gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
- ret = gfs2_glock_nq(&gh);
- if (ret == 0) {
- ret = generic_setxattr(dentry, name, data, size, flags);
- gfs2_glock_dq(&gh);
- }
- gfs2_holder_uninit(&gh);
- return ret;
-}
-
-static ssize_t gfs2_getxattr(struct dentry *dentry, const char *name,
- void *data, size_t size)
-{
- struct inode *inode = dentry->d_inode;
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_holder gh;
- int ret;
-
- gfs2_holder_init(ip->i_gl, LM_ST_SHARED, LM_FLAG_ANY, &gh);
- ret = gfs2_glock_nq(&gh);
- if (ret == 0) {
- ret = generic_getxattr(dentry, name, data, size);
- gfs2_glock_dq(&gh);
- }
- gfs2_holder_uninit(&gh);
- return ret;
-}
-
-static int gfs2_removexattr(struct dentry *dentry, const char *name)
-{
- struct inode *inode = dentry->d_inode;
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_holder gh;
- int ret;
-
- gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
- ret = gfs2_glock_nq(&gh);
- if (ret == 0) {
- ret = generic_removexattr(dentry, name);
- gfs2_glock_dq(&gh);
- }
- gfs2_holder_uninit(&gh);
- return ret;
-}
-
-static int gfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
- u64 start, u64 len)
-{
- struct gfs2_inode *ip = GFS2_I(inode);
- struct gfs2_holder gh;
- int ret;
-
- ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
- if (ret)
- return ret;
-
- mutex_lock(&inode->i_mutex);
-
- ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_SHARED, 0, &gh);
- if (ret)
- goto out;
-
- if (gfs2_is_stuffed(ip)) {
- u64 phys = ip->i_no_addr << inode->i_blkbits;
- u64 size = i_size_read(inode);
- u32 flags = FIEMAP_EXTENT_LAST|FIEMAP_EXTENT_NOT_ALIGNED|
- FIEMAP_EXTENT_DATA_INLINE;
- phys += sizeof(struct gfs2_dinode);
- phys += start;
- if (start + len > size)
- len = size - start;
- if (start < size)
- ret = fiemap_fill_next_extent(fieinfo, start, phys,
- len, flags);
- if (ret == 1)
- ret = 0;
- } else {
- ret = __generic_block_fiemap(inode, fieinfo, start, len,
- gfs2_block_map);
- }
-
- gfs2_glock_dq_uninit(&gh);
-out:
- mutex_unlock(&inode->i_mutex);
- return ret;
-}
-
-const struct inode_operations gfs2_file_iops = {
- .permission = gfs2_permission,
- .setattr = gfs2_setattr,
- .getattr = gfs2_getattr,
- .setxattr = gfs2_setxattr,
- .getxattr = gfs2_getxattr,
- .listxattr = gfs2_listxattr,
- .removexattr = gfs2_removexattr,
- .fiemap = gfs2_fiemap,
-};
-
-const struct inode_operations gfs2_dir_iops = {
- .create = gfs2_create,
- .lookup = gfs2_lookup,
- .link = gfs2_link,
- .unlink = gfs2_unlink,
- .symlink = gfs2_symlink,
- .mkdir = gfs2_mkdir,
- .rmdir = gfs2_rmdir,
- .mknod = gfs2_mknod,
- .rename = gfs2_rename,
- .permission = gfs2_permission,
- .setattr = gfs2_setattr,
- .getattr = gfs2_getattr,
- .setxattr = gfs2_setxattr,
- .getxattr = gfs2_getxattr,
- .listxattr = gfs2_listxattr,
- .removexattr = gfs2_removexattr,
- .fiemap = gfs2_fiemap,
-};
-
-const struct inode_operations gfs2_symlink_iops = {
- .readlink = generic_readlink,
- .follow_link = gfs2_follow_link,
- .put_link = gfs2_put_link,
- .permission = gfs2_permission,
- .setattr = gfs2_setattr,
- .getattr = gfs2_getattr,
- .setxattr = gfs2_setxattr,
- .getxattr = gfs2_getxattr,
- .listxattr = gfs2_listxattr,
- .removexattr = gfs2_removexattr,
- .fiemap = gfs2_fiemap,
-};
-
diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
index a689901963d..42e8d23bc04 100644
--- a/fs/gfs2/quota.c
+++ b/fs/gfs2/quota.c
@@ -38,6 +38,7 @@
#include <linux/sched.h>
#include <linux/slab.h>
+#include <linux/mm.h>
#include <linux/spinlock.h>
#include <linux/completion.h>
#include <linux/buffer_head.h>
@@ -77,19 +78,20 @@ 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(struct shrinker *shrink, int nr, gfp_t gfp_mask)
+int gfs2_shrink_qd_memory(struct shrinker *shrink, struct shrink_control *sc)
{
struct gfs2_quota_data *qd;
struct gfs2_sbd *sdp;
+ int nr_to_scan = sc->nr_to_scan;
- if (nr == 0)
+ if (nr_to_scan == 0)
goto out;
- if (!(gfp_mask & __GFP_FS))
+ if (!(sc->gfp_mask & __GFP_FS))
return -1;
spin_lock(&qd_lru_lock);
- while (nr && !list_empty(&qd_lru_list)) {
+ while (nr_to_scan && !list_empty(&qd_lru_list)) {
qd = list_entry(qd_lru_list.next,
struct gfs2_quota_data, qd_reclaim);
sdp = qd->qd_gl->gl_sbd;
@@ -110,7 +112,7 @@ int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask)
spin_unlock(&qd_lru_lock);
kmem_cache_free(gfs2_quotad_cachep, qd);
spin_lock(&qd_lru_lock);
- nr--;
+ nr_to_scan--;
}
spin_unlock(&qd_lru_lock);
@@ -834,6 +836,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
goto out_end_trans;
do_qc(qd, -qd->qd_change_sync);
+ set_bit(QDF_REFRESH, &qd->qd_flags);
}
error = 0;
@@ -929,6 +932,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, u32 uid, u32 gid)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_alloc *al = ip->i_alloc;
+ struct gfs2_quota_data *qd;
unsigned int x;
int error = 0;
@@ -942,7 +946,11 @@ int gfs2_quota_lock(struct gfs2_inode *ip, u32 uid, u32 gid)
sort_qd, NULL);
for (x = 0; x < al->al_qd_num; x++) {
- error = do_glock(al->al_qd[x], NO_FORCE, &al->al_qd_ghs[x]);
+ int force = NO_FORCE;
+ qd = al->al_qd[x];
+ if (test_and_clear_bit(QDF_REFRESH, &qd->qd_flags))
+ force = FORCE;
+ error = do_glock(qd, force, &al->al_qd_ghs[x]);
if (error)
break;
}
@@ -1587,6 +1595,8 @@ static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id,
offset = qd2offset(qd);
alloc_required = gfs2_write_alloc_required(ip, offset, sizeof(struct gfs2_quota));
+ if (gfs2_is_stuffed(ip))
+ alloc_required = 1;
if (alloc_required) {
al = gfs2_alloc_get(ip);
if (al == NULL)
@@ -1600,7 +1610,9 @@ static int gfs2_set_dqblk(struct super_block *sb, int type, qid_t id,
blocks += gfs2_rg_blocks(al);
}
- error = gfs2_trans_begin(sdp, blocks + RES_DINODE + 1, 0);
+ /* Some quotas span block boundaries and can update two blocks,
+ adding an extra block to the transaction to handle such quotas */
+ error = gfs2_trans_begin(sdp, blocks + RES_DINODE + 2, 0);
if (error)
goto out_release;
diff --git a/fs/gfs2/quota.h b/fs/gfs2/quota.h
index e7d236ca48b..90bf1c302a9 100644
--- a/fs/gfs2/quota.h
+++ b/fs/gfs2/quota.h
@@ -12,6 +12,7 @@
struct gfs2_inode;
struct gfs2_sbd;
+struct shrink_control;
#define NO_QUOTA_CHANGE ((u32)-1)
@@ -51,7 +52,8 @@ static inline int gfs2_quota_lock_check(struct gfs2_inode *ip)
return ret;
}
-extern int gfs2_shrink_qd_memory(struct shrinker *shrink, int nr, gfp_t gfp_mask);
+extern int gfs2_shrink_qd_memory(struct shrinker *shrink,
+ struct shrink_control *sc);
extern const struct quotactl_ops gfs2_quotactl_ops;
#endif /* __QUOTA_DOT_H__ */
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 7293ea27020..9b780df3fd5 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -78,10 +78,11 @@ static u32 rgblk_search(struct gfs2_rgrpd *rgd, u32 goal,
static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf1,
unsigned char *buf2, unsigned int offset,
- unsigned int buflen, u32 block,
+ struct gfs2_bitmap *bi, u32 block,
unsigned char new_state)
{
unsigned char *byte1, *byte2, *end, cur_state;
+ unsigned int buflen = bi->bi_len;
const unsigned int bit = (block % GFS2_NBBY) * GFS2_BIT_SIZE;
byte1 = buf1 + offset + (block / GFS2_NBBY);
@@ -92,6 +93,16 @@ static inline void gfs2_setbit(struct gfs2_rgrpd *rgd, unsigned char *buf1,
cur_state = (*byte1 >> bit) & GFS2_BIT_MASK;
if (unlikely(!valid_change[new_state * 4 + cur_state])) {
+ printk(KERN_WARNING "GFS2: buf_blk = 0x%llx old_state=%d, "
+ "new_state=%d\n",
+ (unsigned long long)block, cur_state, new_state);
+ printk(KERN_WARNING "GFS2: rgrp=0x%llx bi_start=0x%lx\n",
+ (unsigned long long)rgd->rd_addr,
+ (unsigned long)bi->bi_start);
+ printk(KERN_WARNING "GFS2: bi_offset=0x%lx bi_len=0x%lx\n",
+ (unsigned long)bi->bi_offset,
+ (unsigned long)bi->bi_len);
+ dump_stack();
gfs2_consist_rgrpd(rgd);
return;
}
@@ -381,6 +392,7 @@ static void clear_rgrpdi(struct gfs2_sbd *sdp)
if (gl) {
gl->gl_object = NULL;
+ gfs2_glock_add_to_lru(gl);
gfs2_glock_put(gl);
}
@@ -945,7 +957,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip
/* rgblk_search can return a block < goal, so we need to
keep it marching forward. */
no_addr = block + rgd->rd_data0;
- goal++;
+ goal = max(block + 1, goal + 1);
if (*last_unlinked != NO_BLOCK && no_addr <= *last_unlinked)
continue;
if (no_addr == skip)
@@ -971,7 +983,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip
found++;
/* Limit reclaim to sensible number of tasks */
- if (found > 2*NR_CPUS)
+ if (found > NR_CPUS)
return;
}
@@ -1365,7 +1377,7 @@ skip:
gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset,
- bi->bi_len, blk, new_state);
+ bi, blk, new_state);
goal = blk;
while (*n < elen) {
goal++;
@@ -1375,7 +1387,7 @@ skip:
GFS2_BLKST_FREE)
break;
gfs2_setbit(rgd, bi->bi_bh->b_data, bi->bi_clone, bi->bi_offset,
- bi->bi_len, goal, new_state);
+ bi, goal, new_state);
(*n)++;
}
out:
@@ -1432,7 +1444,7 @@ static struct gfs2_rgrpd *rgblk_free(struct gfs2_sbd *sdp, u64 bstart,
}
gfs2_trans_add_bh(rgd->rd_gl, bi->bi_bh, 1);
gfs2_setbit(rgd, bi->bi_bh->b_data, NULL, bi->bi_offset,
- bi->bi_len, buf_blk, new_state);
+ bi, buf_blk, new_state);
}
return rgd;
@@ -1602,7 +1614,7 @@ rgrp_error:
*
*/
-void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen)
+void __gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_rgrpd *rgd;
@@ -1618,6 +1630,24 @@ void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen)
gfs2_trans_add_rg(rgd);
+ /* Directories keep their data in the metadata address space */
+ if (ip->i_depth)
+ gfs2_meta_wipe(ip, bstart, blen);
+}
+
+/**
+ * gfs2_free_data - free a contiguous run of data block(s)
+ * @ip: the inode these blocks are being freed from
+ * @bstart: first block of a run of contiguous blocks
+ * @blen: the length of the block run
+ *
+ */
+
+void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen)
+{
+ struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+ __gfs2_free_data(ip, bstart, blen);
gfs2_statfs_change(sdp, 0, +blen, 0);
gfs2_quota_change(ip, -(s64)blen, ip->i_inode.i_uid, ip->i_inode.i_gid);
}
@@ -1630,7 +1660,7 @@ void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen)
*
*/
-void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen)
+void __gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen)
{
struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
struct gfs2_rgrpd *rgd;
@@ -1645,10 +1675,24 @@ void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen)
gfs2_rgrp_out(rgd, rgd->rd_bits[0].bi_bh->b_data);
gfs2_trans_add_rg(rgd);
+ gfs2_meta_wipe(ip, bstart, blen);
+}
+
+/**
+ * gfs2_free_meta - free a contiguous run of data block(s)
+ * @ip: the inode these blocks are being freed from
+ * @bstart: first block of a run of contiguous blocks
+ * @blen: the length of the block run
+ *
+ */
+
+void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen)
+{
+ struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+ __gfs2_free_meta(ip, bstart, blen);
gfs2_statfs_change(sdp, 0, +blen, 0);
gfs2_quota_change(ip, -(s64)blen, ip->i_inode.i_uid, ip->i_inode.i_gid);
- gfs2_meta_wipe(ip, bstart, blen);
}
void gfs2_unlink_di(struct inode *inode)
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index 50c2bb04369..a80e3034ac4 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -52,7 +52,9 @@ extern int gfs2_ri_update(struct gfs2_inode *ip);
extern int gfs2_alloc_block(struct gfs2_inode *ip, u64 *bn, unsigned int *n);
extern int gfs2_alloc_di(struct gfs2_inode *ip, u64 *bn, u64 *generation);
+extern void __gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen);
extern void gfs2_free_data(struct gfs2_inode *ip, u64 bstart, u32 blen);
+extern void __gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
extern void gfs2_free_meta(struct gfs2_inode *ip, u64 bstart, u32 blen);
extern void gfs2_free_di(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip);
extern void gfs2_unlink_di(struct inode *inode);
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index ec73ed70bae..ed540e7018b 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -23,6 +23,7 @@
#include <linux/time.h>
#include <linux/wait.h>
#include <linux/writeback.h>
+#include <linux/backing-dev.h>
#include "gfs2.h"
#include "incore.h"
@@ -657,7 +658,7 @@ out:
* @sdp: the file system
*
* This function flushes data and meta data for all machines by
- * aquiring the transaction log exclusively. All journals are
+ * acquiring the transaction log exclusively. All journals are
* ensured to be in a clean state as well.
*
* Returns: errno
@@ -700,11 +701,47 @@ void gfs2_unfreeze_fs(struct gfs2_sbd *sdp)
mutex_unlock(&sdp->sd_freeze_lock);
}
+void gfs2_dinode_out(const struct gfs2_inode *ip, void *buf)
+{
+ struct gfs2_dinode *str = buf;
+
+ str->di_header.mh_magic = cpu_to_be32(GFS2_MAGIC);
+ str->di_header.mh_type = cpu_to_be32(GFS2_METATYPE_DI);
+ str->di_header.mh_format = cpu_to_be32(GFS2_FORMAT_DI);
+ str->di_num.no_addr = cpu_to_be64(ip->i_no_addr);
+ str->di_num.no_formal_ino = cpu_to_be64(ip->i_no_formal_ino);
+ str->di_mode = cpu_to_be32(ip->i_inode.i_mode);
+ str->di_uid = cpu_to_be32(ip->i_inode.i_uid);
+ str->di_gid = cpu_to_be32(ip->i_inode.i_gid);
+ str->di_nlink = cpu_to_be32(ip->i_inode.i_nlink);
+ str->di_size = cpu_to_be64(i_size_read(&ip->i_inode));
+ str->di_blocks = cpu_to_be64(gfs2_get_inode_blocks(&ip->i_inode));
+ str->di_atime = cpu_to_be64(ip->i_inode.i_atime.tv_sec);
+ str->di_mtime = cpu_to_be64(ip->i_inode.i_mtime.tv_sec);
+ str->di_ctime = cpu_to_be64(ip->i_inode.i_ctime.tv_sec);
+
+ str->di_goal_meta = cpu_to_be64(ip->i_goal);
+ str->di_goal_data = cpu_to_be64(ip->i_goal);
+ str->di_generation = cpu_to_be64(ip->i_generation);
+
+ str->di_flags = cpu_to_be32(ip->i_diskflags);
+ str->di_height = cpu_to_be16(ip->i_height);
+ str->di_payload_format = cpu_to_be32(S_ISDIR(ip->i_inode.i_mode) &&
+ !(ip->i_diskflags & GFS2_DIF_EXHASH) ?
+ GFS2_FORMAT_DE : 0);
+ str->di_depth = cpu_to_be16(ip->i_depth);
+ str->di_entries = cpu_to_be32(ip->i_entries);
+
+ str->di_eattr = cpu_to_be64(ip->i_eattr);
+ str->di_atime_nsec = cpu_to_be32(ip->i_inode.i_atime.tv_nsec);
+ str->di_mtime_nsec = cpu_to_be32(ip->i_inode.i_mtime.tv_nsec);
+ str->di_ctime_nsec = cpu_to_be32(ip->i_inode.i_ctime.tv_nsec);
+}
/**
* gfs2_write_inode - Make sure the inode is stable on the disk
* @inode: The inode
- * @sync: synchronous write flag
+ * @wbc: The writeback control structure
*
* Returns: errno
*/
@@ -713,15 +750,17 @@ static int gfs2_write_inode(struct inode *inode, struct writeback_control *wbc)
{
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_sbd *sdp = GFS2_SB(inode);
+ struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
+ struct backing_dev_info *bdi = metamapping->backing_dev_info;
struct gfs2_holder gh;
struct buffer_head *bh;
struct timespec atime;
struct gfs2_dinode *di;
- int ret = 0;
+ int ret = -EAGAIN;
- /* Check this is a "normal" inode, etc */
+ /* Skip timestamp update, if this is from a memalloc */
if (current->flags & PF_MEMALLOC)
- return 0;
+ goto do_flush;
ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
if (ret)
goto do_flush;
@@ -745,6 +784,13 @@ do_unlock:
do_flush:
if (wbc->sync_mode == WB_SYNC_ALL)
gfs2_log_flush(GFS2_SB(inode), ip->i_gl);
+ filemap_fdatawrite(metamapping);
+ if (bdi->dirty_exceeded)
+ gfs2_ail1_flush(sdp, wbc);
+ if (!ret && (wbc->sync_mode == WB_SYNC_ALL))
+ ret = filemap_fdatawait(metamapping);
+ if (ret)
+ mark_inode_dirty_sync(inode);
return ret;
}
@@ -874,8 +920,9 @@ restart:
static int gfs2_sync_fs(struct super_block *sb, int wait)
{
- if (wait && sb->s_fs_info)
- gfs2_log_flush(sb->s_fs_info, NULL);
+ struct gfs2_sbd *sdp = sb->s_fs_info;
+ if (wait && sdp)
+ gfs2_log_flush(sdp, NULL);
return 0;
}
@@ -1308,6 +1355,78 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
return 0;
}
+static void gfs2_final_release_pages(struct gfs2_inode *ip)
+{
+ struct inode *inode = &ip->i_inode;
+ struct gfs2_glock *gl = ip->i_gl;
+
+ truncate_inode_pages(gfs2_glock2aspace(ip->i_gl), 0);
+ truncate_inode_pages(&inode->i_data, 0);
+
+ if (atomic_read(&gl->gl_revokes) == 0) {
+ clear_bit(GLF_LFLUSH, &gl->gl_flags);
+ clear_bit(GLF_DIRTY, &gl->gl_flags);
+ }
+}
+
+static int gfs2_dinode_dealloc(struct gfs2_inode *ip)
+{
+ struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+ struct gfs2_alloc *al;
+ struct gfs2_rgrpd *rgd;
+ int error;
+
+ if (gfs2_get_inode_blocks(&ip->i_inode) != 1) {
+ gfs2_consist_inode(ip);
+ return -EIO;
+ }
+
+ al = gfs2_alloc_get(ip);
+ if (!al)
+ return -ENOMEM;
+
+ error = gfs2_quota_hold(ip, NO_QUOTA_CHANGE, NO_QUOTA_CHANGE);
+ if (error)
+ goto out;
+
+ error = gfs2_rindex_hold(sdp, &al->al_ri_gh);
+ if (error)
+ goto out_qs;
+
+ rgd = gfs2_blk2rgrpd(sdp, ip->i_no_addr);
+ if (!rgd) {
+ gfs2_consist_inode(ip);
+ error = -EIO;
+ goto out_rindex_relse;
+ }
+
+ error = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE, 0,
+ &al->al_rgd_gh);
+ if (error)
+ goto out_rindex_relse;
+
+ error = gfs2_trans_begin(sdp, RES_RG_BIT + RES_STATFS + RES_QUOTA,
+ sdp->sd_jdesc->jd_blocks);
+ if (error)
+ goto out_rg_gunlock;
+
+ gfs2_free_di(rgd, ip);
+
+ gfs2_final_release_pages(ip);
+
+ gfs2_trans_end(sdp);
+
+out_rg_gunlock:
+ gfs2_glock_dq_uninit(&al->al_rgd_gh);
+out_rindex_relse:
+ gfs2_glock_dq_uninit(&al->al_ri_gh);
+out_qs:
+ gfs2_quota_unhold(ip);
+out:
+ gfs2_alloc_put(ip);
+ return error;
+}
+
/*
* We have to (at the moment) hold the inodes main lock to cover
* the gap between unlocking the shared lock on the iopen lock and
@@ -1318,15 +1437,17 @@ static int gfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
static void gfs2_evict_inode(struct inode *inode)
{
- struct gfs2_sbd *sdp = inode->i_sb->s_fs_info;
+ struct super_block *sb = inode->i_sb;
+ struct gfs2_sbd *sdp = sb->s_fs_info;
struct gfs2_inode *ip = GFS2_I(inode);
struct gfs2_holder gh;
int error;
- if (inode->i_nlink)
+ if (inode->i_nlink || (sb->s_flags & MS_RDONLY))
goto out;
- error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
+ /* Must not read inode block until block type has been verified */
+ error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh);
if (unlikely(error)) {
gfs2_glock_dq_uninit(&ip->i_iopen_gh);
goto out;
@@ -1336,6 +1457,12 @@ static void gfs2_evict_inode(struct inode *inode)
if (error)
goto out_truncate;
+ if (test_bit(GIF_INVALID, &ip->i_flags)) {
+ error = gfs2_inode_refresh(ip);
+ if (error)
+ goto out_truncate;
+ }
+
ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
gfs2_glock_dq_wait(&ip->i_iopen_gh);
gfs2_holder_reinit(LM_ST_EXCLUSIVE, LM_FLAG_TRY_1CB | GL_NOCACHE, &ip->i_iopen_gh);
@@ -1363,15 +1490,13 @@ static void gfs2_evict_inode(struct inode *inode)
}
error = gfs2_dinode_dealloc(ip);
- if (error)
- goto out_unlock;
+ goto out_unlock;
out_truncate:
error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks);
if (error)
goto out_unlock;
- /* Needs to be done before glock release & also in a transaction */
- truncate_inode_pages(&inode->i_data, 0);
+ gfs2_final_release_pages(ip);
gfs2_trans_end(sdp);
out_unlock:
@@ -1386,6 +1511,7 @@ out:
end_writeback(inode);
ip->i_gl->gl_object = NULL;
+ gfs2_glock_add_to_lru(ip->i_gl);
gfs2_glock_put(ip->i_gl);
ip->i_gl = NULL;
if (ip->i_iopen_gh.gh_gl) {
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index 748ccb557c1..e20eab37bc8 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -81,7 +81,8 @@ static int gfs2_uuid_valid(const u8 *uuid)
static ssize_t uuid_show(struct gfs2_sbd *sdp, char *buf)
{
- const u8 *uuid = sdp->sd_sb.sb_uuid;
+ struct super_block *s = sdp->sd_vfs;
+ const u8 *uuid = s->s_uuid;
buf[0] = '\0';
if (!gfs2_uuid_valid(uuid))
return 0;
@@ -616,7 +617,8 @@ static int gfs2_uevent(struct kset *kset, struct kobject *kobj,
struct kobj_uevent_env *env)
{
struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
- const u8 *uuid = sdp->sd_sb.sb_uuid;
+ struct super_block *s = sdp->sd_vfs;
+ const u8 *uuid = s->s_uuid;
add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name);
add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name);
diff --git a/fs/gfs2/trace_gfs2.h b/fs/gfs2/trace_gfs2.h
index cedb0bb96d9..5d07609ec57 100644
--- a/fs/gfs2/trace_gfs2.h
+++ b/fs/gfs2/trace_gfs2.h
@@ -10,6 +10,7 @@
#include <linux/buffer_head.h>
#include <linux/dlmconstants.h>
#include <linux/gfs2_ondisk.h>
+#include <linux/writeback.h>
#include "incore.h"
#include "glock.h"
@@ -40,7 +41,9 @@
{(1UL << GLF_REPLY_PENDING), "r" }, \
{(1UL << GLF_INITIAL), "I" }, \
{(1UL << GLF_FROZEN), "F" }, \
- {(1UL << GLF_QUEUED), "q" })
+ {(1UL << GLF_QUEUED), "q" }, \
+ {(1UL << GLF_LRU), "L" }, \
+ {(1UL << GLF_OBJECT), "o" })
#ifndef NUMPTY
#define NUMPTY
@@ -94,7 +97,7 @@ TRACE_EVENT(gfs2_glock_state_change,
__entry->new_state = glock_trace_state(new_state);
__entry->tgt_state = glock_trace_state(gl->gl_target);
__entry->dmt_state = glock_trace_state(gl->gl_demote_state);
- __entry->flags = gl->gl_flags;
+ __entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
),
TP_printk("%u,%u glock %d:%lld state %s to %s tgt:%s dmt:%s flags:%s",
@@ -127,7 +130,7 @@ TRACE_EVENT(gfs2_glock_put,
__entry->gltype = gl->gl_name.ln_type;
__entry->glnum = gl->gl_name.ln_number;
__entry->cur_state = glock_trace_state(gl->gl_state);
- __entry->flags = gl->gl_flags;
+ __entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
),
TP_printk("%u,%u glock %d:%lld state %s => %s flags:%s",
@@ -161,7 +164,7 @@ TRACE_EVENT(gfs2_demote_rq,
__entry->glnum = gl->gl_name.ln_number;
__entry->cur_state = glock_trace_state(gl->gl_state);
__entry->dmt_state = glock_trace_state(gl->gl_demote_state);
- __entry->flags = gl->gl_flags;
+ __entry->flags = gl->gl_flags | (gl->gl_object ? (1UL<<GLF_OBJECT) : 0);
),
TP_printk("%u,%u glock %d:%lld demote %s to %s flags:%s",
@@ -318,6 +321,33 @@ TRACE_EVENT(gfs2_log_blocks,
MINOR(__entry->dev), __entry->blocks)
);
+/* Writing back the AIL */
+TRACE_EVENT(gfs2_ail_flush,
+
+ TP_PROTO(const struct gfs2_sbd *sdp, const struct writeback_control *wbc, int start),
+
+ TP_ARGS(sdp, wbc, start),
+
+ TP_STRUCT__entry(
+ __field( dev_t, dev )
+ __field( int, start )
+ __field( int, sync_mode )
+ __field( long, nr_to_write )
+ ),
+
+ TP_fast_assign(
+ __entry->dev = sdp->sd_vfs->s_dev;
+ __entry->start = start;
+ __entry->sync_mode = wbc->sync_mode;
+ __entry->nr_to_write = wbc->nr_to_write;
+ ),
+
+ TP_printk("%u,%u ail flush %s %s %ld", MAJOR(__entry->dev),
+ MINOR(__entry->dev), __entry->start ? "start" : "end",
+ __entry->sync_mode == WB_SYNC_ALL ? "all" : "none",
+ __entry->nr_to_write)
+);
+
/* Section 3 - bmap
*
* Objectives:
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2024-11-11 12:37:40 +0000