Merge branch 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2

* 'upstream-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mfasheh/ocfs2: (32 commits) ocfs2: recover orphans in offline slots during recovery and mount ocfs2: Pagecache usage optimization on ocfs2 ocfs2: fix rare stale inode errors when exporting via nfs ocfs2/dlm: Tweak mle_state output ocfs2/dlm: Do not purge lockres that is being migrated dlm_purge_lockres() ocfs2/dlm: Remove struct dlm_lock_name in struct dlm_master_list_entry ocfs2/dlm: Show the number of lockres/mles in dlm_state ocfs2/dlm: dlm_set_lockres_owner() and dlm_change_lockres_owner() inlined ocfs2/dlm: Improve lockres counts ocfs2/dlm: Track number of mles ocfs2/dlm: Indent dlm_cleanup_master_list() ocfs2/dlm: Activate dlm->master_hash for master list entries ocfs2/dlm: Create and destroy the dlm->master_hash ocfs2/dlm: Refactor dlm_clean_master_list() ocfs2/dlm: Clean up struct dlm_lock_name ocfs2/dlm: Encapsulate adding and removing of mle from dlm->master_list ocfs2: Optimize inode group allocation by recording last used group. ocfs2: Allocate inode groups from global_bitmap. ocfs2: Optimize inode allocation by remembering last group ocfs2: fix leaf start calculation in ocfs2_dx_dir_rebalance() ...
author: Linus Torvalds <torvalds@linux-foundation.org> 2009-04-03 12:13:56 -0700
committer: Linus Torvalds <torvalds@linux-foundation.org> 2009-04-03 12:13:56 -0700
commit: 78609a812e9afa87202631d128018361f68c44a9 (patch)
tree: 8c2d4b924ade170c69776d6cc39bec4dff3c8574
parent: 133e2a3164771454aa326859c2b293687189b553 (diff)
parent: 9140db04ef185f934acf2b1b15b3dd5e6a6bfc22 (diff)
30 files changed, 4389 insertions, 689 deletions
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 19e3a96aa02..678a067d925 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -294,6 +294,55 @@ static struct ocfs2_extent_tree_operations ocfs2_xattr_tree_et_ops = {
 	.eo_fill_max_leaf_clusters = ocfs2_xattr_tree_fill_max_leaf_clusters,
 };
 
+static void ocfs2_dx_root_set_last_eb_blk(struct ocfs2_extent_tree *et,
+					  u64 blkno)
+{
+	struct ocfs2_dx_root_block *dx_root = et->et_object;
+
+	dx_root->dr_last_eb_blk = cpu_to_le64(blkno);
+}
+
+static u64 ocfs2_dx_root_get_last_eb_blk(struct ocfs2_extent_tree *et)
+{
+	struct ocfs2_dx_root_block *dx_root = et->et_object;
+
+	return le64_to_cpu(dx_root->dr_last_eb_blk);
+}
+
+static void ocfs2_dx_root_update_clusters(struct inode *inode,
+					  struct ocfs2_extent_tree *et,
+					  u32 clusters)
+{
+	struct ocfs2_dx_root_block *dx_root = et->et_object;
+
+	le32_add_cpu(&dx_root->dr_clusters, clusters);
+}
+
+static int ocfs2_dx_root_sanity_check(struct inode *inode,
+				      struct ocfs2_extent_tree *et)
+{
+	struct ocfs2_dx_root_block *dx_root = et->et_object;
+
+	BUG_ON(!OCFS2_IS_VALID_DX_ROOT(dx_root));
+
+	return 0;
+}
+
+static void ocfs2_dx_root_fill_root_el(struct ocfs2_extent_tree *et)
+{
+	struct ocfs2_dx_root_block *dx_root = et->et_object;
+
+	et->et_root_el = &dx_root->dr_list;
+}
+
+static struct ocfs2_extent_tree_operations ocfs2_dx_root_et_ops = {
+	.eo_set_last_eb_blk	= ocfs2_dx_root_set_last_eb_blk,
+	.eo_get_last_eb_blk	= ocfs2_dx_root_get_last_eb_blk,
+	.eo_update_clusters	= ocfs2_dx_root_update_clusters,
+	.eo_sanity_check	= ocfs2_dx_root_sanity_check,
+	.eo_fill_root_el	= ocfs2_dx_root_fill_root_el,
+};
+
 static void __ocfs2_init_extent_tree(struct ocfs2_extent_tree *et,
 				     struct inode *inode,
 				     struct buffer_head *bh,
@@ -339,6 +388,14 @@ void ocfs2_init_xattr_value_extent_tree(struct ocfs2_extent_tree *et,
 				 &ocfs2_xattr_value_et_ops);
 }
 
+void ocfs2_init_dx_root_extent_tree(struct ocfs2_extent_tree *et,
+				    struct inode *inode,
+				    struct buffer_head *bh)
+{
+	__ocfs2_init_extent_tree(et, inode, bh, ocfs2_journal_access_dr,
+				 NULL, &ocfs2_dx_root_et_ops);
+}
+
 static inline void ocfs2_et_set_last_eb_blk(struct ocfs2_extent_tree *et,
 					    u64 new_last_eb_blk)
 {
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index cceff5c37f4..353254ba29e 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -75,6 +75,9 @@ struct ocfs2_xattr_value_buf;
 void ocfs2_init_xattr_value_extent_tree(struct ocfs2_extent_tree *et,
 					struct inode *inode,
 					struct ocfs2_xattr_value_buf *vb);
+void ocfs2_init_dx_root_extent_tree(struct ocfs2_extent_tree *et,
+				    struct inode *inode,
+				    struct buffer_head *bh);
 
 /*
  * Read an extent block into *bh.  If *bh is NULL, a bh will be
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 8e1709a679b..b2c52b3a148 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1956,15 +1956,16 @@ static int ocfs2_write_end(struct file *file, struct address_space *mapping,
 }
 
 const struct address_space_operations ocfs2_aops = {
-	.readpage	= ocfs2_readpage,
-	.readpages	= ocfs2_readpages,
-	.writepage	= ocfs2_writepage,
-	.write_begin	= ocfs2_write_begin,
-	.write_end	= ocfs2_write_end,
-	.bmap		= ocfs2_bmap,
-	.sync_page	= block_sync_page,
-	.direct_IO	= ocfs2_direct_IO,
-	.invalidatepage	= ocfs2_invalidatepage,
-	.releasepage	= ocfs2_releasepage,
-	.migratepage	= buffer_migrate_page,
+	.readpage		= ocfs2_readpage,
+	.readpages		= ocfs2_readpages,
+	.writepage		= ocfs2_writepage,
+	.write_begin		= ocfs2_write_begin,
+	.write_end		= ocfs2_write_end,
+	.bmap			= ocfs2_bmap,
+	.sync_page		= block_sync_page,
+	.direct_IO		= ocfs2_direct_IO,
+	.invalidatepage		= ocfs2_invalidatepage,
+	.releasepage		= ocfs2_releasepage,
+	.migratepage		= buffer_migrate_page,
+	.is_partially_uptodate	= block_is_partially_uptodate,
 };
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 04697ba7f73..4f85eceab37 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -33,6 +33,7 @@
 #include <linux/random.h>
 #include <linux/crc32.h>
 #include <linux/time.h>
+#include <linux/debugfs.h>
 
 #include "heartbeat.h"
 #include "tcp.h"
@@ -60,6 +61,11 @@ static unsigned long o2hb_live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
 static LIST_HEAD(o2hb_node_events);
 static DECLARE_WAIT_QUEUE_HEAD(o2hb_steady_queue);
 
+#define O2HB_DEBUG_DIR			"o2hb"
+#define O2HB_DEBUG_LIVENODES		"livenodes"
+static struct dentry *o2hb_debug_dir;
+static struct dentry *o2hb_debug_livenodes;
+
 static LIST_HEAD(o2hb_all_regions);
 
 static struct o2hb_callback {
@@ -905,7 +911,77 @@ static int o2hb_thread(void *data)
 	return 0;
 }
 
-void o2hb_init(void)
+#ifdef CONFIG_DEBUG_FS
+static int o2hb_debug_open(struct inode *inode, struct file *file)
+{
+	unsigned long map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	char *buf = NULL;
+	int i = -1;
+	int out = 0;
+
+	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!buf)
+		goto bail;
+
+	o2hb_fill_node_map(map, sizeof(map));
+
+	while ((i = find_next_bit(map, O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES)
+		out += snprintf(buf + out, PAGE_SIZE - out, "%d ", i);
+	out += snprintf(buf + out, PAGE_SIZE - out, "\n");
+
+	i_size_write(inode, out);
+
+	file->private_data = buf;
+
+	return 0;
+bail:
+	return -ENOMEM;
+}
+
+static int o2hb_debug_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static ssize_t o2hb_debug_read(struct file *file, char __user *buf,
+				 size_t nbytes, loff_t *ppos)
+{
+	return simple_read_from_buffer(buf, nbytes, ppos, file->private_data,
+				       i_size_read(file->f_mapping->host));
+}
+#else
+static int o2hb_debug_open(struct inode *inode, struct file *file)
+{
+	return 0;
+}
+static int o2hb_debug_release(struct inode *inode, struct file *file)
+{
+	return 0;
+}
+static ssize_t o2hb_debug_read(struct file *file, char __user *buf,
+			       size_t nbytes, loff_t *ppos)
+{
+	return 0;
+}
+#endif  /* CONFIG_DEBUG_FS */
+
+static struct file_operations o2hb_debug_fops = {
+	.open =		o2hb_debug_open,
+	.release =	o2hb_debug_release,
+	.read =		o2hb_debug_read,
+	.llseek =	generic_file_llseek,
+};
+
+void o2hb_exit(void)
+{
+	if (o2hb_debug_livenodes)
+		debugfs_remove(o2hb_debug_livenodes);
+	if (o2hb_debug_dir)
+		debugfs_remove(o2hb_debug_dir);
+}
+
+int o2hb_init(void)
 {
 	int i;
 
@@ -918,6 +994,24 @@ void o2hb_init(void)
 	INIT_LIST_HEAD(&o2hb_node_events);
 
 	memset(o2hb_live_node_bitmap, 0, sizeof(o2hb_live_node_bitmap));
+
+	o2hb_debug_dir = debugfs_create_dir(O2HB_DEBUG_DIR, NULL);
+	if (!o2hb_debug_dir) {
+		mlog_errno(-ENOMEM);
+		return -ENOMEM;
+	}
+
+	o2hb_debug_livenodes = debugfs_create_file(O2HB_DEBUG_LIVENODES,
+						   S_IFREG|S_IRUSR,
+						   o2hb_debug_dir, NULL,
+						   &o2hb_debug_fops);
+	if (!o2hb_debug_livenodes) {
+		mlog_errno(-ENOMEM);
+		debugfs_remove(o2hb_debug_dir);
+		return -ENOMEM;
+	}
+
+	return 0;
 }
 
 /* if we're already in a callback then we're already serialized by the sem */
diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h
index e511339886b..2f1649253b4 100644
--- a/fs/ocfs2/cluster/heartbeat.h
+++ b/fs/ocfs2/cluster/heartbeat.h
@@ -75,7 +75,8 @@ void o2hb_unregister_callback(const char *region_uuid,
 			      struct o2hb_callback_func *hc);
 void o2hb_fill_node_map(unsigned long *map,
 			unsigned bytes);
-void o2hb_init(void);
+void o2hb_exit(void);
+int o2hb_init(void);
 int o2hb_check_node_heartbeating(u8 node_num);
 int o2hb_check_node_heartbeating_from_callback(u8 node_num);
 int o2hb_check_local_node_heartbeating(void);
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index 70e8fa9e253..7ee6188bc79 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -881,6 +881,7 @@ static void __exit exit_o2nm(void)
 	o2cb_sys_shutdown();
 
 	o2net_exit();
+	o2hb_exit();
 }
 
 static int __init init_o2nm(void)
@@ -889,11 +890,13 @@ static int __init init_o2nm(void)
 
 	cluster_print_version();
 
-	o2hb_init();
+	ret = o2hb_init();
+	if (ret)
+		goto out;
 
 	ret = o2net_init();
 	if (ret)
-		goto out;
+		goto out_o2hb;
 
 	ret = o2net_register_hb_callbacks();
 	if (ret)
@@ -916,6 +919,8 @@ out_callbacks:
 	o2net_unregister_hb_callbacks();
 out_o2net:
 	o2net_exit();
+out_o2hb:
+	o2hb_exit();
 out:
 	return ret;
 }
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index f2c4098cf33..e71160cda11 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -41,6 +41,7 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/quotaops.h>
+#include <linux/sort.h>
 
 #define MLOG_MASK_PREFIX ML_NAMEI
 #include <cluster/masklog.h>
@@ -58,6 +59,7 @@
 #include "namei.h"
 #include "suballoc.h"
 #include "super.h"
+#include "sysfile.h"
 #include "uptodate.h"
 
 #include "buffer_head_io.h"
@@ -71,11 +73,6 @@ static unsigned char ocfs2_filetype_table[] = {
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
 };
 
-static int ocfs2_extend_dir(struct ocfs2_super *osb,
-			    struct inode *dir,
-			    struct buffer_head *parent_fe_bh,
-			    unsigned int blocks_wanted,
-			    struct buffer_head **new_de_bh);
 static int ocfs2_do_extend_dir(struct super_block *sb,
 			       handle_t *handle,
 			       struct inode *dir,
@@ -83,22 +80,36 @@ static int ocfs2_do_extend_dir(struct super_block *sb,
 			       struct ocfs2_alloc_context *data_ac,
 			       struct ocfs2_alloc_context *meta_ac,
 			       struct buffer_head **new_bh);
+static int ocfs2_dir_indexed(struct inode *inode);
 
 /*
  * These are distinct checks because future versions of the file system will
  * want to have a trailing dirent structure independent of indexing.
  */
-static int ocfs2_dir_has_trailer(struct inode *dir)
+static int ocfs2_supports_dir_trailer(struct inode *dir)
 {
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+
 	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		return 0;
 
-	return ocfs2_meta_ecc(OCFS2_SB(dir->i_sb));
+	return ocfs2_meta_ecc(osb) || ocfs2_dir_indexed(dir);
 }
 
-static int ocfs2_supports_dir_trailer(struct ocfs2_super *osb)
+/*
+ * "new' here refers to the point at which we're creating a new
+ * directory via "mkdir()", but also when we're expanding an inline
+ * directory. In either case, we don't yet have the indexing bit set
+ * on the directory, so the standard checks will fail in when metaecc
+ * is turned off. Only directory-initialization type functions should
+ * use this then. Everything else wants ocfs2_supports_dir_trailer()
+ */
+static int ocfs2_new_dir_wants_trailer(struct inode *dir)
 {
-	return ocfs2_meta_ecc(osb);
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+
+	return ocfs2_meta_ecc(osb) ||
+		ocfs2_supports_indexed_dirs(osb);
 }
 
 static inline unsigned int ocfs2_dir_trailer_blk_off(struct super_block *sb)
@@ -130,7 +141,7 @@ static int ocfs2_skip_dir_trailer(struct inode *dir,
 {
 	unsigned long toff = blklen - sizeof(struct ocfs2_dir_block_trailer);
 
-	if (!ocfs2_dir_has_trailer(dir))
+	if (!ocfs2_supports_dir_trailer(dir))
 		return 0;
 
 	if (offset != toff)
@@ -140,7 +151,7 @@ static int ocfs2_skip_dir_trailer(struct inode *dir,
 }
 
 static void ocfs2_init_dir_trailer(struct inode *inode,
-				   struct buffer_head *bh)
+				   struct buffer_head *bh, u16 rec_len)
 {
 	struct ocfs2_dir_block_trailer *trailer;
 
@@ -150,6 +161,153 @@ static void ocfs2_init_dir_trailer(struct inode *inode,
 			cpu_to_le16(sizeof(struct ocfs2_dir_block_trailer));
 	trailer->db_parent_dinode = cpu_to_le64(OCFS2_I(inode)->ip_blkno);
 	trailer->db_blkno = cpu_to_le64(bh->b_blocknr);
+	trailer->db_free_rec_len = cpu_to_le16(rec_len);
+}
+/*
+ * Link an unindexed block with a dir trailer structure into the index free
+ * list. This function will modify dirdata_bh, but assumes you've already
+ * passed it to the journal.
+ */
+static int ocfs2_dx_dir_link_trailer(struct inode *dir, handle_t *handle,
+				     struct buffer_head *dx_root_bh,
+				     struct buffer_head *dirdata_bh)
+{
+	int ret;
+	struct ocfs2_dx_root_block *dx_root;
+	struct ocfs2_dir_block_trailer *trailer;
+
+	ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+	trailer = ocfs2_trailer_from_bh(dirdata_bh, dir->i_sb);
+	dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+
+	trailer->db_free_next = dx_root->dr_free_blk;
+	dx_root->dr_free_blk = cpu_to_le64(dirdata_bh->b_blocknr);
+
+	ocfs2_journal_dirty(handle, dx_root_bh);
+
+out:
+	return ret;
+}
+
+static int ocfs2_free_list_at_root(struct ocfs2_dir_lookup_result *res)
+{
+	return res->dl_prev_leaf_bh == NULL;
+}
+
+void ocfs2_free_dir_lookup_result(struct ocfs2_dir_lookup_result *res)
+{
+	brelse(res->dl_dx_root_bh);
+	brelse(res->dl_leaf_bh);
+	brelse(res->dl_dx_leaf_bh);
+	brelse(res->dl_prev_leaf_bh);
+}
+
+static int ocfs2_dir_indexed(struct inode *inode)
+{
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INDEXED_DIR_FL)
+		return 1;
+	return 0;
+}
+
+static inline int ocfs2_dx_root_inline(struct ocfs2_dx_root_block *dx_root)
+{
+	return dx_root->dr_flags & OCFS2_DX_FLAG_INLINE;
+}
+
+/*
+ * Hashing code adapted from ext3
+ */
+#define DELTA 0x9E3779B9
+
+static void TEA_transform(__u32 buf[4], __u32 const in[])
+{
+	__u32	sum = 0;
+	__u32	b0 = buf[0], b1 = buf[1];
+	__u32	a = in[0], b = in[1], c = in[2], d = in[3];
+	int	n = 16;
+
+	do {
+		sum += DELTA;
+		b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
+		b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
+	} while (--n);
+
+	buf[0] += b0;
+	buf[1] += b1;
+}
+
+static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
+{
+	__u32	pad, val;
+	int	i;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	val = pad;
+	if (len > num*4)
+		len = num * 4;
+	for (i = 0; i < len; i++) {
+		if ((i % 4) == 0)
+			val = pad;
+		val = msg[i] + (val << 8);
+		if ((i % 4) == 3) {
+			*buf++ = val;
+			val = pad;
+			num--;
+		}
+	}
+	if (--num >= 0)
+		*buf++ = val;
+	while (--num >= 0)
+		*buf++ = pad;
+}
+
+static void ocfs2_dx_dir_name_hash(struct inode *dir, const char *name, int len,
+				   struct ocfs2_dx_hinfo *hinfo)
+{
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+	const char	*p;
+	__u32		in[8], buf[4];
+
+	/*
+	 * XXX: Is this really necessary, if the index is never looked
+	 * at by readdir? Is a hash value of '0' a bad idea?
+	 */
+	if ((len == 1 && !strncmp(".", name, 1)) ||
+	    (len == 2 && !strncmp("..", name, 2))) {
+		buf[0] = buf[1] = 0;
+		goto out;
+	}
+
+#ifdef OCFS2_DEBUG_DX_DIRS
+	/*
+	 * This makes it very easy to debug indexing problems. We
+	 * should never allow this to be selected without hand editing
+	 * this file though.
+	 */
+	buf[0] = buf[1] = len;
+	goto out;
+#endif
+
+	memcpy(buf, osb->osb_dx_seed, sizeof(buf));
+
+	p = name;
+	while (len > 0) {
+		str2hashbuf(p, len, in, 4);
+		TEA_transform(buf, in);
+		len -= 16;
+		p += 16;
+	}
+
+out:
+	hinfo->major_hash = buf[0];
+	hinfo->minor_hash = buf[1];
 }
 
 /*
@@ -312,6 +470,52 @@ static int ocfs2_validate_dir_block(struct super_block *sb,
 }
 
 /*
+ * Validate a directory trailer.
+ *
+ * We check the trailer here rather than in ocfs2_validate_dir_block()
+ * because that function doesn't have the inode to test.
+ */
+static int ocfs2_check_dir_trailer(struct inode *dir, struct buffer_head *bh)
+{
+	int rc = 0;
+	struct ocfs2_dir_block_trailer *trailer;
+
+	trailer = ocfs2_trailer_from_bh(bh, dir->i_sb);
+	if (!OCFS2_IS_VALID_DIR_TRAILER(trailer)) {
+		rc = -EINVAL;
+		ocfs2_error(dir->i_sb,
+			    "Invalid dirblock #%llu: "
+			    "signature = %.*s\n",
+			    (unsigned long long)bh->b_blocknr, 7,
+			    trailer->db_signature);
+		goto out;
+	}
+	if (le64_to_cpu(trailer->db_blkno) != bh->b_blocknr) {
+		rc = -EINVAL;
+		ocfs2_error(dir->i_sb,
+			    "Directory block #%llu has an invalid "
+			    "db_blkno of %llu",
+			    (unsigned long long)bh->b_blocknr,
+			    (unsigned long long)le64_to_cpu(trailer->db_blkno));
+		goto out;
+	}
+	if (le64_to_cpu(trailer->db_parent_dinode) !=
+	    OCFS2_I(dir)->ip_blkno) {
+		rc = -EINVAL;
+		ocfs2_error(dir->i_sb,
+			    "Directory block #%llu on dinode "
+			    "#%llu has an invalid parent_dinode "
+			    "of %llu",
+			    (unsigned long long)bh->b_blocknr,
+			    (unsigned long long)OCFS2_I(dir)->ip_blkno,
+			    (unsigned long long)le64_to_cpu(trailer->db_blkno));
+		goto out;
+	}
+out:
+	return rc;
+}
+
+/*
  * This function forces all errors to -EIO for consistency with its
  * predecessor, ocfs2_bread().  We haven't audited what returning the
  * real error codes would do to callers.  We log the real codes with
@@ -322,7 +526,6 @@ static int ocfs2_read_dir_block(struct inode *inode, u64 v_block,
 {
 	int rc = 0;
 	struct buffer_head *tmp = *bh;
-	struct ocfs2_dir_block_trailer *trailer;
 
 	rc = ocfs2_read_virt_blocks(inode, v_block, 1, &tmp, flags,
 				    ocfs2_validate_dir_block);
@@ -331,42 +534,13 @@ static int ocfs2_read_dir_block(struct inode *inode, u64 v_block,
 		goto out;
 	}
 
-	/*
-	 * We check the trailer here rather than in
-	 * ocfs2_validate_dir_block() because that function doesn't have
-	 * the inode to test.
-	 */
 	if (!(flags & OCFS2_BH_READAHEAD) &&
-	    ocfs2_dir_has_trailer(inode)) {
-		trailer = ocfs2_trailer_from_bh(tmp, inode->i_sb);
-		if (!OCFS2_IS_VALID_DIR_TRAILER(trailer)) {
-			rc = -EINVAL;
-			ocfs2_error(inode->i_sb,
-				    "Invalid dirblock #%llu: "
-				    "signature = %.*s\n",
-				    (unsigned long long)tmp->b_blocknr, 7,
-				    trailer->db_signature);
-			goto out;
-		}
-		if (le64_to_cpu(trailer->db_blkno) != tmp->b_blocknr) {
-			rc = -EINVAL;
-			ocfs2_error(inode->i_sb,
-				    "Directory block #%llu has an invalid "
-				    "db_blkno of %llu",
-				    (unsigned long long)tmp->b_blocknr,
-				    (unsigned long long)le64_to_cpu(trailer->db_blkno));
-			goto out;
-		}
-		if (le64_to_cpu(trailer->db_parent_dinode) !=
-		    OCFS2_I(inode)->ip_blkno) {
-			rc = -EINVAL;
-			ocfs2_error(inode->i_sb,
-				    "Directory block #%llu on dinode "
-				    "#%llu has an invalid parent_dinode "
-				    "of %llu",
-				    (unsigned long long)tmp->b_blocknr,
-				    (unsigned long long)OCFS2_I(inode)->ip_blkno,
-				    (unsigned long long)le64_to_cpu(trailer->db_blkno));
+	    ocfs2_supports_dir_trailer(inode)) {
+		rc = ocfs2_check_dir_trailer(inode, tmp);
+		if (rc) {
+			if (!*bh)
+				brelse(tmp);
+			mlog_errno(rc);
 			goto out;
 		}
 	}
@@ -379,6 +553,141 @@ out:
 	return rc ? -EIO : 0;
 }
 
+/*
+ * Read the block at 'phys' which belongs to this directory
+ * inode. This function does no virtual->physical block translation -
+ * what's passed in is assumed to be a valid directory block.
+ */
+static int ocfs2_read_dir_block_direct(struct inode *dir, u64 phys,
+				       struct buffer_head **bh)
+{
+	int ret;
+	struct buffer_head *tmp = *bh;
+
+	ret = ocfs2_read_block(dir, phys, &tmp, ocfs2_validate_dir_block);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (ocfs2_supports_dir_trailer(dir)) {
+		ret = ocfs2_check_dir_trailer(dir, tmp);
+		if (ret) {
+			if (!*bh)
+				brelse(tmp);
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	if (!ret && !*bh)
+		*bh = tmp;
+out:
+	return ret;
+}
+
+static int ocfs2_validate_dx_root(struct super_block *sb,
+				  struct buffer_head *bh)
+{
+	int ret;
+	struct ocfs2_dx_root_block *dx_root;
+
+	BUG_ON(!buffer_uptodate(bh));
+
+	dx_root = (struct ocfs2_dx_root_block *) bh->b_data;
+
+	ret = ocfs2_validate_meta_ecc(sb, bh->b_data, &dx_root->dr_check);
+	if (ret) {
+		mlog(ML_ERROR,
+		     "Checksum failed for dir index root block %llu\n",
+		     (unsigned long long)bh->b_blocknr);
+		return ret;
+	}
+
+	if (!OCFS2_IS_VALID_DX_ROOT(dx_root)) {
+		ocfs2_error(sb,
+			    "Dir Index Root # %llu has bad signature %.*s",
+			    (unsigned long long)le64_to_cpu(dx_root->dr_blkno),
+			    7, dx_root->dr_signature);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ocfs2_read_dx_root(struct inode *dir, struct ocfs2_dinode *di,
+			      struct buffer_head **dx_root_bh)
+{
+	int ret;
+	u64 blkno = le64_to_cpu(di->i_dx_root);
+	struct buffer_head *tmp = *dx_root_bh;
+
+	ret = ocfs2_read_block(dir, blkno, &tmp, ocfs2_validate_dx_root);
+
+	/* If ocfs2_read_block() got us a new bh, pass it up. */
+	if (!ret && !*dx_root_bh)
+		*dx_root_bh = tmp;
+
+	return ret;
+}
+
+static int ocfs2_validate_dx_leaf(struct super_block *sb,
+				  struct buffer_head *bh)
+{
+	int ret;
+	struct ocfs2_dx_leaf *dx_leaf = (struct ocfs2_dx_leaf *)bh->b_data;
+
+	BUG_ON(!buffer_uptodate(bh));
+
+	ret = ocfs2_validate_meta_ecc(sb, bh->b_data, &dx_leaf->dl_check);
+	if (ret) {
+		mlog(ML_ERROR,
+		     "Checksum failed for dir index leaf block %llu\n",
+		     (unsigned long long)bh->b_blocknr);
+		return ret;
+	}
+
+	if (!OCFS2_IS_VALID_DX_LEAF(dx_leaf)) {
+		ocfs2_error(sb, "Dir Index Leaf has bad signature %.*s",
+			    7, dx_leaf->dl_signature);
+		return -EROFS;
+	}
+
+	return 0;
+}
+
+static int ocfs2_read_dx_leaf(struct inode *dir, u64 blkno,
+			      struct buffer_head **dx_leaf_bh)
+{
+	int ret;
+	struct buffer_head *tmp = *dx_leaf_bh;
+
+	ret = ocfs2_read_block(dir, blkno, &tmp, ocfs2_validate_dx_leaf);
+
+	/* If ocfs2_read_block() got us a new bh, pass it up. */
+	if (!ret && !*dx_leaf_bh)
+		*dx_leaf_bh = tmp;
+
+	return ret;
+}
+
+/*
+ * Read a series of dx_leaf blocks. This expects all buffer_head
+ * pointers to be NULL on function entry.
+ */
+static int ocfs2_read_dx_leaves(struct inode *dir, u64 start, int num,
+				struct buffer_head **dx_leaf_bhs)
+{
+	int ret;
+
+	ret = ocfs2_read_blocks(dir, start, num, dx_leaf_bhs, 0,
+				ocfs2_validate_dx_leaf);
+	if (ret)
+		mlog_errno(ret);
+
+	return ret;
+}
+
 static struct buffer_head *ocfs2_find_entry_el(const char *name, int namelen,
 					       struct inode *dir,
 					       struct ocfs2_dir_entry **res_dir)
@@ -480,39 +789,340 @@ cleanup_and_exit:
 	return ret;
 }
 
+static int ocfs2_dx_dir_lookup_rec(struct inode *inode,
+				   struct ocfs2_extent_list *el,
+				   u32 major_hash,
+				   u32 *ret_cpos,
+				   u64 *ret_phys_blkno,
+				   unsigned int *ret_clen)
+{
+	int ret = 0, i, found;
+	struct buffer_head *eb_bh = NULL;
+	struct ocfs2_extent_block *eb;
+	struct ocfs2_extent_rec *rec = NULL;
+
+	if (el->l_tree_depth) {
+		ret = ocfs2_find_leaf(inode, el, major_hash, &eb_bh);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		eb = (struct ocfs2_extent_block *) eb_bh->b_data;
+		el = &eb->h_list;
+
+		if (el->l_tree_depth) {
+			ocfs2_error(inode->i_sb,
+				    "Inode %lu has non zero tree depth in "
+				    "btree tree block %llu\n", inode->i_ino,
+				    (unsigned long long)eb_bh->b_blocknr);
+			ret = -EROFS;
+			goto out;
+		}
+	}
+
+	found = 0;
+	for (i = le16_to_cpu(el->l_next_free_rec) - 1; i >= 0; i--) {
+		rec = &el->l_recs[i];
+
+		if (le32_to_cpu(rec->e_cpos) <= major_hash) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found) {
+		ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
+			    "record (%u, %u, 0) in btree", inode->i_ino,
+			    le32_to_cpu(rec->e_cpos),
+			    ocfs2_rec_clusters(el, rec));
+		ret = -EROFS;
+		goto out;
+	}
+
+	if (ret_phys_blkno)
+		*ret_phys_blkno = le64_to_cpu(rec->e_blkno);
+	if (ret_cpos)
+		*ret_cpos = le32_to_cpu(rec->e_cpos);
+	if (ret_clen)
+		*ret_clen = le16_to_cpu(rec->e_leaf_clusters);
+
+out:
+	brelse(eb_bh);
+	return ret;
+}
+
+/*
+ * Returns the block index, from the start of the cluster which this
+ * hash belongs too.
+ */
+static inline unsigned int __ocfs2_dx_dir_hash_idx(struct ocfs2_super *osb,
+						   u32 minor_hash)
+{
+	return minor_hash & osb->osb_dx_mask;
+}
+
+static inline unsigned int ocfs2_dx_dir_hash_idx(struct ocfs2_super *osb,
+					  struct ocfs2_dx_hinfo *hinfo)
+{
+	return __ocfs2_dx_dir_hash_idx(osb, hinfo->minor_hash);
+}
+
+static int ocfs2_dx_dir_lookup(struct inode *inode,
+			       struct ocfs2_extent_list *el,
+			       struct ocfs2_dx_hinfo *hinfo,
+			       u32 *ret_cpos,
+			       u64 *ret_phys_blkno)
+{
+	int ret = 0;
+	unsigned int cend, uninitialized_var(clen);
+	u32 uninitialized_var(cpos);
+	u64 uninitialized_var(blkno);
+	u32 name_hash = hinfo->major_hash;
+
+	ret = ocfs2_dx_dir_lookup_rec(inode, el, name_hash, &cpos, &blkno,
+				      &clen);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	cend = cpos + clen;
+	if (name_hash >= cend) {
+		/* We want the last cluster */
+		blkno += ocfs2_clusters_to_blocks(inode->i_sb, clen - 1);
+		cpos += clen
author	Linus Torvalds <torvalds@linux-foundation.org>	2009-04-03 12:13:56 -0700
committer	Linus Torvalds <torvalds@linux-foundation.org>	2009-04-03 12:13:56 -0700
commit	78609a812e9afa87202631d128018361f68c44a9 (patch)
tree	8c2d4b924ade170c69776d6cc39bec4dff3c8574
parent	133e2a3164771454aa326859c2b293687189b553 (diff)
parent	9140db04ef185f934acf2b1b15b3dd5e6a6bfc22 (diff)