Skip to contentSkip to conversation

Linux 2.6.32.1

DISCUSSION Greg KH 1 participant 2 messages Dec 14, 2009

Subsystems (9)
Documentation SCSI Kbuild Scheduler +5 more subsystems
lore
Share & tools
lore
author
#1 lore raw
In reply to Greg KH
Documentation/filesystems/ext4.txt +8 -2
index 6d94e06..af6885c 100644
@@ -153,8 +153,8 @@ journal_dev=devnum	When the external journal device's major/minor numbers
 			identified through its new major/minor numbers encoded
 			in devnum.
 
-noload			Don't load the journal on mounting.  Note that
-                     	if the filesystem was not unmounted cleanly,
+norecovery		Don't load the journal on mounting.  Note that
+noload			if the filesystem was not unmounted cleanly,
                      	skipping the journal replay will lead to the
                      	filesystem containing inconsistencies that can
                      	lead to any number of problems.
@@ -353,6 +353,12 @@ noauto_da_alloc		replacing existing files via patterns such as
 			system crashes before the delayed allocation
 			blocks are forced to disk.
 
+discard		Controls whether ext4 should issue discard/TRIM
+nodiscard(*)		commands to the underlying block device when
+			blocks are freed.  This is useful for SSD devices
+			and sparse/thinly-provisioned LUNs, but it is off
+			by default until sufficient testing has been done.
+
 Data Mode
 =========
 There are 3 different data modes:
Makefile +1 -1
index f5cdb72..d0d7e9c 100644
@@ -1,7 +1,7 @@
 VERSION = 2
 PATCHLEVEL = 6
 SUBLEVEL = 32
-EXTRAVERSION =
+EXTRAVERSION = .1
 NAME = Man-Eating Seals of Antiquity
 
 # *DOCUMENTATION*
drivers/scsi/hosts.c +10 -3
index c968cc3..554626e 100644
@@ -180,14 +180,20 @@ void scsi_remove_host(struct Scsi_Host *shost)
 EXPORT_SYMBOL(scsi_remove_host);
 
 /**
- * scsi_add_host - add a scsi host
+ * scsi_add_host_with_dma - add a scsi host with dma device
  * @shost:	scsi host pointer to add
  * @dev:	a struct device of type scsi class
+ * @dma_dev:	dma device for the host
+ *
+ * Note: You rarely need to worry about this unless you're in a
+ * virtualised host environments, so use the simpler scsi_add_host()
+ * function instead.
  *
  * Return value: 
  * 	0 on success / != 0 for error
  **/
-int scsi_add_host(struct Scsi_Host *shost, struct device *dev)
+int scsi_add_host_with_dma(struct Scsi_Host *shost, struct device *dev,
+			   struct device *dma_dev)
 {
 	struct scsi_host_template *sht = shost->hostt;
 	int error = -EINVAL;
@@ -207,6 +213,7 @@ int scsi_add_host(struct Scsi_Host *shost, struct device *dev)
 
 	if (!shost->shost_gendev.parent)
 		shost->shost_gendev.parent = dev ? dev : &platform_bus;
+	shost->dma_dev = dma_dev;
 
 	error = device_add(&shost->shost_gendev);
 	if (error)
@@ -262,7 +269,7 @@ int scsi_add_host(struct Scsi_Host *shost, struct device *dev)
  fail:
 	return error;
 }
-EXPORT_SYMBOL(scsi_add_host);
+EXPORT_SYMBOL(scsi_add_host_with_dma);
 
 static void scsi_host_dev_release(struct device *dev)
 {
drivers/scsi/lpfc/lpfc_init.c +1 -1
index 562d8ce..f913f1e 100644
@@ -2408,7 +2408,7 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev)
 	vport->els_tmofunc.function = lpfc_els_timeout;
 	vport->els_tmofunc.data = (unsigned long)vport;
 
-	error = scsi_add_host(shost, dev);
+	error = scsi_add_host_with_dma(shost, dev, &phba->pcidev->dev);
 	if (error)
 		goto out_put_shost;
 
drivers/scsi/megaraid/megaraid_sas.c +4 -4
index a39addc..507ccc6 100644
@@ -3032,7 +3032,7 @@ megasas_mgmt_fw_ioctl(struct megasas_instance *instance,
 	int error = 0, i;
 	void *sense = NULL;
 	dma_addr_t sense_handle;
-	u32 *sense_ptr;
+	unsigned long *sense_ptr;
 
 	memset(kbuff_arr, 0, sizeof(kbuff_arr));
 
@@ -3109,7 +3109,7 @@ megasas_mgmt_fw_ioctl(struct megasas_instance *instance,
 		}
 
 		sense_ptr =
-		    (u32 *) ((unsigned long)cmd->frame + ioc->sense_off);
+		(unsigned long *) ((unsigned long)cmd->frame + ioc->sense_off);
 		*sense_ptr = sense_handle;
 	}
 
@@ -3140,8 +3140,8 @@ megasas_mgmt_fw_ioctl(struct megasas_instance *instance,
 		 * sense_ptr points to the location that has the user
 		 * sense buffer address
 		 */
-		sense_ptr = (u32 *) ((unsigned long)ioc->frame.raw +
-				     ioc->sense_off);
+		sense_ptr = (unsigned long *) ((unsigned long)ioc->frame.raw +
+				ioc->sense_off);
 
 		if (copy_to_user((void __user *)((unsigned long)(*sense_ptr)),
 				 sense, ioc->sense_len)) {
drivers/scsi/qla2xxx/qla_attr.c +2 -1
index fbcb82a..21e2bc4 100644
@@ -1654,7 +1654,8 @@ qla24xx_vport_create(struct fc_vport *fc_vport, bool disable)
 			fc_vport_set_state(fc_vport, FC_VPORT_LINKDOWN);
 	}
 
-	if (scsi_add_host(vha->host, &fc_vport->dev)) {
+	if (scsi_add_host_with_dma(vha->host, &fc_vport->dev,
+				   &ha->pdev->dev)) {
 		DEBUG15(printk("scsi(%ld): scsi_add_host failure for VP[%d].\n",
 			vha->host_no, vha->vp_idx));
 		goto vport_create_failed_2;
drivers/scsi/scsi_lib_dma.c +2 -2
index ac6855c..dcd1285 100644
@@ -23,7 +23,7 @@ int scsi_dma_map(struct scsi_cmnd *cmd)
 	int nseg = 0;
 
 	if (scsi_sg_count(cmd)) {
-		struct device *dev = cmd->device->host->shost_gendev.parent;
+		struct device *dev = cmd->device->host->dma_dev;
 
 		nseg = dma_map_sg(dev, scsi_sglist(cmd), scsi_sg_count(cmd),
 				  cmd->sc_data_direction);
@@ -41,7 +41,7 @@ EXPORT_SYMBOL(scsi_dma_map);
 void scsi_dma_unmap(struct scsi_cmnd *cmd)
 {
 	if (scsi_sg_count(cmd)) {
-		struct device *dev = cmd->device->host->shost_gendev.parent;
+		struct device *dev = cmd->device->host->dma_dev;
 
 		dma_unmap_sg(dev, scsi_sglist(cmd), scsi_sg_count(cmd),
 			     cmd->sc_data_direction);
fs/ext4/balloc.c +7 -1
index 1d04189..f3032c9 100644
@@ -761,7 +761,13 @@ static unsigned long ext4_bg_num_gdb_meta(struct super_block *sb,
 static unsigned long ext4_bg_num_gdb_nometa(struct super_block *sb,
 					ext4_group_t group)
 {
-	return ext4_bg_has_super(sb, group) ? EXT4_SB(sb)->s_gdb_count : 0;
+	if (!ext4_bg_has_super(sb, group))
+		return 0;
+
+	if (EXT4_HAS_INCOMPAT_FEATURE(sb,EXT4_FEATURE_INCOMPAT_META_BG))
+		return le32_to_cpu(EXT4_SB(sb)->s_es->s_first_meta_bg);
+	else
+		return EXT4_SB(sb)->s_gdb_count;
 }
 
 /**
fs/ext4/block_validity.c +1 -1
index 50784ef..dc79b75 100644
@@ -160,7 +160,7 @@ int ext4_setup_system_zone(struct super_block *sb)
 		if (ext4_bg_has_super(sb, i) &&
 		    ((i < 5) || ((i % flex_size) == 0)))
 			add_system_zone(sbi, ext4_group_first_block_no(sb, i),
-					sbi->s_gdb_count + 1);
+					ext4_bg_num_gdb(sb, i) + 1);
 		gdp = ext4_get_group_desc(sb, i, NULL);
 		ret = add_system_zone(sbi, ext4_block_bitmap(sb, gdp), 1);
 		if (ret)
fs/ext4/ext4.h +8 -0
index 8825515..bd2a9dd 100644
@@ -703,6 +703,13 @@ struct ext4_inode_info {
 	struct list_head i_aio_dio_complete_list;
 	/* current io_end structure for async DIO write*/
 	ext4_io_end_t *cur_aio_dio;
+
+	/*
+	 * Transactions that contain inode's metadata needed to complete
+	 * fsync and fdatasync, respectively.
+	 */
+	tid_t i_sync_tid;
+	tid_t i_datasync_tid;
 };
 
 /*
@@ -750,6 +757,7 @@ struct ext4_inode_info {
 #define EXT4_MOUNT_DELALLOC		0x8000000 /* Delalloc support */
 #define EXT4_MOUNT_DATA_ERR_ABORT	0x10000000 /* Abort on file data write */
 #define EXT4_MOUNT_BLOCK_VALIDITY	0x20000000 /* Block validity checking */
+#define EXT4_MOUNT_DISCARD		0x40000000 /* Issue DISCARD requests */
 
 #define clear_opt(o, opt)		o &= ~EXT4_MOUNT_##opt
 #define set_opt(o, opt)			o |= EXT4_MOUNT_##opt
fs/ext4/ext4_jbd2.h +19 -2
index a286598..1892a77 100644
@@ -49,7 +49,7 @@
 
 #define EXT4_DATA_TRANS_BLOCKS(sb)	(EXT4_SINGLEDATA_TRANS_BLOCKS(sb) + \
 					 EXT4_XATTR_TRANS_BLOCKS - 2 + \
-					 2*EXT4_QUOTA_TRANS_BLOCKS(sb))
+					 EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
 
 /*
  * Define the number of metadata blocks we need to account to modify data.
@@ -57,7 +57,7 @@
  * This include super block, inode block, quota blocks and xattr blocks
  */
 #define EXT4_META_TRANS_BLOCKS(sb)	(EXT4_XATTR_TRANS_BLOCKS + \
-					2*EXT4_QUOTA_TRANS_BLOCKS(sb))
+					EXT4_MAXQUOTAS_TRANS_BLOCKS(sb))
 
 /* Delete operations potentially hit one directory's namespace plus an
  * entire inode, plus arbitrary amounts of bitmap/indirection data.  Be
@@ -92,6 +92,7 @@
  * but inode, sb and group updates are done only once */
 #define EXT4_QUOTA_INIT_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_INIT_ALLOC*\
 		(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_INIT_REWRITE) : 0)
+
 #define EXT4_QUOTA_DEL_BLOCKS(sb) (test_opt(sb, QUOTA) ? (DQUOT_DEL_ALLOC*\
 		(EXT4_SINGLEDATA_TRANS_BLOCKS(sb)-3)+3+DQUOT_DEL_REWRITE) : 0)
 #else
@@ -99,6 +100,9 @@
 #define EXT4_QUOTA_INIT_BLOCKS(sb) 0
 #define EXT4_QUOTA_DEL_BLOCKS(sb) 0
 #endif
+#define EXT4_MAXQUOTAS_TRANS_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_TRANS_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
+#define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
 
 int
 ext4_mark_iloc_dirty(handle_t *handle,
@@ -254,6 +258,19 @@ static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
 	return 0;
 }
 
+static inline void ext4_update_inode_fsync_trans(handle_t *handle,
+						 struct inode *inode,
+						 int datasync)
+{
+	struct ext4_inode_info *ei = EXT4_I(inode);
+
+	if (ext4_handle_valid(handle)) {
+		ei->i_sync_tid = handle->h_transaction->t_tid;
+		if (datasync)
+			ei->i_datasync_tid = handle->h_transaction->t_tid;
+	}
+}
+
 /* super.c */
 int ext4_force_commit(struct super_block *sb);
 
fs/ext4/extents.c +16 -6
index 715264b..8b8bae4 100644
@@ -1761,7 +1761,9 @@ int ext4_ext_walk_space(struct inode *inode, ext4_lblk_t block,
 	while (block < last && block != EXT_MAX_BLOCK) {
 		num = last - block;
 		/* find extent for this block */
+		down_read(&EXT4_I(inode)->i_data_sem);
 		path = ext4_ext_find_extent(inode, block, path);
+		up_read(&EXT4_I(inode)->i_data_sem);
 		if (IS_ERR(path)) {
 			err = PTR_ERR(path);
 			path = NULL;
@@ -2074,7 +2076,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode,
 		ext_debug("free last %u blocks starting %llu\n", num, start);
 		for (i = 0; i < num; i++) {
 			bh = sb_find_get_block(inode->i_sb, start + i);
-			ext4_forget(handle, 0, inode, bh, start + i);
+			ext4_forget(handle, metadata, inode, bh, start + i);
 		}
 		ext4_free_blocks(handle, inode, start, num, metadata);
 	} else if (from == le32_to_cpu(ex->ee_block)
@@ -2167,7 +2169,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode,
 			correct_index = 1;
 			credits += (ext_depth(inode)) + 1;
 		}
-		credits += 2 * EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
+		credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
 
 		err = ext4_ext_truncate_extend_restart(handle, inode, credits);
 		if (err)
@@ -3064,6 +3066,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 	if (flags == EXT4_GET_BLOCKS_DIO_CONVERT_EXT) {
 		ret = ext4_convert_unwritten_extents_dio(handle, inode,
 							path);
+		if (ret >= 0)
+			ext4_update_inode_fsync_trans(handle, inode, 1);
 		goto out2;
 	}
 	/* buffered IO case */
@@ -3091,6 +3095,8 @@ ext4_ext_handle_uninitialized_extents(handle_t *handle, struct inode *inode,
 	ret = ext4_ext_convert_to_initialized(handle, inode,
 						path, iblock,
 						max_blocks);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 out:
 	if (ret <= 0) {
 		err = ret;
@@ -3329,10 +3335,16 @@ int ext4_ext_get_blocks(handle_t *handle, struct inode *inode,
 	allocated = ext4_ext_get_actual_len(&newex);
 	set_buffer_new(bh_result);
 
-	/* Cache only when it is _not_ an uninitialized extent */
-	if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0)
+	/*
+	 * Cache the extent and update transaction to commit on fdatasync only
+	 * when it is _not_ an uninitialized extent.
+	 */
+	if ((flags & EXT4_GET_BLOCKS_UNINIT_EXT) == 0) {
 		ext4_ext_put_in_cache(inode, iblock, allocated, newblock,
 						EXT4_EXT_CACHE_EXTENT);
+		ext4_update_inode_fsync_trans(handle, inode, 1);
+	} else
+		ext4_update_inode_fsync_trans(handle, inode, 0);
 out:
 	if (allocated > max_blocks)
 		allocated = max_blocks;
@@ -3720,10 +3732,8 @@ int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		 * Walk the extent tree gathering extent information.
 		 * ext4_ext_fiemap_cb will push extents back to user.
 		 */
-		down_read(&EXT4_I(inode)->i_data_sem);
 		error = ext4_ext_walk_space(inode, start_blk, len_blks,
 					  ext4_ext_fiemap_cb, fieinfo);
-		up_read(&EXT4_I(inode)->i_data_sem);
 	}
 
 	return error;
fs/ext4/fsync.c +20 -34

77 lines not on this page · raw message

fs/ext4/inode.c +57 -24

223 lines not on this page · raw message

fs/ext4/ioctl.c +18 -11
index c1cdf61..b63d193 100644
@@ -221,31 +221,38 @@ setversion_out:
 		struct file *donor_filp;
 		int err;
 
+		if (!(filp->f_mode & FMODE_READ) ||
+		    !(filp->f_mode & FMODE_WRITE))
+			return -EBADF;
+
 		if (copy_from_user(&me,
 			(struct move_extent __user *)arg, sizeof(me)))
 			return -EFAULT;
+		me.moved_len = 0;
 
 		donor_filp = fget(me.donor_fd);
 		if (!donor_filp)
 			return -EBADF;
 
-		if (!capable(CAP_DAC_OVERRIDE)) {
-			if ((current->real_cred->fsuid != inode->i_uid) ||
-				!(inode->i_mode & S_IRUSR) ||
-				!(donor_filp->f_dentry->d_inode->i_mode &
-				S_IRUSR)) {
-				fput(donor_filp);
-				return -EACCES;
-			}
+		if (!(donor_filp->f_mode & FMODE_WRITE)) {
+			err = -EBADF;
+			goto mext_out;
 		}
 
+		err = mnt_want_write(filp->f_path.mnt);
+		if (err)
+			goto mext_out;
+
 		err = ext4_move_extents(filp, donor_filp, me.orig_start,
 					me.donor_start, me.len, &me.moved_len);
-		fput(donor_filp);
+		mnt_drop_write(filp->f_path.mnt);
+		if (me.moved_len > 0)
+			file_remove_suid(donor_filp);
 
 		if (copy_to_user((struct move_extent *)arg, &me, sizeof(me)))
-			return -EFAULT;
-
+			err = -EFAULT;
+mext_out:
+		fput(donor_filp);
 		return err;
 	}
 
fs/ext4/mballoc.c +32 -8
index bba1282..7d71148 100644
@@ -2529,7 +2529,6 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 	struct ext4_group_info *db;
 	int err, count = 0, count2 = 0;
 	struct ext4_free_data *entry;
-	ext4_fsblk_t discard_block;
 	struct list_head *l, *ltmp;
 
 	list_for_each_safe(l, ltmp, &txn->t_private_list) {
@@ -2559,13 +2558,19 @@ static void release_blocks_on_commit(journal_t *journal, transaction_t *txn)
 			page_cache_release(e4b.bd_bitmap_page);
 		}
 		ext4_unlock_group(sb, entry->group);
-		discard_block = (ext4_fsblk_t) entry->group * EXT4_BLOCKS_PER_GROUP(sb)
-			+ entry->start_blk
-			+ le32_to_cpu(EXT4_SB(sb)->s_es->s_first_data_block);
-		trace_ext4_discard_blocks(sb, (unsigned long long)discard_block,
-					  entry->count);
-		sb_issue_discard(sb, discard_block, entry->count);
-
+		if (test_opt(sb, DISCARD)) {
+			ext4_fsblk_t discard_block;
+			struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+
+			discard_block = (ext4_fsblk_t)entry->group *
+						EXT4_BLOCKS_PER_GROUP(sb)
+					+ entry->start_blk
+					+ le32_to_cpu(es->s_first_data_block);
+			trace_ext4_discard_blocks(sb,
+					(unsigned long long)discard_block,
+					entry->count);
+			sb_issue_discard(sb, discard_block, entry->count);
+		}
 		kmem_cache_free(ext4_free_ext_cachep, entry);
 		ext4_mb_release_desc(&e4b);
 	}
@@ -3006,6 +3011,24 @@ static void ext4_mb_collect_stats(struct ext4_allocation_context *ac)
 }
 
 /*
+ * Called on failure; free up any blocks from the inode PA for this
+ * context.  We don't need this for MB_GROUP_PA because we only change
+ * pa_free in ext4_mb_release_context(), but on failure, we've already
+ * zeroed out ac->ac_b_ex.fe_len, so group_pa->pa_free is not changed.
+ */
+static void ext4_discard_allocated_blocks(struct ext4_allocation_context *ac)
+{
+	struct ext4_prealloc_space *pa = ac->ac_pa;
+	int len;
+
+	if (pa && pa->pa_type == MB_INODE_PA) {
+		len = ac->ac_b_ex.fe_len;
+		pa->pa_free += len;
+	}
+
+}
+
+/*
  * use blocks preallocated to inode
  */
 static void ext4_mb_use_inode_pa(struct ext4_allocation_context *ac,
@@ -4290,6 +4313,7 @@ repeat:
 			ac->ac_status = AC_STATUS_CONTINUE;
 			goto repeat;
 		} else if (*errp) {
+			ext4_discard_allocated_blocks(ac);
 			ac->ac_b_ex.fe_len = 0;
 			ar->len = 0;
 			ext4_mb_show_ac(ac);
fs/ext4/migrate.c +2 -2
index a93d5b8..8646149 100644
@@ -238,7 +238,7 @@ static int extend_credit_for_blkdel(handle_t *handle, struct inode *inode)
 	 * So allocate a credit of 3. We may update
 	 * quota (user and group).
 	 */
-	needed = 3 + 2*EXT4_QUOTA_TRANS_BLOCKS(inode->i_sb);
+	needed = 3 + EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb);
 
 	if (ext4_journal_extend(handle, needed) != 0)
 		retval = ext4_journal_restart(handle, needed);
@@ -477,7 +477,7 @@ int ext4_ext_migrate(struct inode *inode)
 	handle = ext4_journal_start(inode,
 					EXT4_DATA_TRANS_BLOCKS(inode->i_sb) +
 					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
-					2 * EXT4_QUOTA_INIT_BLOCKS(inode->i_sb)
+					EXT4_MAXQUOTAS_INIT_BLOCKS(inode->i_sb)
 					+ 1);
 	if (IS_ERR(handle)) {
 		retval = PTR_ERR(handle);
fs/ext4/move_extent.c +131 -147

556 lines not on this page · raw message

fs/ext4/namei.c +16 -22
index 6d2c1b8..17a17e1 100644
@@ -1292,9 +1292,6 @@ errout:
  * add_dirent_to_buf will attempt search the directory block for
  * space.  It will return -ENOSPC if no space is available, and -EIO
  * and -EEXIST if directory entry already exists.
- *
- * NOTE!  bh is NOT released in the case where ENOSPC is returned.  In
- * all other cases bh is released.
  */
 static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 			     struct inode *inode, struct ext4_dir_entry_2 *de,
@@ -1315,14 +1312,10 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 		top = bh->b_data + blocksize - reclen;
 		while ((char *) de <= top) {
 			if (!ext4_check_dir_entry("ext4_add_entry", dir, de,
-						  bh, offset)) {
-				brelse(bh);
+						  bh, offset))
 				return -EIO;
-			}
-			if (ext4_match(namelen, name, de)) {
-				brelse(bh);
+			if (ext4_match(namelen, name, de))
 				return -EEXIST;
-			}
 			nlen = EXT4_DIR_REC_LEN(de->name_len);
 			rlen = ext4_rec_len_from_disk(de->rec_len, blocksize);
 			if ((de->inode? rlen - nlen: rlen) >= reclen)
@@ -1337,7 +1330,6 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 	err = ext4_journal_get_write_access(handle, bh);
 	if (err) {
 		ext4_std_error(dir->i_sb, err);
-		brelse(bh);
 		return err;
 	}
 
@@ -1377,7 +1369,6 @@ static int add_dirent_to_buf(handle_t *handle, struct dentry *dentry,
 	err = ext4_handle_dirty_metadata(handle, dir, bh);
 	if (err)
 		ext4_std_error(dir->i_sb, err);
-	brelse(bh);
 	return 0;
 }
 
@@ -1471,7 +1462,9 @@ static int make_indexed_dir(handle_t *handle, struct dentry *dentry,
 	if (!(de))
 		return retval;
 
-	return add_dirent_to_buf(handle, dentry, inode, de, bh);
+	retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+	brelse(bh);
+	return retval;
 }
 
 /*
@@ -1514,8 +1507,10 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 		if(!bh)
 			return retval;
 		retval = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
-		if (retval != -ENOSPC)
+		if (retval != -ENOSPC) {
+			brelse(bh);
 			return retval;
+		}
 
 		if (blocks == 1 && !dx_fallback &&
 		    EXT4_HAS_COMPAT_FEATURE(sb, EXT4_FEATURE_COMPAT_DIR_INDEX))
@@ -1528,7 +1523,9 @@ static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
 	de = (struct ext4_dir_entry_2 *) bh->b_data;
 	de->inode = 0;
 	de->rec_len = ext4_rec_len_to_disk(blocksize, blocksize);
-	return add_dirent_to_buf(handle, dentry, inode, de, bh);
+	retval = add_dirent_to_buf(handle, dentry, inode, de, bh);
+	brelse(bh);
+	return retval;
 }
 
 /*
@@ -1561,10 +1558,8 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 		goto journal_error;
 
 	err = add_dirent_to_buf(handle, dentry, inode, NULL, bh);
-	if (err != -ENOSPC) {
-		bh = NULL;
+	if (err != -ENOSPC)
 		goto cleanup;
-	}
 
 	/* Block full, should compress but for now just split */
 	dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n",
@@ -1657,7 +1652,6 @@ static int ext4_dx_add_entry(handle_t *handle, struct dentry *dentry,
 	if (!de)
 		goto cleanup;
 	err = add_dirent_to_buf(handle, dentry, inode, de, bh);
-	bh = NULL;
 	goto cleanup;
 
 journal_error:
@@ -1775,7 +1769,7 @@ static int ext4_create(struct inode *dir, struct dentry *dentry, int mode,
 retry:
 	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
-					2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+					EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
@@ -1809,7 +1803,7 @@ static int ext4_mknod(struct inode *dir, struct dentry *dentry,
 retry:
 	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
-					2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+					EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
@@ -1846,7 +1840,7 @@ static int ext4_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 retry:
 	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3 +
-					2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+					EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
@@ -2259,7 +2253,7 @@ static int ext4_symlink(struct inode *dir,
 retry:
 	handle = ext4_journal_start(dir, EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
 					EXT4_INDEX_EXTRA_TRANS_BLOCKS + 5 +
-					2*EXT4_QUOTA_INIT_BLOCKS(dir->i_sb));
+					EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb));
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
fs/ext4/resize.c +1 -1
index 3cfc343..3b2c554 100644
@@ -247,7 +247,7 @@ static int setup_new_group_blocks(struct super_block *sb,
 			goto exit_bh;
 
 		if (IS_ERR(gdb = bclean(handle, sb, block))) {
-			err = PTR_ERR(bh);
+			err = PTR_ERR(gdb);
 			goto exit_bh;
 		}
 		ext4_handle_dirty_metadata(handle, NULL, gdb);
fs/ext4/super.c +29 -11
index d4ca92a..9ae5217 100644
@@ -603,10 +603,6 @@ static void ext4_put_super(struct super_block *sb)
 	if (sb->s_dirt)
 		ext4_commit_super(sb, 1);
 
-	ext4_release_system_zone(sb);
-	ext4_mb_release(sb);
-	ext4_ext_release(sb);
-	ext4_xattr_put_super(sb);
 	if (sbi->s_journal) {
 		err = jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
@@ -614,6 +610,12 @@ static void ext4_put_super(struct super_block *sb)
 			ext4_abort(sb, __func__,
 				   "Couldn't clean up the journal");
 	}
+
+	ext4_release_system_zone(sb);
+	ext4_mb_release(sb);
+	ext4_ext_release(sb);
+	ext4_xattr_put_super(sb);
+
 	if (!(sb->s_flags & MS_RDONLY)) {
 		EXT4_CLEAR_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_RECOVER);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
@@ -704,6 +706,8 @@ static struct inode *ext4_alloc_inode(struct super_block *sb)
 	spin_lock_init(&(ei->i_block_reservation_lock));
 	INIT_LIST_HEAD(&ei->i_aio_dio_complete_list);
 	ei->cur_aio_dio = NULL;
+	ei->i_sync_tid = 0;
+	ei->i_datasync_tid = 0;
 
 	return &ei->vfs_inode;
 }
@@ -899,6 +903,12 @@ static int ext4_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	if (test_opt(sb, NO_AUTO_DA_ALLOC))
 		seq_puts(seq, ",noauto_da_alloc");
 
+	if (test_opt(sb, DISCARD))
+		seq_puts(seq, ",discard");
+
+	if (test_opt(sb, NOLOAD))
+		seq_puts(seq, ",norecovery");
+
 	ext4_show_quota_options(seq, sb);
 
 	return 0;
@@ -1079,7 +1089,8 @@ enum {
 	Opt_usrquota, Opt_grpquota, Opt_i_version,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc,
 	Opt_block_validity, Opt_noblock_validity,
-	Opt_inode_readahead_blks, Opt_journal_ioprio
+	Opt_inode_readahead_blks, Opt_journal_ioprio,
+	Opt_discard, Opt_nodiscard,
 };
 
 static const match_table_t tokens = {
@@ -1104,6 +1115,7 @@ static const match_table_t tokens = {
 	{Opt_acl, "acl"},
 	{Opt_noacl, "noacl"},
 	{Opt_noload, "noload"},
+	{Opt_noload, "norecovery"},
 	{Opt_nobh, "nobh"},
 	{Opt_bh, "bh"},
 	{Opt_commit, "commit=%u"},
@@ -1144,6 +1156,8 @@ static const match_table_t tokens = {
 	{Opt_auto_da_alloc, "auto_da_alloc=%u"},
 	{Opt_auto_da_alloc, "auto_da_alloc"},
 	{Opt_noauto_da_alloc, "noauto_da_alloc"},
+	{Opt_discard, "discard"},
+	{Opt_nodiscard, "nodiscard"},
 	{Opt_err, NULL},
 };
 
@@ -1565,6 +1579,12 @@ set_qf_format:
 			else
 				set_opt(sbi->s_mount_opt,NO_AUTO_DA_ALLOC);
 			break;
+		case Opt_discard:
+			set_opt(sbi->s_mount_opt, DISCARD);
+			break;
+		case Opt_nodiscard:
+			clear_opt(sbi->s_mount_opt, DISCARD);
+			break;
 		default:
 			ext4_msg(sb, KERN_ERR,
 			       "Unrecognized mount option \"%s\" "
@@ -1673,14 +1693,14 @@ static int ext4_fill_flex_info(struct super_block *sb)
 	size_t size;
 	int i;
 
-	if (!sbi->s_es->s_log_groups_per_flex) {
+	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
+	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
+
+	if (groups_per_flex < 2) {
 		sbi->s_log_groups_per_flex = 0;
 		return 1;
 	}
 
-	sbi->s_log_groups_per_flex = sbi->s_es->s_log_groups_per_flex;
-	groups_per_flex = 1 << sbi->s_log_groups_per_flex;
-
 	/* We allocate both existing and potentially added groups */
 	flex_group_count = ((sbi->s_groups_count + groups_per_flex - 1) +
 			((le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks) + 1) <<
@@ -3668,13 +3688,11 @@ static int ext4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks = ext4_blocks_count(es) - sbi->s_overhead_last;
 	buf->f_bfree = percpu_counter_sum_positive(&sbi->s_freeblocks_counter) -
 		       percpu_counter_sum_positive(&sbi->s_dirtyblocks_counter);
-	ext4_free_blocks_count_set(es, buf->f_bfree);
 	buf->f_bavail = buf->f_bfree - ext4_r_blocks_count(es);
 	if (buf->f_bfree < ext4_r_blocks_count(es))
 		buf->f_bavail = 0;
 	buf->f_files = le32_to_cpu(es->s_inodes_count);
 	buf->f_ffree = percpu_counter_sum_positive(&sbi->s_freeinodes_counter);
-	es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
 	buf->f_namelen = EXT4_NAME_LEN;
 	fsid = le64_to_cpup((void *)es->s_uuid) ^
 	       le64_to_cpup((void *)es->s_uuid + sizeof(u64));
fs/ext4/xattr.c +4 -3
index fed5b01..0257019 100644
@@ -988,6 +988,10 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 	if (error)
 		goto cleanup;
 
+	error = ext4_journal_get_write_access(handle, is.iloc.bh);
+	if (error)
+		goto cleanup;
+
 	if (EXT4_I(inode)->i_state & EXT4_STATE_NEW) {
 		struct ext4_inode *raw_inode = ext4_raw_inode(&is.iloc);
 		memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
@@ -1013,9 +1017,6 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		if (flags & XATTR_CREATE)
 			goto cleanup;
 	}
-	error = ext4_journal_get_write_access(handle, is.iloc.bh);
-	if (error)
-		goto cleanup;
 	if (!value) {
 		if (!is.s.not_found)
 			error = ext4_xattr_ibody_set(handle, inode, &i, &is);
fs/jbd2/commit.c +4 -0
index d4cfd6d..8896c1d 100644
@@ -636,6 +636,10 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 		JBUFFER_TRACE(jh, "ph3: write metadata");
 		flags = jbd2_journal_write_metadata_buffer(commit_transaction,
 						      jh, &new_jh, blocknr);
+		if (flags < 0) {
+			jbd2_journal_abort(journal, flags);
+			continue;
+		}
 		set_bit(BH_JWrite, &jh2bh(new_jh)->b_state);
 		wbuf[bufs++] = jh2bh(new_jh);
 
fs/jbd2/journal.c +5 -0
index fed8538..82c295d 100644
@@ -78,6 +78,7 @@ EXPORT_SYMBOL(jbd2_journal_errno);
 EXPORT_SYMBOL(jbd2_journal_ack_err);
 EXPORT_SYMBOL(jbd2_journal_clear_err);
 EXPORT_SYMBOL(jbd2_log_wait_commit);
+EXPORT_SYMBOL(jbd2_log_start_commit);
 EXPORT_SYMBOL(jbd2_journal_start_commit);
 EXPORT_SYMBOL(jbd2_journal_force_commit_nested);
 EXPORT_SYMBOL(jbd2_journal_wipe);
@@ -358,6 +359,10 @@ repeat:
 
 		jbd_unlock_bh_state(bh_in);
 		tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
+		if (!tmp) {
+			jbd2_journal_put_journal_head(new_jh);
+			return -ENOMEM;
+		}
 		jbd_lock_bh_state(bh_in);
 		if (jh_in->b_frozen_data) {
 			jbd2_free(tmp, bh_in->b_size);
include/linux/sched.h +10 -3
index 75e6e60..0f67914 100644
@@ -2086,11 +2086,18 @@ static inline int is_si_special(const struct siginfo *info)
 	return info <= SEND_SIG_FORCED;
 }
 
-/* True if we are on the alternate signal stack.  */
-
+/*
+ * True if we are on the alternate signal stack.
+ */
 static inline int on_sig_stack(unsigned long sp)
 {
-	return (sp - current->sas_ss_sp < current->sas_ss_size);
+#ifdef CONFIG_STACK_GROWSUP
+	return sp >= current->sas_ss_sp &&
+		sp - current->sas_ss_sp < current->sas_ss_size;
+#else
+	return sp > current->sas_ss_sp &&
+		sp - current->sas_ss_sp <= current->sas_ss_size;
+#endif
 }
 
 static inline int sas_ss_flags(unsigned long sp)
include/scsi/osd_protocol.h +1 -0
index 2cc8e8b..6856612 100644
@@ -17,6 +17,7 @@
 #define __OSD_PROTOCOL_H__
 
 #include <linux/types.h>
+#include <linux/kernel.h>
 #include <asm/unaligned.h>
 #include <scsi/scsi.h>
 
include/scsi/scsi_host.h +15 -1
index 47941fc..0b4baba 100644
@@ -677,6 +677,12 @@ struct Scsi_Host {
 	void *shost_data;
 
 	/*
+	 * Points to the physical bus device we'd use to do DMA
+	 * Needed just in case we have virtual hosts.
+	 */
+	struct device *dma_dev;
+
+	/*
 	 * We should ensure that this is aligned, both for better performance
 	 * and also because some compilers (m68k) don't automatically force
 	 * alignment to a long boundary.
@@ -720,7 +726,9 @@ extern int scsi_queue_work(struct Scsi_Host *, struct work_struct *);
 extern void scsi_flush_work(struct Scsi_Host *);
 
 extern struct Scsi_Host *scsi_host_alloc(struct scsi_host_template *, int);
-extern int __must_check scsi_add_host(struct Scsi_Host *, struct device *);
+extern int __must_check scsi_add_host_with_dma(struct Scsi_Host *,
+					       struct device *,
+					       struct device *);
 extern void scsi_scan_host(struct Scsi_Host *);
 extern void scsi_rescan_device(struct device *);
 extern void scsi_remove_host(struct Scsi_Host *);
@@ -731,6 +739,12 @@ extern const char *scsi_host_state_name(enum scsi_host_state);
 
 extern u64 scsi_calculate_bounce_limit(struct Scsi_Host *);
 
+static inline int __must_check scsi_add_host(struct Scsi_Host *host,
+					     struct device *dev)
+{
+	return scsi_add_host_with_dma(host, dev, dev);
+}
+
 static inline struct device *scsi_get_device(struct Scsi_Host *shost)
 {
         return shost->shost_gendev.parent;

Greg KH

author
#0 lore raw

I'm announcing the release of the 2.6.32.1 kernel. All users of the 2.6.32 kernel series are very strongly encouraged to upgrade.

I'll also be replying to this message with a copy of the patch between 2.6.32 and 2.6.32.1

The updated 2.6.32.y git tree can be found at:

        git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-2.6.32.y.git
and can be browsed at the normal kernel.org git web browser:
        http://git.kernel.org/?p=linux/kernel/git/stable/linux-2.6.32.y.git;a=summary

thanks,

greg k-h

------------

 Documentation/filesystems/ext4.txt   |   10 +
 Makefile                             |    2 
 drivers/scsi/hosts.c                 |   13 +
 drivers/scsi/lpfc/lpfc_init.c        |    2 
 drivers/scsi/megaraid/megaraid_sas.c |    8 -
 drivers/scsi/qla2xxx/qla_attr.c      |    3 
 drivers/scsi/scsi_lib_dma.c          |    4 
 fs/ext4/balloc.c                     |    8 -
 fs/ext4/block_validity.c             |    2 
 fs/ext4/ext4.h                       |    8 +
 fs/ext4/ext4_jbd2.h                  |   21 ++
 fs/ext4/extents.c                    |   22 ++
 fs/ext4/fsync.c                      |   54 ++----
 fs/ext4/inode.c                      |   81 +++++++---
 fs/ext4/ioctl.c                      |   29 ++-
 fs/ext4/mballoc.c                    |   40 ++++-
 fs/ext4/migrate.c                    |    4 
 fs/ext4/move_extent.c                |  278 ++++++++++++++++-------------------
 fs/ext4/namei.c                      |   38 ++--
 fs/ext4/resize.c                     |    2 
 fs/ext4/super.c                      |   40 +++--
 fs/ext4/xattr.c                      |    7 
 fs/jbd2/commit.c                     |    4 
 fs/jbd2/journal.c                    |    5 
 include/linux/sched.h                |   13 +
 include/scsi/osd_protocol.h          |    1 
 include/scsi/scsi_host.h             |   16 +-
 27 files changed, 424 insertions(+), 291 deletions(-)

Akira Fujita (6):
ext4: fix the returned block count if EXT4_IOC_MOVE_EXT fails
ext4: fix lock order problem in ext4_move_extents()
ext4: fix possible recursive locking warning in EXT4_IOC_MOVE_EXT
ext4: Fix double-free of blocks with EXT4_IOC_MOVE_EXT
ext4: move_extent_per_page() cleanup
ext4: Fix insufficient checks in EXT4_IOC_MOVE_EXT

Curt Wohlgemuth (1):
ext4: remove blocks from inode prealloc list on failure

Dmitry Monakhov (3):
ext4: ext4_get_reserved_space() must return bytes instead of blocks
ext4: quota macros cleanup
ext4: fix incorrect block reservation on quota transfer.

Eric Sandeen (3):
ext4: journal all modifications in ext4_xattr_set_handle
ext4: make trim/discard optional (and off by default)
ext4: make "norecovery" an alias for "noload"

Greg Kroah-Hartman (1):

      Linux 2.6.32.1

James Bottomley (1):
SCSI: scsi_lib_dma: fix bug with dma maps on nested scsi objects

Jan Kara (3):
ext4: fix error handling in ext4_ind_get_blocks()
ext4: Avoid data / filesystem corruption when write fails to copy data
ext4: Wait for proper transaction commit on fsync

Josef Bacik (1):
ext4: wait for log to commit when umounting

Julia Lawall (1):
ext4: fix i_flags access in ext4_da_writepages_trans_blocks()

Kazuya Mio (1):
ext4: initialize moved_len before calling ext4_move_extents()

Martin Michlmayr (1):
SCSI: osd_protocol.h: Add missing #include

Roel Kluin (1):
ext4: Return the PTR_ERR of the correct pointer in setup_new_group_blocks()

Sebastian Andrzej Siewior (1):
signal: Fix alternate signal stack check

Theodore Ts'o (10):
ext4: fix potential buffer head leak when add_dirent_to_buf() returns ENOSPC
ext4: avoid divide by zero when trying to mount a corrupted file system
ext4: plug a buffer_head leak in an error path of ext4_iget()
ext4: make sure directory and symlink blocks are revoked
ext4: don't update the superblock in ext4_statfs()
ext4: fix uninit block bitmap initialization when s_meta_first_bg is non-zero
ext4: fix block validity checks so they work correctly with meta_bg
ext4: avoid issuing unnecessary barriers
jbd2: Add ENOMEM checking in and for jbd2_journal_write_metadata_buffer()
ext4: Fix potential fiemap deadlock (mmap_sem vs. i_data_sem)

Yang, Bo (1):
SCSI: megaraid_sas: fix 64 bit sense pointer truncation