Merge tag 'gfs2-merge-window' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2

Pull GFS2 updates from Bob Peterson:
 "Here is a list of patches we've accumulated for GFS2 for the current
  upstream merge window.  Last window's set was short, but I warned that
  this one would be bigger, and so it is.  We've got 19 patches:

   - A patch from Abhi Das to propagate the GFS2_DIF_SYSTEM bit so that
     newly added journals don't get flagged, deleted, and recreated by
     fsck.gfs2.

   - Two patches from Andreas Gruenbacher to improve GFS2 performance
     where extended attributes are involved.

   - A patch from Andy Price to fix a suspicious rcu dereference error.

   - Two patches from Ben Marzinski that rework how GFS2's NFS cookies
     are managed.  This fixes readdir problems with nfs-over-gfs2.

   - A patch from Ben Marzinski that fixes a race in unmounting GFS2.

   - A set of four patches from me to move the resource group
     reservations inside the gfs2 inode to improve performance and fix a
     bug whereby get_write_access improperly prevented some operations
     like chown.

   - A patch from me to spinlock-protect the setting of system statfs
     file data.  This was causing small discrepancies between df and du.

   - A patch from me to reintroduce a timeout while clearing glocks
     which was accidentally dropped some time ago.

   - A patch from me to wait for iopen glock dequeues in order to
     improve deleting of files that were unlinked from a different
     cluster node.

   - A patch from me to ensure metadata address spaces get truncated
     when an inode is evicted.

   - A patch from me to fix a bug in which a memory leak could occur in
     some error cases when inodes were trying to be created.

   - A patch to consistently use iopen glocks to transition from the
     unlinked state to the deleted state.

   - A patch to fix a glock reference count error when inode creation
     fails.

   - A patch from Junxiao Bi to fix an flock panic.

   - A patch from Markus Elfring that removes an unnecessary if"

* tag 'gfs2-merge-window' of git://git.kernel.org/pub/scm/linux/kernel/git/gfs2/linux-gfs2:
  gfs2: fix flock panic issue
  GFS2: Don't do glock put on when inode creation fails
  GFS2: Always use iopen glock for gl_deletes
  GFS2: Release iopen glock in gfs2_create_inode error cases
  GFS2: Truncate address space mapping when deleting an inode
  GFS2: Wait for iopen glock dequeues
  gfs2: clear journal live bit in	gfs2_log_flush
  gfs2: change gfs2 readdir cookie
  gfs2: keep offset when splitting dir leaf blocks
  GFS2: Reintroduce a timeout in function gfs2_gl_hash_clear
  GFS2: Update master statfs buffer with sd_statfs_spin locked
  GFS2: Reduce size of incore inode
  GFS2: Make rgrp reservations part of the gfs2_inode structure
  GFS2: Extract quota data from reservations structure (revert 5407e242)
  gfs2: Extended attribute readahead optimization
  gfs2: Extended attribute readahead
  GFS2: Use rht_for_each_entry_rcu in glock_hash_walk
  GFS2: Delete an unnecessary check before the function call "iput"
  gfs2: Automatically set GFS2_DIF_SYSTEM flag on system files

fs/gfs2/aops.c

@@ -914,7 +914,7 @@ static int gfs2_write_end(struct file *file, struct address_space *mapping,
 failed:
 	gfs2_trans_end(sdp);
 	gfs2_inplace_release(ip);
-	if (ip->i_res->rs_qa_qd_num)
+	if (ip->i_qadata && ip->i_qadata->qa_qd_num)
 		gfs2_quota_unlock(ip);
 	if (inode == sdp->sd_rindex) {
 		gfs2_glock_dq(&m_ip->i_gh);

fs/gfs2/bmap.c

@@ -787,8 +787,8 @@ static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
 	if (error)
 		goto out_rlist;
 
-	if (gfs2_rs_active(ip->i_res)) /* needs to be done with the rgrp glock held */
-		gfs2_rs_deltree(ip->i_res);
+	if (gfs2_rs_active(&ip->i_res)) /* needs to be done with the rgrp glock held */
+		gfs2_rs_deltree(&ip->i_res);
 
 	error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE +
 				 RES_INDIRECT + RES_STATFS + RES_QUOTA,
@@ -1291,13 +1291,9 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize)
 	if (ret)
 		return ret;
 
-	ret = get_write_access(inode);
-	if (ret)
-		return ret;
-
 	inode_dio_wait(inode);
 
-	ret = gfs2_rs_alloc(ip);
+	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
 		goto out;
 
@@ -1307,10 +1303,9 @@ int gfs2_setattr_size(struct inode *inode, u64 newsize)
 		goto out;
 	}
 
-	gfs2_rs_deltree(ip->i_res);
 	ret = do_shrink(inode, oldsize, newsize);
 out:
-	put_write_access(inode);
+	gfs2_rsqa_delete(ip, NULL);
 	return ret;
 }
 

fs/gfs2/file.c

@@ -298,9 +298,9 @@ static int gfs2_set_flags(struct file *filp, u32 __user *ptr)
 		gfsflags &= ~GFS2_DIF_TOPDIR;
 		if (gfsflags & GFS2_DIF_INHERIT_JDATA)
 			gfsflags ^= (GFS2_DIF_JDATA | GFS2_DIF_INHERIT_JDATA);
-		return do_gfs2_set_flags(filp, gfsflags, ~0);
+		return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_SYSTEM);
 	}
-	return do_gfs2_set_flags(filp, gfsflags, ~GFS2_DIF_JDATA);
+	return do_gfs2_set_flags(filp, gfsflags, ~(GFS2_DIF_SYSTEM | GFS2_DIF_JDATA));
 }
 
 static long gfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
@@ -336,8 +336,8 @@ static void gfs2_size_hint(struct file *filep, loff_t offset, size_t size)
 	size_t blks = (size + sdp->sd_sb.sb_bsize - 1) >> sdp->sd_sb.sb_bsize_shift;
 	int hint = min_t(size_t, INT_MAX, blks);
 
-	if (hint > atomic_read(&ip->i_res->rs_sizehint))
-		atomic_set(&ip->i_res->rs_sizehint, hint);
+	if (hint > atomic_read(&ip->i_res.rs_sizehint))
+		atomic_set(&ip->i_res.rs_sizehint, hint);
 }
 
 /**
@@ -397,14 +397,10 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	/* Update file times before taking page lock */
 	file_update_time(vma->vm_file);
 
-	ret = get_write_access(inode);
+	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
 		goto out;
 
-	ret = gfs2_rs_alloc(ip);
-	if (ret)
-		goto out_write_access;
-
 	gfs2_size_hint(vma->vm_file, pos, PAGE_CACHE_SIZE);
 
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
@@ -486,8 +482,6 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 		set_page_dirty(page);
 		wait_for_stable_page(page);
 	}
-out_write_access:
-	put_write_access(inode);
 out:
 	sb_end_pagefault(inode->i_sb);
 	return block_page_mkwrite_return(ret);
@@ -623,7 +617,7 @@ static int gfs2_release(struct inode *inode, struct file *file)
 	if (!(file->f_mode & FMODE_WRITE))
 		return 0;
 
-	gfs2_rs_delete(ip, &inode->i_writecount);
+	gfs2_rsqa_delete(ip, &inode->i_writecount);
 	return 0;
 }
 
@@ -703,7 +697,7 @@ static ssize_t gfs2_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct gfs2_inode *ip = GFS2_I(file_inode(file));
 	int ret;
 
-	ret = gfs2_rs_alloc(ip);
+	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
 		return ret;
 
@@ -938,13 +932,14 @@ static long gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t le
 	if (ret)
 		goto out_unlock;
 
-	ret = gfs2_rs_alloc(ip);
+	ret = gfs2_rsqa_alloc(ip);
 	if (ret)
 		goto out_putw;
 
 	ret = __gfs2_fallocate(file, mode, offset, len);
 	if (ret)
-		gfs2_rs_deltree(ip->i_res);
+		gfs2_rs_deltree(&ip->i_res);
+
 out_putw:
 	put_write_access(inode);
 out_unlock:
@@ -962,7 +957,7 @@ static ssize_t gfs2_file_splice_write(struct pipe_inode_info *pipe,
 	int error;
 	struct gfs2_inode *ip = GFS2_I(out->f_mapping->host);
 
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		return (ssize_t)error;
 
@@ -1018,7 +1013,7 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 	struct gfs2_inode *ip = GFS2_I(file_inode(file));
 	struct gfs2_glock *gl;
 	unsigned int state;
-	int flags;
+	u16 flags;
 	int error = 0;
 	int sleeptime;
 
@@ -1032,7 +1027,10 @@ static int do_flock(struct file *file, int cmd, struct file_lock *fl)
 		if (fl_gh->gh_state == state)
 			goto out;
 		locks_lock_file_wait(file,
-				     &(struct file_lock){.fl_type = F_UNLCK});
+				     &(struct file_lock) {
+					     .fl_type = F_UNLCK,
+					     .fl_flags = FL_FLOCK
+				     });
 		gfs2_glock_dq(fl_gh);
 		gfs2_holder_reinit(state, flags, fl_gh);
 	} else {

fs/gfs2/glock.c

@@ -446,7 +446,7 @@ __acquires(&gl->gl_lockref.lock)
 {
 	const struct gfs2_glock_operations *glops = gl->gl_ops;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	unsigned int lck_flags = gh ? gh->gh_flags : 0;
+	unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0);
 	int ret;
 
 	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
@@ -750,7 +750,7 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
  *
  */
 
-void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
+void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, u16 flags,
 		      struct gfs2_holder *gh)
 {
 	INIT_LIST_HEAD(&gh->gh_list);
@@ -774,7 +774,7 @@ void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state, unsigned flags,
  *
  */
 
-void gfs2_holder_reinit(unsigned int state, unsigned flags, struct gfs2_holder *gh)
+void gfs2_holder_reinit(unsigned int state, u16 flags, struct gfs2_holder *gh)
 {
 	gh->gh_state = state;
 	gh->gh_flags = flags;
@@ -1080,7 +1080,7 @@ void gfs2_glock_dq_uninit(struct gfs2_holder *gh)
 
 int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
 		      const struct gfs2_glock_operations *glops,
-		      unsigned int state, int flags, struct gfs2_holder *gh)
+		      unsigned int state, u16 flags, struct gfs2_holder *gh)
 {
 	struct gfs2_glock *gl;
 	int error;
@@ -1417,14 +1417,14 @@ static struct shrinker glock_shrinker = {
 static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
 {
 	struct gfs2_glock *gl;
-	struct rhash_head *pos, *next;
+	struct rhash_head *pos;
 	const struct bucket_table *tbl;
 	int i;
 
 	rcu_read_lock();
 	tbl = rht_dereference_rcu(gl_hash_table.tbl, &gl_hash_table);
 	for (i = 0; i < tbl->size; i++) {
-		rht_for_each_entry_safe(gl, pos, next, tbl, i, gl_node) {
+		rht_for_each_entry_rcu(gl, pos, tbl, i, gl_node) {
 			if ((gl->gl_name.ln_sbd == sdp) &&
 			    lockref_get_not_dead(&gl->gl_lockref))
 				examiner(gl);
@@ -1506,7 +1506,9 @@ void gfs2_gl_hash_clear(struct gfs2_sbd *sdp)
 	flush_workqueue(glock_workqueue);
 	glock_hash_walk(clear_glock, sdp);
 	flush_workqueue(glock_workqueue);
-	wait_event(sdp->sd_glock_wait, atomic_read(&sdp->sd_glock_disposal) == 0);
+	wait_event_timeout(sdp->sd_glock_wait,
+			   atomic_read(&sdp->sd_glock_disposal) == 0,
+			   HZ * 600);
 	glock_hash_walk(dump_glock_func, sdp);
 }
 
@@ -1539,7 +1541,7 @@ static const char *state2str(unsigned state)
 	return "??";
 }
 
-static const char *hflags2str(char *buf, unsigned flags, unsigned long iflags)
+static const char *hflags2str(char *buf, u16 flags, unsigned long iflags)
 {
 	char *p = buf;
 	if (flags & LM_FLAG_TRY)

fs/gfs2/glock.h

@@ -79,15 +79,15 @@ enum {
  * requested had acquired and released the lock.
  */
 
-#define LM_FLAG_TRY		0x00000001
-#define LM_FLAG_TRY_1CB		0x00000002
-#define LM_FLAG_NOEXP		0x00000004
-#define LM_FLAG_ANY		0x00000008
-#define LM_FLAG_PRIORITY	0x00000010
-#define GL_ASYNC		0x00000040
-#define GL_EXACT		0x00000080
-#define GL_SKIP			0x00000100
-#define GL_NOCACHE		0x00000400
+#define LM_FLAG_TRY		0x0001
+#define LM_FLAG_TRY_1CB		0x0002
+#define LM_FLAG_NOEXP		0x0004
+#define LM_FLAG_ANY		0x0008
+#define LM_FLAG_PRIORITY	0x0010
+#define GL_ASYNC		0x0040
+#define GL_EXACT		0x0080
+#define GL_SKIP			0x0100
+#define GL_NOCACHE		0x0400
   
 /*
  * lm_async_cb return flags
@@ -183,8 +183,8 @@ extern int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 			  int create, struct gfs2_glock **glp);
 extern void gfs2_glock_put(struct gfs2_glock *gl);
 extern void gfs2_holder_init(struct gfs2_glock *gl, unsigned int state,
-			     unsigned flags, struct gfs2_holder *gh);
-extern void gfs2_holder_reinit(unsigned int state, unsigned flags,
+			     u16 flags, struct gfs2_holder *gh);
+extern void gfs2_holder_reinit(unsigned int state, u16 flags,
 			       struct gfs2_holder *gh);
 extern void gfs2_holder_uninit(struct gfs2_holder *gh);
 extern int gfs2_glock_nq(struct gfs2_holder *gh);
@@ -195,7 +195,7 @@ extern void gfs2_glock_dq_wait(struct gfs2_holder *gh);
 extern void gfs2_glock_dq_uninit(struct gfs2_holder *gh);
 extern int gfs2_glock_nq_num(struct gfs2_sbd *sdp, u64 number,
 			     const struct gfs2_glock_operations *glops,
-			     unsigned int state, int flags,
+			     unsigned int state, u16 flags,
 			     struct gfs2_holder *gh);
 extern int gfs2_glock_nq_m(unsigned int num_gh, struct gfs2_holder *ghs);
 extern void gfs2_glock_dq_m(unsigned int num_gh, struct gfs2_holder *ghs);
@@ -215,7 +215,7 @@ void gfs2_print_dbg(struct seq_file *seq, const char *fmt, ...);
  */
 
 static inline int gfs2_glock_nq_init(struct gfs2_glock *gl,
-				     unsigned int state, int flags,
+				     unsigned int state, u16 flags,
 				     struct gfs2_holder *gh)
 {
 	int error;

fs/gfs2/incore.h

@@ -259,8 +259,8 @@ struct gfs2_holder {
 
 	struct gfs2_glock *gh_gl;
 	struct pid *gh_owner_pid;
-	unsigned int gh_state;
-	unsigned gh_flags;
+	u16 gh_flags;
+	u16 gh_state;
 
 	int gh_error;
 	unsigned long gh_iflags; /* HIF_... */
@@ -270,6 +270,13 @@ struct gfs2_holder {
 /* Number of quota types we support */
 #define GFS2_MAXQUOTAS 2
 
+struct gfs2_qadata { /* quota allocation data */
+	/* Quota stuff */
+	struct gfs2_quota_data *qa_qd[2 * GFS2_MAXQUOTAS];
+	struct gfs2_holder qa_qd_ghs[2 * GFS2_MAXQUOTAS];
+	unsigned int qa_qd_num;
+};
+
 /* Resource group multi-block reservation, in order of appearance:
 
    Step 1. Function prepares to write, allocates a mb, sets the size hint.
@@ -288,11 +295,6 @@ struct gfs2_blkreserv {
 	struct gfs2_rbm rs_rbm;       /* Start of reservation */
 	u32 rs_free;                  /* how many blocks are still free */
 	u64 rs_inum;                  /* Inode number for reservation */
-
-	/* ancillary quota stuff */
-	struct gfs2_quota_data *rs_qa_qd[2 * GFS2_MAXQUOTAS];
-	struct gfs2_holder rs_qa_qd_ghs[2 * GFS2_MAXQUOTAS];
-	unsigned int rs_qa_qd_num;
 };
 
 /*
@@ -391,7 +393,8 @@ struct gfs2_inode {
 	struct gfs2_glock *i_gl; /* Move into i_gh? */
 	struct gfs2_holder i_iopen_gh;
 	struct gfs2_holder i_gh; /* for prepare/commit_write only */
-	struct gfs2_blkreserv *i_res; /* rgrp multi-block reservation */
+	struct gfs2_qadata *i_qadata; /* quota allocation data */
+	struct gfs2_blkreserv i_res; /* rgrp multi-block reservation */
 	struct gfs2_rgrpd *i_rgd;
 	u64 i_goal;	/* goal block for allocations */
 	struct rw_semaphore i_rw_mutex;
@@ -402,6 +405,7 @@ struct gfs2_inode {
 	u32 i_diskflags;
 	u8 i_height;
 	u8 i_depth;
+	u16 i_rahead;
 };
 
 /*
@@ -558,6 +562,8 @@ struct gfs2_args {
 	unsigned int ar_errors:2;               /* errors=withdraw | panic */
 	unsigned int ar_nobarrier:1;            /* do not send barriers */
 	unsigned int ar_rgrplvb:1;		/* use lvbs for rgrp info */
+	unsigned int ar_loccookie:1;		/* use location based readdir
+						   cookies */
 	int ar_commit;				/* Commit interval */
 	int ar_statfs_quantum;			/* The fast statfs interval */
 	int ar_quota_quantum;			/* The quota interval */
@@ -685,6 +691,7 @@ struct gfs2_sbd {
 	u64 sd_heightsize[GFS2_MAX_META_HEIGHT + 1];
 	u32 sd_max_jheight; /* Max height of journaled file's meta tree */
 	u64 sd_jheightsize[GFS2_MAX_META_HEIGHT + 1];
+	u32 sd_max_dents_per_leaf; /* Max number of dirents in a leaf block */
 
 	struct gfs2_args sd_args;	/* Mount arguments */
 	struct gfs2_tune sd_tune;	/* Filesystem tuning structure */

fs/gfs2/inode.c

@@ -191,13 +191,13 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 fail_refresh:
 	ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
 	ip->i_iopen_gh.gh_gl->gl_object = NULL;
-	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+	gfs2_glock_dq_wait(&ip->i_iopen_gh);
+	gfs2_holder_uninit(&ip->i_iopen_gh);
 fail_iopen:
 	if (io_gl)
 		gfs2_glock_put(io_gl);
 fail_put:
 	ip->i_gl->gl_object = NULL;
-	gfs2_glock_put(ip->i_gl);
 fail:
 	iget_failed(inode);
 	return ERR_PTR(error);
@@ -593,7 +593,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	struct gfs2_inode *dip = GFS2_I(dir), *ip;
 	struct gfs2_sbd *sdp = GFS2_SB(&dip->i_inode);
 	struct gfs2_glock *io_gl;
-	int error, free_vfs_inode = 0;
+	int error, free_vfs_inode = 1;
 	u32 aflags = 0;
 	unsigned blocks = 1;
 	struct gfs2_diradd da = { .bh = NULL, .save_loc = 1, };
@@ -601,7 +601,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	if (!name->len || name->len > GFS2_FNAMESIZE)
 		return -ENAMETOOLONG;
 
-	error = gfs2_rs_alloc(dip);
+	error = gfs2_rsqa_alloc(dip);
 	if (error)
 		return error;
 
@@ -650,10 +650,10 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 
 	error = posix_acl_create(dir, &mode, &default_acl, &acl);
 	if (error)
-		goto fail_free_vfs_inode;
+		goto fail_gunlock;
 
 	ip = GFS2_I(inode);
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		goto fail_free_acls;
 
@@ -685,6 +685,11 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 		ip->i_entries = 2;
 		break;
 	}
+
+	/* Force SYSTEM flag on all files and subdirs of a SYSTEM directory */
+	if (dip->i_diskflags & GFS2_DIF_SYSTEM)
+		ip->i_diskflags |= GFS2_DIF_SYSTEM;
+
 	gfs2_set_inode_flags(inode);
 
 	if ((GFS2_I(d_inode(sdp->sd_root_dir)) == dip) ||
@@ -733,6 +738,9 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	gfs2_set_iop(inode);
 	insert_inode_hash(inode);
 
+	free_vfs_inode = 0; /* After this point, the inode is no longer
+			       considered free. Any failures need to undo
+			       the gfs2 structures. */
 	if (default_acl) {
 		error = gfs2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
 		posix_acl_release(default_acl);
@@ -766,24 +774,19 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	return error;
 
 fail_gunlock3:
-	gfs2_glock_dq_uninit(ghs + 1);
-	if (ip->i_gl)
-		gfs2_glock_put(ip->i_gl);
-	goto fail_gunlock;
-
+	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+	gfs2_glock_put(io_gl);
 fail_gunlock2:
 	gfs2_glock_dq_uninit(ghs + 1);
 fail_free_inode:
 	if (ip->i_gl)
 		gfs2_glock_put(ip->i_gl);
-	gfs2_rs_delete(ip, NULL);
+	gfs2_rsqa_delete(ip, NULL);
 fail_free_acls:
 	if (default_acl)
 		posix_acl_release(default_acl);
 	if (acl)
 		posix_acl_release(acl);
-fail_free_vfs_inode:
-	free_vfs_inode = 1;
 fail_gunlock:
 	gfs2_dir_no_add(&da);
 	gfs2_glock_dq_uninit(ghs);
@@ -898,7 +901,7 @@ static int gfs2_link(struct dentry *old_dentry, struct inode *dir,
 	if (S_ISDIR(inode->i_mode))
 		return -EPERM;
 
-	error = gfs2_rs_alloc(dip);
+	error = gfs2_rsqa_alloc(dip);
 	if (error)
 		return error;
 
@@ -1371,7 +1374,7 @@ static int gfs2_rename(struct inode *odir, struct dentry *odentry,
 	if (error)
 		return error;
 
-	error = gfs2_rs_alloc(ndip);
+	error = gfs2_rsqa_alloc(ndip);
 	if (error)
 		return error;
 
@@ -1860,11 +1863,7 @@ static int setattr_chown(struct inode *inode, struct iattr *attr)
 	if (!(attr->ia_valid & ATTR_GID) || gid_eq(ogid, ngid))
 		ogid = ngid = NO_GID_QUOTA_CHANGE;
 
-	error = get_write_access(inode);
-	if (error)
-		return error;
-
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		goto out;
 
@@ -1904,7 +1903,6 @@ static int setattr_chown(struct inode *inode, struct iattr *attr)
 out_gunlock_q:
 	gfs2_quota_unlock(ip);
 out:
-	put_write_access(inode);
 	return error;
 }
 
@@ -1926,7 +1924,7 @@ static int gfs2_setattr(struct dentry *dentry, struct iattr *attr)
 	struct gfs2_holder i_gh;
 	int error;
 
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		return error;
 
@@ -2008,7 +2006,7 @@ static int gfs2_setxattr(struct dentry *dentry, const char *name,
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
 	ret = gfs2_glock_nq(&gh);
 	if (ret == 0) {
-		ret = gfs2_rs_alloc(ip);
+		ret = gfs2_rsqa_alloc(ip);
 		if (ret == 0)
 			ret = generic_setxattr(dentry, name, data, size, flags);
 		gfs2_glock_dq(&gh);
@@ -2049,7 +2047,7 @@ static int gfs2_removexattr(struct dentry *dentry, const char *name)
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
 	ret = gfs2_glock_nq(&gh);
 	if (ret == 0) {
-		ret = gfs2_rs_alloc(ip);
+		ret = gfs2_rsqa_alloc(ip);
 		if (ret == 0)
 			ret = generic_removexattr(dentry, name);
 		gfs2_glock_dq(&gh);

fs/gfs2/log.c

@@ -716,6 +716,9 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
 	}
 	trace_gfs2_log_flush(sdp, 1);
 
+	if (type == SHUTDOWN_FLUSH)
+		clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
+
 	sdp->sd_log_flush_head = sdp->sd_log_head;
 	sdp->sd_log_flush_wrapped = 0;
 	tr = sdp->sd_log_tr;

fs/gfs2/main.c

@@ -41,7 +41,9 @@ static void gfs2_init_inode_once(void *foo)
 	inode_init_once(&ip->i_inode);
 	init_rwsem(&ip->i_rw_mutex);
 	INIT_LIST_HEAD(&ip->i_trunc_list);
-	ip->i_res = NULL;
+	ip->i_qadata = NULL;
+	memset(&ip->i_res, 0, sizeof(ip->i_res));
+	RB_CLEAR_NODE(&ip->i_res.rs_node);
 	ip->i_hash_cache = NULL;
 }
 
@@ -135,10 +137,10 @@ static int __init init_gfs2_fs(void)
 	if (!gfs2_quotad_cachep)
 		goto fail;
 
-	gfs2_rsrv_cachep = kmem_cache_create("gfs2_mblk",
-					     sizeof(struct gfs2_blkreserv),
+	gfs2_qadata_cachep = kmem_cache_create("gfs2_qadata",
+					       sizeof(struct gfs2_qadata),
 					       0, 0, NULL);
-	if (!gfs2_rsrv_cachep)
+	if (!gfs2_qadata_cachep)
 		goto fail;
 
 	register_shrinker(&gfs2_qd_shrinker);
@@ -193,8 +195,8 @@ static int __init init_gfs2_fs(void)
 	unregister_shrinker(&gfs2_qd_shrinker);
 	gfs2_glock_exit();
 
-	if (gfs2_rsrv_cachep)
-		kmem_cache_destroy(gfs2_rsrv_cachep);
+	if (gfs2_qadata_cachep)
+		kmem_cache_destroy(gfs2_qadata_cachep);
 
 	if (gfs2_quotad_cachep)
 		kmem_cache_destroy(gfs2_quotad_cachep);
@@ -238,7 +240,7 @@ static void __exit exit_gfs2_fs(void)
 	rcu_barrier();
 
 	mempool_destroy(gfs2_page_pool);
-	kmem_cache_destroy(gfs2_rsrv_cachep);
+	kmem_cache_destroy(gfs2_qadata_cachep);
 	kmem_cache_destroy(gfs2_quotad_cachep);
 	kmem_cache_destroy(gfs2_rgrpd_cachep);
 	kmem_cache_destroy(gfs2_bufdata_cachep);

fs/gfs2/meta_io.c

@@ -187,6 +187,52 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
 	return bh;
 }
 
+static void gfs2_meta_read_endio(struct bio *bio)
+{
+	struct bio_vec *bvec;
+	int i;
+
+	bio_for_each_segment_all(bvec, bio, i) {
+		struct page *page = bvec->bv_page;
+		struct buffer_head *bh = page_buffers(page);
+		unsigned int len = bvec->bv_len;
+
+		while (bh_offset(bh) < bvec->bv_offset)
+			bh = bh->b_this_page;
+		do {
+			struct buffer_head *next = bh->b_this_page;
+			len -= bh->b_size;
+			bh->b_end_io(bh, !bio->bi_error);
+			bh = next;
+		} while (bh && len);
+	}
+	bio_put(bio);
+}
+
+/*
+ * Submit several consecutive buffer head I/O requests as a single bio I/O
+ * request.  (See submit_bh_wbc.)
+ */
+static void gfs2_submit_bhs(int rw, struct buffer_head *bhs[], int num)
+{
+	struct buffer_head *bh = bhs[0];
+	struct bio *bio;
+	int i;
+
+	if (!num)
+		return;
+
+	bio = bio_alloc(GFP_NOIO, num);
+	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
+	bio->bi_bdev = bh->b_bdev;
+	for (i = 0; i < num; i++) {
+		bh = bhs[i];
+		bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
+	}
+	bio->bi_end_io = gfs2_meta_read_endio;
+	submit_bio(rw, bio);
+}
+
 /**
  * gfs2_meta_read - Read a block from disk
  * @gl: The glock covering the block
@@ -198,10 +244,11 @@ struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno)
  */
 
 int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
-		   struct buffer_head **bhp)
+		   int rahead, struct buffer_head **bhp)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	struct buffer_head *bh;
+	struct buffer_head *bh, *bhs[2];
+	int num = 0;
 
 	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags))) {
 		*bhp = NULL;
@@ -213,14 +260,31 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 	lock_buffer(bh);
 	if (buffer_uptodate(bh)) {
 		unlock_buffer(bh);
-		return 0;
-	}
+		flags &= ~DIO_WAIT;
+	} else {
 		bh->b_end_io = end_buffer_read_sync;
 		get_bh(bh);
-	submit_bh(READ_SYNC | REQ_META | REQ_PRIO, bh);
+		bhs[num++] = bh;
+	}
+
+	if (rahead) {
+		bh = gfs2_getbuf(gl, blkno + 1, CREATE);
+
+		lock_buffer(bh);
+		if (buffer_uptodate(bh)) {
+			unlock_buffer(bh);
+			brelse(bh);
+		} else {
+			bh->b_end_io = end_buffer_read_sync;
+			bhs[num++] = bh;
+		}
+	}
+
+	gfs2_submit_bhs(READ_SYNC | REQ_META | REQ_PRIO, bhs, num);
 	if (!(flags & DIO_WAIT))
 		return 0;
 
+	bh = *bhp;
 	wait_on_buffer(bh);
 	if (unlikely(!buffer_uptodate(bh))) {
 		struct gfs2_trans *tr = current->journal_info;
@@ -341,8 +405,12 @@ int gfs2_meta_indirect_buffer(struct gfs2_inode *ip, int height, u64 num,
 	struct buffer_head *bh;
 	int ret = 0;
 	u32 mtype = height ? GFS2_METATYPE_IN : GFS2_METATYPE_DI;
+	int rahead = 0;
+
+	if (num == ip->i_no_addr)
+		rahead = ip->i_rahead;
 
-	ret = gfs2_meta_read(gl, num, DIO_WAIT, &bh);
+	ret = gfs2_meta_read(gl, num, DIO_WAIT, rahead, &bh);
 	if (ret == 0 && gfs2_metatype_check(sdp, bh, mtype)) {
 		brelse(bh);
 		ret = -EIO;

fs/gfs2/meta_io.h

@@ -53,7 +53,7 @@ static inline struct gfs2_sbd *gfs2_mapping2sbd(struct address_space *mapping)
 
 extern struct buffer_head *gfs2_meta_new(struct gfs2_glock *gl, u64 blkno);
 extern int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
-			  struct buffer_head **bhp);
+			  int rahead, struct buffer_head **bhp);
 extern int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh);
 extern struct buffer_head *gfs2_getbuf(struct gfs2_glock *gl, u64 blkno,
 				       int create);

fs/gfs2/ops_fstype.c

@@ -352,6 +352,9 @@ static int gfs2_read_sb(struct gfs2_sbd *sdp, int silent)
 	sdp->sd_jheightsize[x] = ~0;
 	gfs2_assert(sdp, sdp->sd_max_jheight <= GFS2_MAX_META_HEIGHT);
 
+	sdp->sd_max_dents_per_leaf = (sdp->sd_sb.sb_bsize -
+				      sizeof(struct gfs2_leaf)) /
+				     GFS2_MIN_DIRENT_SIZE;
 	return 0;
 }
 
@@ -910,7 +913,6 @@ static int init_per_node(struct gfs2_sbd *sdp, int undo)
 fail_ut_i:
 	iput(sdp->sd_sc_inode);
 fail:
-	if (pn)
 	iput(pn);
 	return error;
 }

fs/gfs2/quota.c

@@ -388,7 +388,7 @@ static int bh_get(struct gfs2_quota_data *qd)
 	error = gfs2_block_map(&ip->i_inode, block, &bh_map, 0);
 	if (error)
 		goto fail;
-	error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, &bh);
+	error = gfs2_meta_read(ip->i_gl, bh_map.b_blocknr, DIO_WAIT, 0, &bh);
 	if (error)
 		goto fail;
 	error = -EIO;
@@ -527,37 +527,70 @@ static void qdsb_put(struct gfs2_quota_data *qd)
 	qd_put(qd);
 }
 
+/**
+ * gfs2_qa_alloc - make sure we have a quota allocations data structure,
+ *                 if necessary
+ * @ip: the inode for this reservation
+ */
+int gfs2_qa_alloc(struct gfs2_inode *ip)
+{
+	int error = 0;
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+
+	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+		return 0;
+
+	down_write(&ip->i_rw_mutex);
+	if (ip->i_qadata == NULL) {
+		ip->i_qadata = kmem_cache_zalloc(gfs2_qadata_cachep, GFP_NOFS);
+		if (!ip->i_qadata)
+			error = -ENOMEM;
+	}
+	up_write(&ip->i_rw_mutex);
+	return error;
+}
+
+void gfs2_qa_delete(struct gfs2_inode *ip, atomic_t *wcount)
+{
+	down_write(&ip->i_rw_mutex);
+	if (ip->i_qadata && ((wcount == NULL) || (atomic_read(wcount) <= 1))) {
+		kmem_cache_free(gfs2_qadata_cachep, ip->i_qadata);
+		ip->i_qadata = NULL;
+	}
+	up_write(&ip->i_rw_mutex);
+}
+
 int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data **qd;
 	int error;
 
-	if (ip->i_res == NULL) {
-		error = gfs2_rs_alloc(ip);
+	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
+		return 0;
+
+	if (ip->i_qadata == NULL) {
+		error = gfs2_rsqa_alloc(ip);
 		if (error)
 			return error;
 	}
 
-	qd = ip->i_res->rs_qa_qd;
+	qd = ip->i_qadata->qa_qd;
 
-	if (gfs2_assert_warn(sdp, !ip->i_res->rs_qa_qd_num) ||
+	if (gfs2_assert_warn(sdp, !ip->i_qadata->qa_qd_num) ||
 	    gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags)))
 		return -EIO;
 
-	if (sdp->sd_args.ar_quota == GFS2_QUOTA_OFF)
-		return 0;
-
 	error = qdsb_get(sdp, make_kqid_uid(ip->i_inode.i_uid), qd);
 	if (error)
 		goto out;
-	ip->i_res->rs_qa_qd_num++;
+	ip->i_qadata->qa_qd_num++;
 	qd++;
 
 	error = qdsb_get(sdp, make_kqid_gid(ip->i_inode.i_gid), qd);
 	if (error)
 		goto out;
-	ip->i_res->rs_qa_qd_num++;
+	ip->i_qadata->qa_qd_num++;
 	qd++;
 
 	if (!uid_eq(uid, NO_UID_QUOTA_CHANGE) &&
@@ -565,7 +598,7 @@ int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 		error = qdsb_get(sdp, make_kqid_uid(uid), qd);
 		if (error)
 			goto out;
-		ip->i_res->rs_qa_qd_num++;
+		ip->i_qadata->qa_qd_num++;
 		qd++;
 	}
 
@@ -574,7 +607,7 @@ int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 		error = qdsb_get(sdp, make_kqid_gid(gid), qd);
 		if (error)
 			goto out;
-		ip->i_res->rs_qa_qd_num++;
+		ip->i_qadata->qa_qd_num++;
 		qd++;
 	}
 
@@ -587,17 +620,17 @@ int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 void gfs2_quota_unhold(struct gfs2_inode *ip)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	unsigned int x;
+	u32 x;
 
-	if (ip->i_res == NULL)
+	if (ip->i_qadata == NULL)
 		return;
 	gfs2_assert_warn(sdp, !test_bit(GIF_QD_LOCKED, &ip->i_flags));
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
-		qdsb_put(ip->i_res->rs_qa_qd[x]);
-		ip->i_res->rs_qa_qd[x] = NULL;
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
+		qdsb_put(ip->i_qadata->qa_qd[x]);
+		ip->i_qadata->qa_qd[x] = NULL;
 	}
-	ip->i_res->rs_qa_qd_num = 0;
+	ip->i_qadata->qa_qd_num = 0;
 }
 
 static int sort_qd(const void *a, const void *b)
@@ -843,7 +876,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
 	unsigned int nalloc = 0, blocks;
 	int error;
 
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		return error;
 
@@ -1003,23 +1036,23 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data *qd;
-	unsigned int x;
+	u32 x;
 	int error = 0;
 
-	error = gfs2_quota_hold(ip, uid, gid);
-	if (error)
-		return error;
-
 	if (capable(CAP_SYS_RESOURCE) ||
 	    sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
 		return 0;
 
-	sort(ip->i_res->rs_qa_qd, ip->i_res->rs_qa_qd_num,
+	error = gfs2_quota_hold(ip, uid, gid);
+	if (error)
+		return error;
+
+	sort(ip->i_qadata->qa_qd, ip->i_qadata->qa_qd_num,
 	     sizeof(struct gfs2_quota_data *), sort_qd, NULL);
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
-		qd = ip->i_res->rs_qa_qd[x];
-		error = do_glock(qd, NO_FORCE, &ip->i_res->rs_qa_qd_ghs[x]);
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
+		qd = ip->i_qadata->qa_qd[x];
+		error = do_glock(qd, NO_FORCE, &ip->i_qadata->qa_qd_ghs[x]);
 		if (error)
 			break;
 	}
@@ -1028,7 +1061,7 @@ int gfs2_quota_lock(struct gfs2_inode *ip, kuid_t uid, kgid_t gid)
 		set_bit(GIF_QD_LOCKED, &ip->i_flags);
 	else {
 		while (x--)
-			gfs2_glock_dq_uninit(&ip->i_res->rs_qa_qd_ghs[x]);
+			gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]);
 		gfs2_quota_unhold(ip);
 	}
 
@@ -1076,20 +1109,20 @@ void gfs2_quota_unlock(struct gfs2_inode *ip)
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data *qda[4];
 	unsigned int count = 0;
-	unsigned int x;
+	u32 x;
 	int found;
 
 	if (!test_and_clear_bit(GIF_QD_LOCKED, &ip->i_flags))
 		goto out;
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
 		struct gfs2_quota_data *qd;
 		int sync;
 
-		qd = ip->i_res->rs_qa_qd[x];
+		qd = ip->i_qadata->qa_qd[x];
 		sync = need_sync(qd);
 
-		gfs2_glock_dq_uninit(&ip->i_res->rs_qa_qd_ghs[x]);
+		gfs2_glock_dq_uninit(&ip->i_qadata->qa_qd_ghs[x]);
 		if (!sync)
 			continue;
 
@@ -1158,7 +1191,7 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid,
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_quota_data *qd;
 	s64 value, warn, limit;
-	unsigned int x;
+	u32 x;
 	int error = 0;
 
 	ap->allowed = UINT_MAX; /* Assume we are permitted a whole lot */
@@ -1168,8 +1201,8 @@ int gfs2_quota_check(struct gfs2_inode *ip, kuid_t uid, kgid_t gid,
         if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON)
                 return 0;
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
-		qd = ip->i_res->rs_qa_qd[x];
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
+		qd = ip->i_qadata->qa_qd[x];
 
 		if (!(qid_eq(qd->qd_id, make_kqid_uid(uid)) ||
 		      qid_eq(qd->qd_id, make_kqid_gid(gid))))
@@ -1216,15 +1249,17 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
 		       kuid_t uid, kgid_t gid)
 {
 	struct gfs2_quota_data *qd;
-	unsigned int x;
+	u32 x;
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 
-	if (gfs2_assert_warn(GFS2_SB(&ip->i_inode), change))
+	if (sdp->sd_args.ar_quota != GFS2_QUOTA_ON ||
+	    gfs2_assert_warn(sdp, change))
 		return;
 	if (ip->i_diskflags & GFS2_DIF_SYSTEM)
 		return;
 
-	for (x = 0; x < ip->i_res->rs_qa_qd_num; x++) {
-		qd = ip->i_res->rs_qa_qd[x];
+	for (x = 0; x < ip->i_qadata->qa_qd_num; x++) {
+		qd = ip->i_qadata->qa_qd[x];
 
 		if (qid_eq(qd->qd_id, make_kqid_uid(uid)) ||
 		    qid_eq(qd->qd_id, make_kqid_gid(gid))) {
@@ -1635,7 +1670,7 @@ static int gfs2_set_dqblk(struct super_block *sb, struct kqid qid,
 	if (error)
 		return error;
 
-	error = gfs2_rs_alloc(ip);
+	error = gfs2_rsqa_alloc(ip);
 	if (error)
 		goto out_put;
 

fs/gfs2/quota.h

@@ -18,6 +18,8 @@ struct gfs2_sbd;
 #define NO_UID_QUOTA_CHANGE INVALID_UID
 #define NO_GID_QUOTA_CHANGE INVALID_GID
 
+extern int gfs2_qa_alloc(struct gfs2_inode *ip);
+extern void gfs2_qa_delete(struct gfs2_inode *ip, atomic_t *wcount);
 extern int gfs2_quota_hold(struct gfs2_inode *ip, kuid_t uid, kgid_t gid);
 extern void gfs2_quota_unhold(struct gfs2_inode *ip);
 

fs/gfs2/rgrp.c

@@ -596,27 +596,13 @@ void gfs2_free_clones(struct gfs2_rgrpd *rgd)
 }
 
 /**
- * gfs2_rs_alloc - make sure we have a reservation assigned to the inode
+ * gfs2_rsqa_alloc - make sure we have a reservation assigned to the inode
+ *                 plus a quota allocations data structure, if necessary
  * @ip: the inode for this reservation
  */
-int gfs2_rs_alloc(struct gfs2_inode *ip)
+int gfs2_rsqa_alloc(struct gfs2_inode *ip)
 {
-	int error = 0;
-
-	down_write(&ip->i_rw_mutex);
-	if (ip->i_res)
-		goto out;
-
-	ip->i_res = kmem_cache_zalloc(gfs2_rsrv_cachep, GFP_NOFS);
-	if (!ip->i_res) {
-		error = -ENOMEM;
-		goto out;
-	}
-
-	RB_CLEAR_NODE(&ip->i_res->rs_node);
-out:
-	up_write(&ip->i_rw_mutex);
-	return error;
+	return gfs2_qa_alloc(ip);
 }
 
 static void dump_rs(struct seq_file *seq, const struct gfs2_blkreserv *rs)
@@ -678,21 +664,20 @@ void gfs2_rs_deltree(struct gfs2_blkreserv *rs)
 }
 
 /**
- * gfs2_rs_delete - delete a multi-block reservation
+ * gfs2_rsqa_delete - delete a multi-block reservation and quota allocation
  * @ip: The inode for this reservation
  * @wcount: The inode's write count, or NULL
  *
  */
-void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount)
+void gfs2_rsqa_delete(struct gfs2_inode *ip, atomic_t *wcount)
 {
 	down_write(&ip->i_rw_mutex);
-	if (ip->i_res && ((wcount == NULL) || (atomic_read(wcount) <= 1))) {
-		gfs2_rs_deltree(ip->i_res);
-		BUG_ON(ip->i_res->rs_free);
-		kmem_cache_free(gfs2_rsrv_cachep, ip->i_res);
-		ip->i_res = NULL;
+	if ((wcount == NULL) || (atomic_read(wcount) <= 1)) {
+		gfs2_rs_deltree(&ip->i_res);
+		BUG_ON(ip->i_res.rs_free);
 	}
 	up_write(&ip->i_rw_mutex);
+	gfs2_qa_delete(ip, wcount);
 }
 
 /**
@@ -1158,7 +1143,7 @@ static int gfs2_rgrp_bh_get(struct gfs2_rgrpd *rgd)
 
 	for (x = 0; x < length; x++) {
 		bi = rgd->rd_bits + x;
-		error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, &bi->bi_bh);
+		error = gfs2_meta_read(gl, rgd->rd_addr + x, 0, 0, &bi->bi_bh);
 		if (error)
 			goto fail;
 	}
@@ -1456,7 +1441,7 @@ static void rs_insert(struct gfs2_inode *ip)
 {
 	struct rb_node **newn, *parent = NULL;
 	int rc;
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 	struct gfs2_rgrpd *rgd = rs->rs_rbm.rgd;
 	u64 fsblock = gfs2_rbm_to_block(&rs->rs_rbm);
 
@@ -1503,7 +1488,7 @@ static void rg_mblk_search(struct gfs2_rgrpd *rgd, struct gfs2_inode *ip,
 {
 	struct gfs2_rbm rbm = { .rgd = rgd, };
 	u64 goal;
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 	u32 extlen;
 	u32 free_blocks = rgd->rd_free_clone - rgd->rd_reserved;
 	int ret;
@@ -1574,7 +1559,7 @@ static u64 gfs2_next_unreserved_block(struct gfs2_rgrpd *rgd, u64 block,
 	}
 
 	if (n) {
-		while ((rs_cmp(block, length, rs) == 0) && (ip->i_res != rs)) {
+		while ((rs_cmp(block, length, rs) == 0) && (&ip->i_res != rs)) {
 			block = gfs2_rbm_to_block(&rs->rs_rbm) + rs->rs_free;
 			n = n->rb_right;
 			if (n == NULL)
@@ -1804,7 +1789,7 @@ static void try_rgrp_unlink(struct gfs2_rgrpd *rgd, u64 *last_unlinked, u64 skip
 			continue;
 		*last_unlinked = block;
 
-		error = gfs2_glock_get(sdp, block, &gfs2_inode_glops, CREATE, &gl);
+		error = gfs2_glock_get(sdp, block, &gfs2_iopen_glops, CREATE, &gl);
 		if (error)
 			continue;
 
@@ -1984,7 +1969,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
 	struct gfs2_rgrpd *begin = NULL;
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 	int error = 0, rg_locked, flags = 0;
 	u64 last_unlinked = NO_BLOCK;
 	int loops = 0;
@@ -2113,7 +2098,7 @@ int gfs2_inplace_reserve(struct gfs2_inode *ip, struct gfs2_alloc_parms *ap)
 
 void gfs2_inplace_release(struct gfs2_inode *ip)
 {
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 
 	if (rs->rs_rgd_gh.gh_gl)
 		gfs2_glock_dq_uninit(&rs->rs_rgd_gh);
@@ -2267,7 +2252,7 @@ static void gfs2_rgrp_error(struct gfs2_rgrpd *rgd)
 static void gfs2_adjust_reservation(struct gfs2_inode *ip,
 				    const struct gfs2_rbm *rbm, unsigned len)
 {
-	struct gfs2_blkreserv *rs = ip->i_res;
+	struct gfs2_blkreserv *rs = &ip->i_res;
 	struct gfs2_rgrpd *rgd = rbm->rgd;
 	unsigned rlen;
 	u64 block;
@@ -2310,8 +2295,8 @@ static void gfs2_set_alloc_start(struct gfs2_rbm *rbm,
 {
 	u64 goal;
 
-	if (gfs2_rs_active(ip->i_res)) {
-		*rbm = ip->i_res->rs_rbm;
+	if (gfs2_rs_active(&ip->i_res)) {
+		*rbm = ip->i_res.rs_rbm;
 		return;
 	}
 
@@ -2365,7 +2350,7 @@ int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *nblocks,
 	gfs2_alloc_extent(&rbm, dinode, nblocks);
 	block = gfs2_rbm_to_block(&rbm);
 	rbm.rgd->rd_last_alloc = block - rbm.rgd->rd_data0;
-	if (gfs2_rs_active(ip->i_res))
+	if (gfs2_rs_active(&ip->i_res))
 		gfs2_adjust_reservation(ip, &rbm, *nblocks);
 	ndata = *nblocks;
 	if (dinode)

fs/gfs2/rgrp.h

@@ -49,9 +49,9 @@ extern void gfs2_inplace_release(struct gfs2_inode *ip);
 extern int gfs2_alloc_blocks(struct gfs2_inode *ip, u64 *bn, unsigned int *n,
 			     bool dinode, u64 *generation);
 
-extern int gfs2_rs_alloc(struct gfs2_inode *ip);
+extern int gfs2_rsqa_alloc(struct gfs2_inode *ip);
 extern void gfs2_rs_deltree(struct gfs2_blkreserv *rs);
-extern void gfs2_rs_delete(struct gfs2_inode *ip, atomic_t *wcount);
+extern void gfs2_rsqa_delete(struct gfs2_inode *ip, atomic_t *wcount);
 extern void __gfs2_free_blocks(struct gfs2_inode *ip, u64 bstart, u32 blen, int meta);
 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);
@@ -78,7 +78,7 @@ extern int gfs2_rgrp_send_discards(struct gfs2_sbd *sdp, u64 offset,
 extern int gfs2_fitrim(struct file *filp, void __user *argp);
 
 /* This is how to tell if a reservation is in the rgrp tree: */
-static inline bool gfs2_rs_active(struct gfs2_blkreserv *rs)
+static inline bool gfs2_rs_active(const struct gfs2_blkreserv *rs)
 {
 	return rs && !RB_EMPTY_NODE(&rs->rs_node);
 }

fs/gfs2/super.c

@@ -83,6 +83,8 @@ enum {
 	Opt_nobarrier,
 	Opt_rgrplvb,
 	Opt_norgrplvb,
+	Opt_loccookie,
+	Opt_noloccookie,
 	Opt_error,
 };
 
@@ -122,6 +124,8 @@ static const match_table_t tokens = {
 	{Opt_nobarrier, "nobarrier"},
 	{Opt_rgrplvb, "rgrplvb"},
 	{Opt_norgrplvb, "norgrplvb"},
+	{Opt_loccookie, "loccookie"},
+	{Opt_noloccookie, "noloccookie"},
 	{Opt_error, NULL}
 };
 
@@ -278,6 +282,12 @@ int gfs2_mount_args(struct gfs2_args *args, char *options)
 		case Opt_norgrplvb:
 			args->ar_rgrplvb = 0;
 			break;
+		case Opt_loccookie:
+			args->ar_loccookie = 1;
+			break;
+		case Opt_noloccookie:
+			args->ar_loccookie = 0;
+			break;
 		case Opt_error:
 		default:
 			pr_warn("invalid mount option: %s\n", o);
@@ -556,6 +566,7 @@ void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
 	struct gfs2_statfs_change_host *l_sc = &sdp->sd_statfs_local;
 
 	gfs2_trans_add_meta(l_ip->i_gl, l_bh);
+	gfs2_trans_add_meta(m_ip->i_gl, m_bh);
 
 	spin_lock(&sdp->sd_statfs_spin);
 	m_sc->sc_total += l_sc->sc_total;
@@ -564,10 +575,8 @@ void update_statfs(struct gfs2_sbd *sdp, struct buffer_head *m_bh,
 	memset(l_sc, 0, sizeof(struct gfs2_statfs_change));
 	memset(l_bh->b_data + sizeof(struct gfs2_dinode),
 	       0, sizeof(struct gfs2_statfs_change));
-	spin_unlock(&sdp->sd_statfs_spin);
-
-	gfs2_trans_add_meta(m_ip->i_gl, m_bh);
 	gfs2_statfs_change_out(m_sc, m_bh->b_data + sizeof(struct gfs2_dinode));
+	spin_unlock(&sdp->sd_statfs_spin);
 }
 
 int gfs2_statfs_sync(struct super_block *sb, int type)
@@ -842,10 +851,6 @@ static int gfs2_make_fs_ro(struct gfs2_sbd *sdp)
 	gfs2_quota_sync(sdp->sd_vfs, 0);
 	gfs2_statfs_sync(sdp->sd_vfs, 0);
 
-	down_write(&sdp->sd_log_flush_lock);
-	clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
-	up_write(&sdp->sd_log_flush_lock);
-
 	gfs2_log_flush(sdp, NULL, SHUTDOWN_FLUSH);
 	wait_event(sdp->sd_reserving_log_wait, atomic_read(&sdp->sd_reserving_log) == 0);
 	gfs2_assert_warn(sdp, atomic_read(&sdp->sd_log_blks_free) == sdp->sd_jdesc->jd_blocks);
@@ -1419,6 +1424,8 @@ static int gfs2_show_options(struct seq_file *s, struct dentry *root)
 		seq_puts(s, ",demote_interface_used");
 	if (args->ar_rgrplvb)
 		seq_puts(s, ",rgrplvb");
+	if (args->ar_loccookie)
+		seq_puts(s, ",loccookie");
 	return 0;
 }
 
@@ -1512,6 +1519,7 @@ static void gfs2_evict_inode(struct inode *inode)
 	struct gfs2_sbd *sdp = sb->s_fs_info;
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
+	struct address_space *metamapping;
 	int error;
 
 	if (test_bit(GIF_FREE_VFS_INODE, &ip->i_flags)) {
@@ -1526,7 +1534,8 @@ static void gfs2_evict_inode(struct inode *inode)
 	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh);
 	if (unlikely(error)) {
 		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		gfs2_glock_dq_wait(&ip->i_iopen_gh);
+		gfs2_holder_uninit(&ip->i_iopen_gh);
 		goto out;
 	}
 
@@ -1575,8 +1584,8 @@ static void gfs2_evict_inode(struct inode *inode)
 
 out_truncate:
 	gfs2_log_flush(sdp, ip->i_gl, NORMAL_FLUSH);
+	metamapping = gfs2_glock2aspace(ip->i_gl);
 	if (test_bit(GLF_DIRTY, &ip->i_gl->gl_flags)) {
-		struct address_space *metamapping = gfs2_glock2aspace(ip->i_gl);
 		filemap_fdatawrite(metamapping);
 		filemap_fdatawait(metamapping);
 	}
@@ -1589,16 +1598,17 @@ static void gfs2_evict_inode(struct inode *inode)
 		goto out_unlock;
 	/* Needs to be done before glock release & also in a transaction */
 	truncate_inode_pages(&inode->i_data, 0);
+	truncate_inode_pages(metamapping, 0);
 	gfs2_trans_end(sdp);
 
 out_unlock:
 	/* Error path for case 1 */
-	if (gfs2_rs_active(ip->i_res))
-		gfs2_rs_deltree(ip->i_res);
+	if (gfs2_rs_active(&ip->i_res))
+		gfs2_rs_deltree(&ip->i_res);
 
 	if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
 		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq(&ip->i_iopen_gh);
+		gfs2_glock_dq_wait(&ip->i_iopen_gh);
 	}
 	gfs2_holder_uninit(&ip->i_iopen_gh);
 	gfs2_glock_dq_uninit(&gh);
@@ -1607,7 +1617,7 @@ static void gfs2_evict_inode(struct inode *inode)
 out:
 	/* Case 3 starts here */
 	truncate_inode_pages_final(&inode->i_data);
-	gfs2_rs_delete(ip, NULL);
+	gfs2_rsqa_delete(ip, NULL);
 	gfs2_ordered_del_inode(ip);
 	clear_inode(inode);
 	gfs2_dir_hash_inval(ip);
@@ -1619,7 +1629,8 @@ static void gfs2_evict_inode(struct inode *inode)
 	if (ip->i_iopen_gh.gh_gl) {
 		ip->i_iopen_gh.gh_gl->gl_object = NULL;
 		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
+		gfs2_glock_dq_wait(&ip->i_iopen_gh);
+		gfs2_holder_uninit(&ip->i_iopen_gh);
 	}
 }
 
@@ -1632,7 +1643,9 @@ static struct inode *gfs2_alloc_inode(struct super_block *sb)
 		ip->i_flags = 0;
 		ip->i_gl = NULL;
 		ip->i_rgd = NULL;
-		ip->i_res = NULL;
+		memset(&ip->i_res, 0, sizeof(ip->i_res));
+		RB_CLEAR_NODE(&ip->i_res.rs_node);
+		ip->i_rahead = 0;
 	}
 	return &ip->i_inode;
 }

fs/gfs2/util.c

@@ -27,7 +27,7 @@ struct kmem_cache *gfs2_inode_cachep __read_mostly;
 struct kmem_cache *gfs2_bufdata_cachep __read_mostly;
 struct kmem_cache *gfs2_rgrpd_cachep __read_mostly;
 struct kmem_cache *gfs2_quotad_cachep __read_mostly;
-struct kmem_cache *gfs2_rsrv_cachep __read_mostly;
+struct kmem_cache *gfs2_qadata_cachep __read_mostly;
 mempool_t *gfs2_page_pool __read_mostly;
 
 void gfs2_assert_i(struct gfs2_sbd *sdp)

fs/gfs2/util.h

@@ -149,7 +149,7 @@ extern struct kmem_cache *gfs2_inode_cachep;
 extern struct kmem_cache *gfs2_bufdata_cachep;
 extern struct kmem_cache *gfs2_rgrpd_cachep;
 extern struct kmem_cache *gfs2_quotad_cachep;
-extern struct kmem_cache *gfs2_rsrv_cachep;
+extern struct kmem_cache *gfs2_qadata_cachep;
 extern mempool_t *gfs2_page_pool;
 
 static inline unsigned int gfs2_tune_get_i(struct gfs2_tune *gt,

fs/gfs2/xattr.c

@@ -119,7 +119,7 @@ static int ea_foreach(struct gfs2_inode *ip, ea_call_t ea_call, void *data)
 	__be64 *eablk, *end;
 	int error;
 
-	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, &bh);
+	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0, &bh);
 	if (error)
 		return error;
 
@@ -143,7 +143,7 @@ static int ea_foreach(struct gfs2_inode *ip, ea_call_t ea_call, void *data)
 			break;
 		bn = be64_to_cpu(*eablk);
 
-		error = gfs2_meta_read(ip->i_gl, bn, DIO_WAIT, &eabh);
+		error = gfs2_meta_read(ip->i_gl, bn, DIO_WAIT, 0, &eabh);
 		if (error)
 			break;
 		error = ea_foreach_i(ip, eabh, ea_call, data);
@@ -477,7 +477,7 @@ static int gfs2_iter_unstuffed(struct gfs2_inode *ip, struct gfs2_ea_header *ea,
 		return -ENOMEM;
 
 	for (x = 0; x < nptrs; x++) {
-		error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0,
+		error = gfs2_meta_read(ip->i_gl, be64_to_cpu(*dataptrs), 0, 0,
 				       bh + x);
 		if (error) {
 			while (x--)
@@ -979,7 +979,7 @@ static int ea_set_block(struct gfs2_inode *ip, struct gfs2_ea_request *er,
 	if (ip->i_diskflags & GFS2_DIF_EA_INDIRECT) {
 		__be64 *end;
 
-		error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT,
+		error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0,
 				       &indbh);
 		if (error)
 			return error;
@@ -1256,7 +1256,7 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip)
 
 	memset(&rlist, 0, sizeof(struct gfs2_rgrp_list));
 
-	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, &indbh);
+	error = gfs2_meta_read(ip->i_gl, ip->i_eattr, DIO_WAIT, 0, &indbh);
 	if (error)
 		return error;
 

include/uapi/linux/gfs2_ondisk.h

@@ -297,6 +297,8 @@ struct gfs2_dinode {
 
 #define GFS2_FNAMESIZE		255
 #define GFS2_DIRENT_SIZE(name_len) ((sizeof(struct gfs2_dirent) + (name_len) + 7) & ~7)
+#define GFS2_MIN_DIRENT_SIZE (GFS2_DIRENT_SIZE(1))
+
 
 struct gfs2_dirent {
 	struct gfs2_inum de_inum;
@@ -304,11 +306,12 @@ struct gfs2_dirent {
 	__be16 de_rec_len;
 	__be16 de_name_len;
 	__be16 de_type;
+	__be16 de_rahead;
 	union {
-		__u8 __pad[14];
+		__u8 __pad[12];
 		struct {
-			__be16 de_rahead;
-			__u8 pad2[12];
+			__u32 de_cookie; /* ondisk value not used */
+			__u8 pad3[8];
 		};
 	};
 };