2.6.27.19-stable review

@@ -123,6 +123,24 @@ extern struct pid *alloc_pid(struct pid_
 extern void free_pid(struct pid *pid);
 
 /*
+ * ns_of_pid() returns the pid namespace in which the specified pid was
+ * allocated.
+ *
+ * NOTE:
+ * 	ns_of_pid() is expected to be called for a process (task) that has
+ * 	an attached 'struct pid' (see attach_pid(), detach_pid()) i.e @pid
+ * 	is expected to be non-NULL. If @pid is NULL, caller should handle
+ * 	the resulting NULL pid-ns.
+ */
+static inline struct pid_namespace *ns_of_pid(struct pid *pid)
+{
+	struct pid_namespace *ns = NULL;
+	if (pid)
+		ns = pid->numbers[pid->level].ns;
+	return ns;
+}
+
+/*
  * the helpers to get the pid's id seen from different namespaces
  *
  * pid_nr()    : global id, i.e. the id seen from the init namespace;

@@ -498,7 +498,8 @@ static void __do_notify(struct mqueue_in
 			sig_i.si_errno = 0;
 			sig_i.si_code = SI_MESGQ;
 			sig_i.si_value = info->notify.sigev_value;
-			sig_i.si_pid = task_tgid_vnr(current);
+			sig_i.si_pid = task_tgid_nr_ns(current,
+						ns_of_pid(info->notify_owner));
 			sig_i.si_uid = current->uid;
 
 			kill_pid_info(info->notify.sigev_signo,

@@ -527,7 +527,7 @@ static void iommu_flush_write_buffer(str
 	u32 val;
 	unsigned long flag;
 
-	if (!cap_rwbf(iommu->cap))
+	if (!rwbf_quirk && !cap_rwbf(iommu->cap))
 		return;
 	val = iommu->gcmd | DMA_GCMD_WBF;
 

@@ -1410,6 +1410,8 @@ static void domain_remove_dev_info(struc
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
 
+static int rwbf_quirk = 0;
+
 /*
  * find_domain
  * Note: we use struct pci_dev->dev.archdata.iommu stores the info

@@ -2453,3 +2455,12 @@ int __init intel_iommu_init(void)
 	return 0;
 }
 
+static void __devinit quirk_iommu_rwbf(struct pci_dev *dev)
+{
+	/* Mobile 4 Series Chipset neglects to set RWBF capability,
+	   but needs it */
+	printk(KERN_INFO "DMAR: Forcing write-buffer flush capability\n");
+	rwbf_quirk = 1;
+}
+
+DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2a40, quirk_iommu_rwbf);

@@ -72,6 +72,8 @@ static struct deferred_flush_tables *def
 /* bitmap for indexing intel_iommus */
 static int g_num_of_iommus;
 
+static int rwbf_quirk = 0;
+
 static DEFINE_SPINLOCK(async_umap_flush_lock);
 static LIST_HEAD(unmaps_to_do);
 

@@ -1410,8 +1412,6 @@ static void domain_remove_dev_info(struc
 	spin_unlock_irqrestore(&device_domain_lock, flags);
 }
 
-static int rwbf_quirk = 0;
-
 /*
  * find_domain
  * Note: we use struct pci_dev->dev.archdata.iommu stores the info

@@ -646,11 +646,16 @@ static int emulate_vsx(unsigned char __u
 		       unsigned int areg, struct pt_regs *regs,
 		       unsigned int flags, unsigned int length)
 {
-	char *ptr = (char *) &current->thread.TS_FPR(reg);
+	char *ptr;
 	int ret = 0;
 
 	flush_vsx_to_thread(current);
 
+	if (reg < 32)
+		ptr = (char *) &current->thread.TS_FPR(reg);
+	else
+		ptr = (char *) &current->thread.vr[reg - 32];
+
 	if (flags & ST)
 		ret = __copy_to_user(addr, ptr, length);
         else {

@@ -421,19 +421,21 @@ static struct ata_port_operations nv_gen
 	.hardreset		= ATA_OP_NULL,
 };
 
-/* OSDL bz3352 reports that nf2/3 controllers can't determine device
- * signature reliably.  Also, the following thread reports detection
- * failure on cold boot with the standard debouncing timing.
+/* nf2 is ripe with hardreset related problems.
+ *
+ * kernel bz#3352 reports nf2/3 controllers can't determine device
+ * signature reliably.  The following thread reports detection failure
+ * on cold boot with the standard debouncing timing.
  *
  * http://thread.gmane.org/gmane.linux.ide/34098
  *
- * Debounce with hotplug timing and request follow-up SRST.
+ * And bz#12176 reports that hardreset simply doesn't work on nf2.
+ * Give up on it and just don't do hardreset.
  */
 static struct ata_port_operations nv_nf2_ops = {
-	.inherits		= &nv_common_ops,
+	.inherits		= &nv_generic_ops,
 	.freeze			= nv_nf2_freeze,
 	.thaw			= nv_nf2_thaw,
-	.hardreset		= nv_noclassify_hardreset,
 };
 
 /* For initial probing after boot and hot plugging, hardreset mostly

@@ -493,21 +493,27 @@ static bool receive_pcb(struct net_devic
 	}
 	/* read the data */
 	spin_lock_irqsave(&adapter->lock, flags);
-	i = 0;
-	do {
-		j = 0;
-		while (((stat = get_status(dev->base_addr)) & ACRF) == 0 && j++ < 20000);
-		pcb->data.raw[i++] = inb_command(dev->base_addr);
-		if (i > MAX_PCB_DATA)
-			INVALID_PCB_MSG(i);
-	} while ((stat & ASF_PCB_MASK) != ASF_PCB_END && j < 20000);
+	for (i = 0; i < MAX_PCB_DATA; i++) {
+		for (j = 0; j < 20000; j++) {
+			stat = get_status(dev->base_addr);
+			if (stat & ACRF)
+				break;
+		}
+		pcb->data.raw[i] = inb_command(dev->base_addr);
+		if ((stat & ASF_PCB_MASK) == ASF_PCB_END || j >= 20000)
+			break;
+	}
 	spin_unlock_irqrestore(&adapter->lock, flags);
+	if (i >= MAX_PCB_DATA) {
+		INVALID_PCB_MSG(i);
+		return false;
+	}
 	if (j >= 20000) {
 		TIMEOUT_MSG(__LINE__);
 		return false;
 	}
-	/* woops, the last "data" byte was really the length! */
-	total_length = pcb->data.raw[--i];
+	/* the last "data" byte was really the length! */
+	total_length = pcb->data.raw[i];
 
 	/* safety check total length vs data length */
 	if (total_length != (pcb->length + 2)) {

@@ -111,7 +111,8 @@ static const struct via_isa_bridge {
 	{ "vt8237s",	PCI_DEVICE_ID_VIA_8237S,    0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
 	{ "vt8251",	PCI_DEVICE_ID_VIA_8251,     0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
 	{ "cx700",	PCI_DEVICE_ID_VIA_CX700,    0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST | VIA_SATA_PATA },
-	{ "vt6410",	PCI_DEVICE_ID_VIA_6410,     0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST | VIA_NO_ENABLES},
+	{ "vt6410",	PCI_DEVICE_ID_VIA_6410,     0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST | VIA_NO_ENABLES },
+	{ "vt6415",	PCI_DEVICE_ID_VIA_6415,     0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST | VIA_NO_ENABLES },
 	{ "vt8237a",	PCI_DEVICE_ID_VIA_8237A,    0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
 	{ "vt8237",	PCI_DEVICE_ID_VIA_8237,     0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },
 	{ "vt8235",	PCI_DEVICE_ID_VIA_8235,     0x00, 0x2f, VIA_UDMA_133 | VIA_BAD_AST },

@@ -594,6 +595,7 @@ static int via_reinit_one(struct pci_dev
 #endif
 
 static const struct pci_device_id via[] = {
+	{ PCI_VDEVICE(VIA, 0x0415), },
 	{ PCI_VDEVICE(VIA, 0x0571), },
 	{ PCI_VDEVICE(VIA, 0x0581), },
 	{ PCI_VDEVICE(VIA, 0x1571), },

@@ -1301,6 +1301,7 @@
 #define PCI_DEVICE_ID_VIA_VT3351	0x0351
 #define PCI_DEVICE_ID_VIA_VT3364	0x0364
 #define PCI_DEVICE_ID_VIA_8371_0	0x0391
+#define PCI_DEVICE_ID_VIA_6415		0x0415
 #define PCI_DEVICE_ID_VIA_8501_0	0x0501
 #define PCI_DEVICE_ID_VIA_82C561	0x0561
 #define PCI_DEVICE_ID_VIA_82C586_1	0x0571

@@ -91,6 +91,7 @@ static int btsdio_tx_packet(struct btsdi
 
 	err = sdio_writesb(data->func, REG_TDAT, skb->data, skb->len);
 	if (err < 0) {
+		skb_pull(skb, 4);
 		sdio_writeb(data->func, 0x01, REG_PC_WRT, NULL);
 		return err;
 	}

@@ -153,7 +153,7 @@ static int btsdio_rx_packet(struct btsdi
 
 	err = sdio_readsb(data->func, skb->data, REG_RDAT, len - 4);
 	if (err < 0) {
-		kfree(skb);
+		kfree_skb(skb);
 		return err;
 	}
 

@@ -1177,9 +1177,12 @@ static int ext2_remount (struct super_bl
 	es = sbi->s_es;
 	if (((sbi->s_mount_opt & EXT2_MOUNT_XIP) !=
 	    (old_mount_opt & EXT2_MOUNT_XIP)) &&
-	    invalidate_inodes(sb))
-		ext2_warning(sb, __func__, "busy inodes while remounting "\
-			     "xip remain in cache (no functional problem)");
+	    invalidate_inodes(sb)) {
+		ext2_warning(sb, __func__, "refusing change of xip flag "
+			     "with busy inodes while remounting");
+		sbi->s_mount_opt &= ~EXT2_MOUNT_XIP;
+		sbi->s_mount_opt |= old_mount_opt & EXT2_MOUNT_XIP;
+	}
 	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
 		return 0;
 	if (*flags & MS_RDONLY) {

@@ -1844,6 +1844,7 @@ void iscsi_pool_free(struct iscsi_pool *
 		kfree(q->pool[i]);
 	if (q->pool)
 		kfree(q->pool);
+	kfree(q->queue);
 }
 EXPORT_SYMBOL_GPL(iscsi_pool_free);
 

@@ -619,6 +619,13 @@ static int __change_page_attr(struct cpa
 	unsigned int level;
 	pte_t *kpte, old_pte;
 
+	/*
+	 * If we're called with lazy mmu updates enabled, the
+	 * in-memory pte state may be stale.  Flush pending updates to
+	 * bring them up to date.
+	 */
+	arch_flush_lazy_mmu_mode();
+
 repeat:
 	kpte = lookup_address(address, &level);
 	if (!kpte)

@@ -836,6 +843,13 @@ static int change_page_attr_set_clr(unsi
 	else
 		cpa_flush_all(cache);
 
+	/*
+	 * If we've been called with lazy mmu updates enabled, then
+	 * make sure that everything gets flushed out before we
+	 * return.
+	 */
+	arch_flush_lazy_mmu_mode();
+
 out:
 	cpa_fill_pool(NULL);
 

@@ -889,6 +889,9 @@ static inline __le16 ext4_rec_len_to_dis
 #define DX_HASH_LEGACY		0
 #define DX_HASH_HALF_MD4	1
 #define DX_HASH_TEA		2
+#define DX_HASH_LEGACY_UNSIGNED	3
+#define DX_HASH_HALF_MD4_UNSIGNED	4
+#define DX_HASH_TEA_UNSIGNED		5
 
 #ifdef __KERNEL__
 

@@ -56,6 +56,7 @@ struct ext4_sb_info {
 	u32 s_next_generation;
 	u32 s_hash_seed[4];
 	int s_def_hash_version;
+	int s_hash_unsigned;	/* 3 if hash should be signed, 0 if not */
 	struct percpu_counter s_freeblocks_counter;
 	struct percpu_counter s_freeinodes_counter;
 	struct percpu_counter s_dirs_counter;

126 lines not on this page · raw message

@@ -371,6 +371,8 @@ dx_probe(struct dentry *dentry, struct i
 		goto fail;
 	}
 	hinfo->hash_version = root->info.hash_version;
+	if (hinfo->hash_version <= DX_HASH_TEA)
+		hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 	if (dentry)
 		ext4fs_dirhash(dentry->d_name.name, dentry->d_name.len, hinfo);

@@ -640,6 +642,9 @@ int ext4_htree_fill_tree(struct file *di
 	dir = dir_file->f_path.dentry->d_inode;
 	if (!(EXT4_I(dir)->i_flags & EXT4_INDEX_FL)) {
 		hinfo.hash_version = EXT4_SB(dir->i_sb)->s_def_hash_version;
+		if (hinfo.hash_version <= DX_HASH_TEA)
+			hinfo.hash_version +=
+				EXT4_SB(dir->i_sb)->s_hash_unsigned;
 		hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 		count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
 					       start_hash, start_minor_hash);

@@ -1418,6 +1423,8 @@ static int make_indexed_dir(handle_t *ha
 
 	/* Initialize as for dx_probe */
 	hinfo.hash_version = root->info.hash_version;
+	if (hinfo.hash_version <= DX_HASH_TEA)
+		hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
 	hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
 	ext4fs_dirhash(name, namelen, &hinfo);
 	frame = frames;

@@ -2172,6 +2172,18 @@ static int ext4_fill_super(struct super_
 	for (i = 0; i < 4; i++)
 		sbi->s_hash_seed[i] = le32_to_cpu(es->s_hash_seed[i]);
 	sbi->s_def_hash_version = es->s_def_hash_version;
+	i = le32_to_cpu(es->s_flags);
+	if (i & EXT2_FLAGS_UNSIGNED_HASH)
+		sbi->s_hash_unsigned = 3;
+	else if ((i & EXT2_FLAGS_SIGNED_HASH) == 0) {
+#ifdef __CHAR_UNSIGNED__
+		es->s_flags |= cpu_to_le32(EXT2_FLAGS_UNSIGNED_HASH);
+		sbi->s_hash_unsigned = 3;
+#else
+		es->s_flags |= cpu_to_le32(EXT2_FLAGS_SIGNED_HASH);
+#endif
+		sb->s_dirt = 1;
+	}
 
 	if (sbi->s_blocks_per_group > blocksize * 8) {
 		printk(KERN_ERR

@@ -2298,6 +2298,20 @@ static int ext4_da_writepages(struct add
 	 */
 	if (!mapping->nrpages || !mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
 		return 0;
+
+	/*
+	 * If the filesystem has aborted, it is read-only, so return
+	 * right away instead of dumping stack traces later on that
+	 * will obscure the real source of the problem.  We test
+	 * EXT4_MOUNT_ABORT instead of sb->s_flag's MS_RDONLY because
+	 * the latter could be true if the filesystem is mounted
+	 * read-only, and in that case, ext4_da_writepages should
+	 * *never* be called, so if that ever happens, we would want
+	 * the stack trace.
+	 */
+	if (unlikely(sbi->s_mount_opt & EXT4_MOUNT_ABORT))
+		return -EROFS;
+
 	/*
 	 * Make sure nr_to_write is >= sbi->s_mb_stream_request
 	 * This make sure small files blocks are allocated in

@@ -2336,7 +2350,7 @@ restart_loop:
 		handle = ext4_journal_start(inode, needed_blocks);
 		if (IS_ERR(handle)) {
 			ret = PTR_ERR(handle);
-			printk(KERN_EMERG "%s: jbd2_start: "
+			printk(KERN_CRIT "%s: jbd2_start: "
 			       "%ld pages, ino %lu; err %d\n", __func__,
 				wbc->nr_to_write, inode->i_ino, ret);
 			dump_stack();

@@ -1648,18 +1648,25 @@ struct mpage_da_data {
  */
 static int mpage_da_submit_io(struct mpage_da_data *mpd)
 {
-	struct address_space *mapping = mpd->inode->i_mapping;
-	int ret = 0, err, nr_pages, i;
-	unsigned long index, end;
+	long pages_skipped;
 	struct pagevec pvec;
+	unsigned long index, end;
+	int ret = 0, err, nr_pages, i;
+	struct inode *inode = mpd->inode;
+	struct address_space *mapping = inode->i_mapping;
 
 	BUG_ON(mpd->next_page <= mpd->first_page);
-	pagevec_init(&pvec, 0);
+	/*
+	 * We need to start from the first_page to the next_page - 1
+	 * to make sure we also write the mapped dirty buffer_heads.
+	 * If we look at mpd->lbh.b_blocknr we would only be looking
+	 * at the currently mapped buffer_heads.
+	 */
 	index = mpd->first_page;
 	end = mpd->next_page - 1;
 
+	pagevec_init(&pvec, 0);
 	while (index <= end) {
-		/* XXX: optimize tail */
 		nr_pages = pagevec_lookup(&pvec, mapping, index, PAGEVEC_SIZE);
 		if (nr_pages == 0)
 			break;

@@ -1671,6 +1678,10 @@ static int mpage_da_submit_io(struct mpa
 				break;
 			index++;
 
+			BUG_ON(!PageLocked(page));
+			BUG_ON(PageWriteback(page));
+
+			pages_skipped = mpd->wbc->pages_skipped;
 			err = mapping->a_ops->writepage(page, mpd->wbc);
 			if (!err)
 				mpd->pages_written++;

@@ -1991,11 +2002,29 @@ static int __mpage_da_writepage(struct p
 		bh = head;
 		do {
 			BUG_ON(buffer_locked(bh));
+			/*
+			 * We need to try to allocate
+			 * unmapped blocks in the same page.
+			 * Otherwise we won't make progress
+			 * with the page in ext4_da_writepage
+			 */
 			if (buffer_dirty(bh) &&
 				(!buffer_mapped(bh) || buffer_delay(bh))) {
 				mpage_add_bh_to_extent(mpd, logical, bh);
 				if (mpd->io_done)
 					return MPAGE_DA_EXTENT_TAIL;
+			} else if (buffer_dirty(bh) && (buffer_mapped(bh))) {
+				/*
+				 * mapped dirty buffer. We need to update
+				 * the b_state because we look at
+				 * b_state in mpage_da_map_blocks. We don't
+				 * update b_size because if we find an
+				 * unmapped buffer_head later we need to
+				 * use the b_state flag of that buffer_head.
+				 */
+				if (mpd->lbh.b_size == 0)
+					mpd->lbh.b_state =
+						bh->b_state & BH_FLAGS;
 			}
 			logical++;
 		} while ((bh = bh->b_this_page) != head);

@@ -1493,7 +1493,6 @@ static int ext4_fill_flex_info(struct su
 	ext4_group_t flex_group_count;
 	ext4_group_t flex_group;
 	int groups_per_flex = 0;
-	__u64 block_bitmap = 0;
 	int i;
 
 	if (!sbi->s_es->s_log_groups_per_flex) {

@@ -1516,9 +1515,6 @@ static int ext4_fill_flex_info(struct su
 		goto failed;
 	}
 
-	gdp = ext4_get_group_desc(sb, 1, &bh);
-	block_bitmap = ext4_block_bitmap(sb, gdp) - 1;

@@ -103,7 +103,8 @@ struct ext4_sb_info {
 	struct list_head s_committed_transaction;
 	spinlock_t s_md_lock;
 	tid_t s_last_transaction;
-	unsigned short *s_mb_offsets, *s_mb_maxs;
+	unsigned short *s_mb_offsets;
+	unsigned int *s_mb_maxs;
 
 	/* tunables */
 	unsigned long s_stripe;

@@ -2495,6 +2495,8 @@ int ext4_mb_init(struct super_block *sb,
 		clear_opt(sbi->s_mount_opt, MBALLOC);
 		return -ENOMEM;
 	}
+
+	i = (sb->s_blocksize_bits + 2) * sizeof(unsigned int);
 	sbi->s_mb_maxs = kmalloc(i, GFP_KERNEL);
 	if (sbi->s_mb_maxs == NULL) {
 		clear_opt(sbi->s_mount_opt, MBALLOC);

@@ -24,6 +24,7 @@
 #include <linux/crc32.h>
 #include <linux/writeback.h>
 #include <linux/backing-dev.h>
+#include <linux/bio.h>
 
 /*
  * Default IO end handler for temporary BJ_IO buffer_heads.

@@ -170,12 +171,34 @@ static int journal_submit_commit_record(
  * This function along with journal_submit_commit_record
  * allows to write the commit record asynchronously.
  */
-static int journal_wait_on_commit_record(struct buffer_head *bh)
+static int journal_wait_on_commit_record(journal_t *journal,
+					 struct buffer_head *bh)
 {
 	int ret = 0;
 
+retry:
 	clear_buffer_dirty(bh);
 	wait_on_buffer(bh);
+	if (buffer_eopnotsupp(bh) && (journal->j_flags & JBD2_BARRIER)) {
+		printk(KERN_WARNING
+		       "JBD2: wait_on_commit_record: sync failed on %s - "
+		       "disabling barriers\n", journal->j_devname);
+		spin_lock(&journal->j_state_lock);
+		journal->j_flags &= ~JBD2_BARRIER;
+		spin_unlock(&journal->j_state_lock);
+
+		lock_buffer(bh);
+		clear_buffer_dirty(bh);
+		set_buffer_uptodate(bh);
+		bh->b_end_io = journal_end_buffer_io_sync;
+
+		ret = submit_bh(WRITE_SYNC, bh);
+		if (ret) {
+			unlock_buffer(bh);
+			return ret;
+		}
+		goto retry;
+	}
 
 	if (unlikely(!buffer_uptodate(bh)))
 		ret = -EIO;

@@ -795,7 +818,7 @@ wait_for_iobuf:
 			__jbd2_journal_abort_hard(journal);
 	}
 	if (!err && !is_journal_aborted(journal))
-		err = journal_wait_on_commit_record(cbh);
+		err = journal_wait_on_commit_record(journal, cbh);
 
 	if (err)
 		jbd2_journal_abort(journal, err);

@@ -1326,6 +1326,8 @@ static void ext4_mb_check_limits(struct 
 	struct ext4_free_extent ex;
 	int max;
 
+	if (ac->ac_status == AC_STATUS_FOUND)
+		return;
 	/*
 	 * We don't want to scan for a whole year
 	 */

@@ -20,6 +20,7 @@
 #include "ext4.h"
 #include "ext4_jbd2.h"
 #include "group.h"
+#include "mballoc.h"
 
 /*
  * balloc.c contains the blocks allocation and deallocation routines

@@ -837,6 +838,131 @@ error_return:
 }
 
 /**
+ * ext4_add_groupblocks() -- Add given blocks to an existing group
+ * @handle:			handle to this transaction
+ * @sb:				super block
+ * @block:			start physcial block to add to the block group
+ * @count:			number of blocks to free
+ *
+ * This marks the blocks as free in the bitmap. We ask the
+ * mballoc to reload the buddy after this by setting group
+ * EXT4_GROUP_INFO_NEED_INIT_BIT flag
+ */
+void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+			 ext4_fsblk_t block, unsigned long count)
+{
+	struct buffer_head *bitmap_bh = NULL;
+	struct buffer_head *gd_bh;
+	ext4_group_t block_group;
+	ext4_grpblk_t bit;
+	unsigned long i;
+	struct ext4_group_desc *desc;
+	struct ext4_super_block *es;
+	struct ext4_sb_info *sbi;
+	int err = 0, ret;
+	ext4_grpblk_t blocks_freed;
+	struct ext4_group_info *grp;
+
+	sbi = EXT4_SB(sb);
+	es = sbi->s_es;
+	ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
+
+	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
+	/*
+	 * Check to see if we are freeing blocks across a group
+	 * boundary.
+	 */
+	if (bit + count > EXT4_BLOCKS_PER_GROUP(sb))
+		goto error_return;
+
+	bitmap_bh = ext4_read_block_bitmap(sb, block_group);
+	if (!bitmap_bh)
+		goto error_return;
+	desc = ext4_get_group_desc(sb, block_group, &gd_bh);
+	if (!desc)
+		goto error_return;
+
+	if (in_range(ext4_block_bitmap(sb, desc), block, count) ||
+	    in_range(ext4_inode_bitmap(sb, desc), block, count) ||
+	    in_range(block, ext4_inode_table(sb, desc), sbi->s_itb_per_group) ||
+	    in_range(block + count - 1, ext4_inode_table(sb, desc),
+		     sbi->s_itb_per_group)) {
+		ext4_error(sb, __func__,
+			   "Adding blocks in system zones - "
+			    "Block = %llu, count = %lu",
+			    block, count);
+		goto error_return;
+	}
+
+	/*
+	 * We are about to add blocks to the bitmap,
+	 * so we need undo access.
+	 */
+	BUFFER_TRACE(bitmap_bh, "getting undo access");
+	err = ext4_journal_get_undo_access(handle, bitmap_bh);
+	if (err)
+		goto error_return;
+
+	/*
+	 * We are about to modify some metadata.  Call the journal APIs
+	 * to unshare ->b_data if a currently-committing transaction is
+	 * using it
+	 */
+	BUFFER_TRACE(gd_bh, "get_write_access");
+	err = ext4_journal_get_write_access(handle, gd_bh);
+	if (err)
+		goto error_return;
+
+	for (i = 0, blocks_freed = 0; i < count; i++) {
+		BUFFER_TRACE(bitmap_bh, "clear bit");
+		if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),
+						bit + i, bitmap_bh->b_data)) {
+			ext4_error(sb, __func__,
+				   "bit already cleared for block %llu",
+				   (ext4_fsblk_t)(block + i));
+			BUFFER_TRACE(bitmap_bh, "bit already cleared");
+		} else {
+			blocks_freed++;
+		}
+	}
+	spin_lock(sb_bgl_lock(sbi, block_group));
+	le16_add_cpu(&desc->bg_free_blocks_count, blocks_freed);
+	desc->bg_checksum = ext4_group_desc_csum(sbi, block_group, desc);
+	spin_unlock(sb_bgl_lock(sbi, block_group));
+	percpu_counter_add(&sbi->s_freeblocks_counter, blocks_freed);
+
+	if (sbi->s_log_groups_per_flex) {
+		ext4_group_t flex_group = ext4_flex_group(sbi, block_group);
+		spin_lock(sb_bgl_lock(sbi, flex_group));
+		sbi->s_flex_groups[flex_group].free_blocks += blocks_freed;
+		spin_unlock(sb_bgl_lock(sbi, flex_group));
+	}
+
+	/* We dirtied the bitmap block */
+	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
+	err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+
+	/* And the group descriptor block */
+	BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
+	ret = ext4_journal_dirty_metadata(handle, gd_bh);
+	if (!err)
+		err = ret;
+	sb->s_dirt = 1;
+	/*
+	 * request to reload the buddy with the
+	 * new bitmap information
+	 */
+	grp = ext4_get_group_info(sb, block_group);
+	set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
+	ext4_mb_update_group_info(grp, blocks_freed);
+
+error_return:
+	brelse(bitmap_bh);
+	ext4_std_error(sb, err);
+	return;
+}
+
+/**
  * ext4_free_blocks() -- Free given blocks and update quota
  * @handle:		handle for this transaction
  * @inode:		inode

@@ -991,9 +991,11 @@ extern ext4_fsblk_t ext4_has_free_blocks
 						ext4_fsblk_t nblocks);
 extern void ext4_free_blocks (handle_t *handle, struct inode *inode,
 			ext4_fsblk_t block, unsigned long count, int metadata);
-extern void ext4_free_blocks_sb (handle_t *handle, struct super_block *sb,
-				 ext4_fsblk_t block, unsigned long count,
+extern void ext4_free_blocks_sb(handle_t *handle, struct super_block *sb,
+				ext4_fsblk_t block, unsigned long count,
 				unsigned long *pdquot_freed_blocks);
+extern void ext4_add_groupblocks(handle_t *handle, struct super_block *sb,
+				ext4_fsblk_t block, unsigned long count);
 extern ext4_fsblk_t ext4_count_free_blocks (struct super_block *);
 extern void ext4_check_blocks_bitmap (struct super_block *);
 extern struct ext4_group_desc * ext4_get_group_desc(struct super_block * sb,

@@ -976,9 +976,7 @@ int ext4_group_extend(struct super_block
 	struct buffer_head * bh;
 	handle_t *handle;
 	int err;
-	unsigned long freed_blocks;
 	ext4_group_t group;
-	struct ext4_group_info *grp;
 
 	/* We don't need to worry about locking wrt other resizers just
 	 * yet: we're going to revalidate es->s_blocks_count after

@@ -1077,7 +1075,8 @@ int ext4_group_extend(struct super_block
 	unlock_super(sb);
 	ext4_debug("freeing blocks %llu through %llu\n", o_blocks_count,
 		   o_blocks_count + add);
-	ext4_free_blocks_sb(handle, sb, o_blocks_count, add, &freed_blocks);
+	/* We add the blocks to the bitmap and set the group need init bit */
+	ext4_add_groupblocks(handle, sb, o_blocks_count, add);
 	ext4_debug("freed blocks %llu through %llu\n", o_blocks_count,
 		   o_blocks_count + add);
 	if ((err = ext4_journal_stop(handle)))

@@ -1113,12 +1112,6 @@ int ext4_group_extend(struct super_block
 			ClearPageUptodate(page);
 			page_cache_release(page);
 		}
-
-		/* Get the info on the last group */
-		grp = ext4_get_group_info(sb, group);

@@ -868,6 +868,7 @@ void ext4_add_groupblocks(handle_t *hand
 	ext4_debug("Adding block(s) %llu-%llu\n", block, block + count - 1);
 
 	ext4_get_group_no_and_offset(sb, block, &block_group, &bit);
+	grp = ext4_get_group_info(sb, block_group);
 	/*
 	 * Check to see if we are freeing blocks across a group
 	 * boundary.

@@ -912,7 +913,11 @@ void ext4_add_groupblocks(handle_t *hand
 	err = ext4_journal_get_write_access(handle, gd_bh);
 	if (err)
 		goto error_return;
-
+	/*
+	 * make sure we don't allow a parallel init on other groups in the
+	 * same buddy cache
+	 */
+	down_write(&grp->alloc_sem);
 	for (i = 0, blocks_freed = 0; i < count; i++) {
 		BUFFER_TRACE(bitmap_bh, "clear bit");
 		if (!ext4_clear_bit_atomic(sb_bgl_lock(sbi, block_group),

@@ -937,6 +942,13 @@ void ext4_add_groupblocks(handle_t *hand
 		sbi->s_flex_groups[flex_group].free_blocks += blocks_freed;
 		spin_unlock(sb_bgl_lock(sbi, flex_group));
 	}
+	/*
+	 * request to reload the buddy with the
+	 * new bitmap information
+	 */
+	set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
+	ext4_mb_update_group_info(grp, blocks_freed);
+	up_write(&grp->alloc_sem);
 
 	/* We dirtied the bitmap block */
 	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");

@@ -948,13 +960,6 @@ void ext4_add_groupblocks(handle_t *hand
 	if (!err)
 		err = ret;
 	sb->s_dirt = 1;
-	/*
-	 * request to reload the buddy with the
-	 * new bitmap information
-	 */
-	grp = ext4_get_group_info(sb, block_group);
-	set_bit(EXT4_GROUP_INFO_NEED_INIT_BIT, &(grp->bb_state));
-	ext4_mb_update_group_info(grp, blocks_freed);
 
 error_return:
 	brelse(bitmap_bh);

@@ -1043,12 +1043,13 @@ extern int __init init_ext4_mballoc(void
 extern void exit_ext4_mballoc(void);
 extern void ext4_mb_free_blocks(handle_t *, struct inode *,
 		unsigned long, unsigned long, int, unsigned long *);
-extern int ext4_mb_add_more_groupinfo(struct super_block *sb,
+extern int ext4_mb_add_groupinfo(struct super_block *sb,
 		ext4_group_t i, struct ext4_group_desc *desc);
 extern void ext4_mb_update_group_info(struct ext4_group_info *grp,
 		ext4_grpblk_t add);
-
-
+extern int ext4_mb_get_buddy_cache_lock(struct super_block *, ext4_group_t);
+extern void ext4_mb_put_buddy_cache_lock(struct super_block *,
+						ext4_group_t, int);
 /* inode.c */
 int ext4_forget(handle_t *handle, int is_metadata, struct inode *inode,
 		struct buffer_head *bh, ext4_fsblk_t blocknr);

349 lines not on this page · raw message

@@ -18,6 +18,7 @@
 #include <linux/pagemap.h>
 #include <linux/seq_file.h>
 #include <linux/version.h>
+#include <linux/mutex.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "group.h"

@@ -122,6 +123,7 @@ struct ext4_group_info {
 #ifdef DOUBLE_CHECK
 	void		*bb_bitmap;
 #endif
+	struct rw_semaphore alloc_sem;
 	unsigned short	bb_counters[];
 };
 

@@ -242,6 +244,7 @@ struct ext4_buddy {
 	struct super_block *bd_sb;
 	__u16 bd_blkbits;
 	ext4_group_t bd_group;
+	struct rw_semaphore *alloc_semp;
 };
 #define EXT4_MB_BITMAP(e4b)	((e4b)->bd_bitmap)
 #define EXT4_MB_BUDDY(e4b)	((e4b)->bd_buddy)

75 lines not on this page · raw message

@@ -100,7 +100,7 @@
  * inode as:
  *
  *  {                        page                        }
- *  [ group 0 buddy][ group 0 bitmap] [group 1][ group 1]...
+ *  [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]...
  *
  *
  * one block each for bitmap and buddy information.  So for each group we

@@ -330,6 +330,15 @@
  *        object
  *
  */
+static struct kmem_cache *ext4_pspace_cachep;
+static struct kmem_cache *ext4_ac_cachep;
+static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
+					ext4_group_t group);
+static int ext4_mb_init_per_dev_proc(struct super_block *sb);
+static int ext4_mb_destroy_per_dev_proc(struct super_block *sb);
+static void ext4_mb_free_committed_blocks(struct super_block *);
+static void ext4_mb_poll_new_transaction(struct super_block *sb,
+					 handle_t *handle);
 
 static inline void *mb_correct_addr_and_bit(int *bit, void *addr)
 {

@@ -718,7 +727,7 @@ static void ext4_mb_generate_buddy(struc
  * stored in the inode as
  *
  * {                        page                        }
- * [ group 0 buddy][ group 0 bitmap] [group 1][ group 1]...
+ * [ group 0 bitmap][ group 0 buddy] [group 1][ group 1]...
  *
  *
  * one block each for bitmap and buddy information.

@@ -1320,8 +1329,13 @@ static void ext4_mb_use_best_found(struc
 	ac->ac_tail = ret & 0xffff;
 	ac->ac_buddy = ret >> 16;
 
-	/* XXXXXXX: SUCH A HORRIBLE **CK */
-	/*FIXME!! Why ? */
+	/*
+	 * take the page reference. We want the page to be pinned
+	 * so that we don't get a ext4_mb_init_cache_call for this
+	 * group until we update the bitmap. That would mean we
+	 * double allocate blocks. The reference is dropped
+	 * in ext4_mb_release_context
+	 */
 	ac->ac_bitmap_page = e4b->bd_bitmap_page;
 	get_page(ac->ac_bitmap_page);
 	ac->ac_buddy_page = e4b->bd_buddy_page;

@@ -97,9 +97,6 @@
  */
 #define MB_DEFAULT_GROUP_PREALLOC	512
 
-static struct kmem_cache *ext4_pspace_cachep;
-static struct kmem_cache *ext4_ac_cachep;
-
 #ifdef EXT4_BB_MAX_BLOCKS
 #undef EXT4_BB_MAX_BLOCKS
 #endif

@@ -254,8 +251,6 @@ static inline void ext4_mb_store_history
 {
 	return;
 }
-#else
-static void ext4_mb_store_history(struct ext4_allocation_context *ac);
 #endif
 
 #define in_range(b, first, len)	((b) >= (first) && (b) <= (first) + (len) - 1)

@@ -263,19 +258,6 @@ static void ext4_mb_store_history(struct
 static struct proc_dir_entry *proc_root_ext4;
 struct buffer_head *read_block_bitmap(struct super_block *, ext4_group_t);
 
-static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
-					ext4_group_t group);
-static void ext4_mb_poll_new_transaction(struct super_block *, handle_t *);
-static void ext4_mb_free_committed_blocks(struct super_block *);
-static void ext4_mb_return_to_preallocation(struct inode *inode,
-					struct ext4_buddy *e4b, sector_t block,
-					int count);
-static void ext4_mb_put_pa(struct ext4_allocation_context *,
-			struct super_block *, struct ext4_prealloc_space *pa);
-static int ext4_mb_init_per_dev_proc(struct super_block *sb);
-static int ext4_mb_destroy_per_dev_proc(struct super_block *sb);
-

@@ -332,6 +332,7 @@
  */
 static struct kmem_cache *ext4_pspace_cachep;
 static struct kmem_cache *ext4_ac_cachep;
+static struct kmem_cache *ext4_free_ext_cachep;
 static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 					ext4_group_t group);
 static int ext4_mb_init_per_dev_proc(struct super_block *sb);

@@ -2506,6 +2507,7 @@ int ext4_mb_add_groupinfo(struct super_b
 
 	INIT_LIST_HEAD(&meta_group_info[i]->bb_prealloc_list);
 	init_rwsem(&meta_group_info[i]->alloc_sem);
+	meta_group_info[i]->bb_free_root.rb_node = NULL;;
 
 #ifdef DOUBLE_CHECK
 	{

@@ -2819,13 +2821,11 @@ int ext4_mb_release(struct super_block *
 static noinline_for_stack void
 ext4_mb_free_committed_blocks(struct super_block *sb)
 {
-	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	int err;
-	int i;
-	int count = 0;
-	int count2 = 0;
-	struct ext4_free_metadata *md;
 	struct ext4_buddy e4b;
+	struct ext4_group_info *db;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	int err, count = 0, count2 = 0;
+	struct ext4_free_data *entry;
 
 	if (list_empty(&sbi->s_committed_transaction))
 		return;

@@ -2833,44 +2833,46 @@ ext4_mb_free_committed_blocks(struct sup
 	/* there is committed blocks to be freed yet */
 	do {
 		/* get next array of blocks */
-		md = NULL;
+		entry = NULL;
 		spin_lock(&sbi->s_md_lock);
 		if (!list_empty(&sbi->s_committed_transaction)) {
-			md = list_entry(sbi->s_committed_transaction.next,
-					struct ext4_free_metadata, list);
-			list_del(&md->list);
+			entry = list_entry(sbi->s_committed_transaction.next,
+					struct ext4_free_data, list);
+			list_del(&entry->list);
 		}
 		spin_unlock(&sbi->s_md_lock);
 
-		if (md == NULL)
+		if (entry == NULL)
 			break;
 
 		mb_debug("gonna free %u blocks in group %lu (0x%p):",
-				md->num, md->group, md);
+				entry->count, entry->group, entry);
 
-		err = ext4_mb_load_buddy(sb, md->group, &e4b);
+		err = ext4_mb_load_buddy(sb, entry->group, &e4b);
 		/* we expect to find existing buddy because it's pinned */
 		BUG_ON(err != 0);
 
+		db = e4b.bd_info;
 		/* there are blocks to put in buddy to make them really free */
-		count += md->num;
+		count += entry->count;
 		count2++;
-		ext4_lock_group(sb, md->group);
-		for (i = 0; i < md->num; i++) {
-			mb_debug(" %u", md->blocks[i]);
-			mb_free_blocks(NULL, &e4b, md->blocks[i], 1);
-		}
-		mb_debug("\n");
-		ext4_unlock_group(sb, md->group);
-
-		/* balance refcounts from ext4_mb_free_metadata() */
-		page_cache_release(e4b.bd_buddy_page);
-		page_cache_release(e4b.bd_bitmap_page);
+		ext4_lock_group(sb, entry->group);
+		/* Take it out of per group rb tree */
+		rb_erase(&entry->node, &(db->bb_free_root));
+		mb_free_blocks(NULL, &e4b, entry->start_blk, entry->count);
+
+		if (!db->bb_free_root.rb_node) {
+			/* No more items in the per group rb tree
+			 * balance refcounts from ext4_mb_free_metadata()
+			 */
+			page_cache_release(e4b.bd_buddy_page);
+			page_cache_release(e4b.bd_bitmap_page);
+		}
+		ext4_unlock_group(sb, entry->group);
 
-		kfree(md);
+		kmem_cache_free(ext4_free_ext_cachep, entry);
 		ext4_mb_release_desc(&e4b);
-
-	} while (md);
+	} while (1);
 
 	mb_debug("freed %u blocks in %u structures\n", count, count2);
 }

@@ -3025,6 +3027,16 @@ int __init init_ext4_mballoc(void)
 		kmem_cache_destroy(ext4_pspace_cachep);
 		return -ENOMEM;
 	}
+
+	ext4_free_ext_cachep =
+		kmem_cache_create("ext4_free_block_extents",
+				     sizeof(struct ext4_free_data),
+				     0, SLAB_RECLAIM_ACCOUNT, NULL);
+	if (ext4_free_ext_cachep == NULL) {
+		kmem_cache_destroy(ext4_pspace_cachep);
+		kmem_cache_destroy(ext4_ac_cachep);
+		return -ENOMEM;
+	}
 #ifdef CONFIG_PROC_FS
 	proc_root_ext4 = proc_mkdir("fs/ext4", NULL);
 	if (proc_root_ext4 == NULL)

@@ -3041,6 +3053,7 @@ void exit_ext4_mballoc(void)
 #ifdef CONFIG_PROC_FS
 	remove_proc_entry("fs/ext4", NULL);
 #endif
+	kmem_cache_destroy(ext4_free_ext_cachep);
 }
 
 

@@ -3561,6 +3574,7 @@ ext4_mb_use_preallocated(struct ext4_all
 		ac->ac_criteria = 20;
 		return 1;
 	}
+
 	return 0;
 }
 

@@ -4678,6 +4692,21 @@ static void ext4_mb_poll_new_transaction
 	ext4_mb_free_committed_blocks(sb);
 }
 
+/*
+ * We can merge two free data extents only if the physical blocks
+ * are contiguous, AND the extents were freed by the same transaction,
+ * AND the blocks are associated with the same group.
+ */
+static int can_merge(struct ext4_free_data *entry1,
+			struct ext4_free_data *entry2)
+{
+	if ((entry1->t_tid == entry2->t_tid) &&
+	    (entry1->group == entry2->group) &&
+	    ((entry1->start_blk + entry1->count) == entry2->start_blk))
+		return 1;
+	return 0;
+}
+
 static noinline_for_stack int
 ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 			  ext4_group_t group, ext4_grpblk_t block, int count)

@@ -4685,57 +4714,80 @@ ext4_mb_free_metadata(handle_t *handle, 
 	struct ext4_group_info *db = e4b->bd_info;
 	struct super_block *sb = e4b->bd_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_free_metadata *md;
-	int i;
+	struct ext4_free_data *entry, *new_entry;
+	struct rb_node **n = &db->bb_free_root.rb_node, *node;
+	struct rb_node *parent = NULL, *new_node;
+
 
 	BUG_ON(e4b->bd_bitmap_page == NULL);
 	BUG_ON(e4b->bd_buddy_page == NULL);
 
+	new_entry  = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
+	new_entry->start_blk = block;
+	new_entry->group  = group;
+	new_entry->count = count;
+	new_entry->t_tid = handle->h_transaction->t_tid;
+	new_node = &new_entry->node;
+
 	ext4_lock_group(sb, group);
-	for (i = 0; i < count; i++) {
-		md = db->bb_md_cur;
-		if (md && db->bb_tid != handle->h_transaction->t_tid) {
-			db->bb_md_cur = NULL;
-			md = NULL;
+	if (!*n) {
+		/* first free block exent. We need to
+		   protect buddy cache from being freed,
+		 * otherwise we'll refresh it from
+		 * on-disk bitmap and lose not-yet-available
+		 * blocks */
+		page_cache_get(e4b->bd_buddy_page);
+		page_cache_get(e4b->bd_bitmap_page);
+	}
+	while (*n) {
+		parent = *n;
+		entry = rb_entry(parent, struct ext4_free_data, node);
+		if (block < entry->start_blk)
+			n = &(*n)->rb_left;
+		else if (block >= (entry->start_blk + entry->count))
+			n = &(*n)->rb_right;
+		else {
+			ext4_error(sb, __func__,
+			    "Double free of blocks %d (%d %d)\n",
+			    block, entry->start_blk, entry->count);
+			return 0;
 		}
+	}
 
-		if (md == NULL) {
-			ext4_unlock_group(sb, group);
-			md = kmalloc(sizeof(*md), GFP_NOFS);
-			if (md == NULL)
-				return -ENOMEM;
-			md->num = 0;
-			md->group = group;
+	rb_link_node(new_node, parent, n);
+	rb_insert_color(new_node, &db->bb_free_root);
 
-			ext4_lock_group(sb, group);
-			if (db->bb_md_cur == NULL) {
-				spin_lock(&sbi->s_md_lock);
-				list_add(&md->list, &sbi->s_active_transaction);
-				spin_unlock(&sbi->s_md_lock);
-				/* protect buddy cache from being freed,
-				 * otherwise we'll refresh it from
-				 * on-disk bitmap and lose not-yet-available
-				 * blocks */
-				page_cache_get(e4b->bd_buddy_page);
-				page_cache_get(e4b->bd_bitmap_page);
-				db->bb_md_cur = md;
-				db->bb_tid = handle->h_transaction->t_tid;
-				mb_debug("new md 0x%p for group %lu\n",
-						md, md->group);
-			} else {
-				kfree(md);
-				md = db->bb_md_cur;
-			}
+	/* Now try to see the extent can be merged to left and right */
+	node = rb_prev(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_free_data, node);
+		if (can_merge(entry, new_entry)) {
+			new_entry->start_blk = entry->start_blk;
+			new_entry->count += entry->count;
+			rb_erase(node, &(db->bb_free_root));
+			spin_lock(&sbi->s_md_lock);
+			list_del(&entry->list);
+			spin_unlock(&sbi->s_md_lock);
+			kmem_cache_free(ext4_free_ext_cachep, entry);
 		}
+	}
 
-		BUG_ON(md->num >= EXT4_BB_MAX_BLOCKS);
-		md->blocks[md->num] = block + i;
-		md->num++;
-		if (md->num == EXT4_BB_MAX_BLOCKS) {
-			/* no more space, put full container on a sb's list */
-			db->bb_md_cur = NULL;
+	node = rb_next(new_node);
+	if (node) {
+		entry = rb_entry(node, struct ext4_free_data, node);
+		if (can_merge(new_entry, entry)) {
+			new_entry->count += entry->count;
+			rb_erase(node, &(db->bb_free_root));
+			spin_lock(&sbi->s_md_lock);
+			list_del(&entry->list);
+			spin_unlock(&sbi->s_md_lock);
+			kmem_cache_free(ext4_free_ext_cachep, entry);
 		}
 	}
+	/* Add the extent to active_transaction list */
+	spin_lock(&sbi->s_md_lock);
+	list_add(&new_entry->list, &sbi->s_active_transaction);
+	spin_unlock(&sbi->s_md_lock);
 	ext4_unlock_group(sb, group);
 	return 0;
 }

@@ -97,22 +97,27 @@
  */
 #define MB_DEFAULT_GROUP_PREALLOC	512
 
-#ifdef EXT4_BB_MAX_BLOCKS
-#undef EXT4_BB_MAX_BLOCKS
-#endif
-#define EXT4_BB_MAX_BLOCKS	30
+struct ext4_free_data {
+	/* this links the free block information from group_info */
+	struct rb_node node;
 
-struct ext4_free_metadata {
-	ext4_group_t group;
-	unsigned short num;
-	ext4_grpblk_t  blocks[EXT4_BB_MAX_BLOCKS];
+	/* this links the free block information from ext4_sb_info */
 	struct list_head list;
+
+	/* group which free block extent belongs */
+	ext4_group_t group;
+
+	/* free block extent */
+	ext4_grpblk_t start_blk;
+	ext4_grpblk_t count;
+
+	/* transaction which freed this extent */
+	tid_t	t_tid;
 };
 
 struct ext4_group_info {
 	unsigned long	bb_state;
-	unsigned long	bb_tid;
-	struct ext4_free_metadata *bb_md_cur;
+	struct rb_root  bb_free_root;
 	unsigned short	bb_first_free;
 	unsigned short	bb_free;
 	unsigned short	bb_fragments;

@@ -335,6 +335,8 @@ static struct kmem_cache *ext4_ac_cachep
 static struct kmem_cache *ext4_free_ext_cachep;
 static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 					ext4_group_t group);
+static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
+						ext4_group_t group);
 static int ext4_mb_init_per_dev_proc(struct super_block *sb);
 static int ext4_mb_destroy_per_dev_proc(struct super_block *sb);
 static void ext4_mb_free_committed_blocks(struct super_block *);

@@ -858,7 +860,9 @@ static int ext4_mb_init_cache(struct pag
 			/*
 			 * incore got set to the group block bitmap below
 			 */
+			ext4_lock_group(sb, group);
 			ext4_mb_generate_buddy(sb, data, incore, group);
+			ext4_unlock_group(sb, group);
 			incore = NULL;
 		} else {
 			/* this is block of bitmap */

@@ -872,6 +876,7 @@ static int ext4_mb_init_cache(struct pag
 
 			/* mark all preallocated blks used in in-core bitmap */
 			ext4_mb_generate_from_pa(sb, data, group);
+			ext4_mb_generate_from_freelist(sb, data, group);
 			ext4_unlock_group(sb, group);
 
 			/* set incore so that the buddy information can be

@@ -3579,6 +3584,32 @@ ext4_mb_use_preallocated(struct ext4_all
 }
 
 /*
+ * the function goes through all block freed in the group
+ * but not yet committed and marks them used in in-core bitmap.
+ * buddy must be generated from this bitmap
+ * Need to be called with ext4 group lock (ext4_lock_group)
+ */
+static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
+						ext4_group_t group)
+{
+	struct rb_node *n;
+	struct ext4_group_info *grp;
+	struct ext4_free_data *entry;
+
+	grp = ext4_get_group_info(sb, group);
+	n = rb_first(&(grp->bb_free_root));
+
+	while (n) {
+		entry = rb_entry(n, struct ext4_free_data, node);
+		mb_set_bits(sb_bgl_lock(EXT4_SB(sb), group),
+				bitmap, entry->start_blk,
+				entry->count);
+		n = rb_next(n);
+	}
+	return;
+}
+
+/*
  * the function goes through all preallocation in this group and marks them
  * used in in-core bitmap. buddy must be generated from this bitmap
  * Need to be called with ext4 group lock (ext4_lock_group)

@@ -4709,27 +4740,22 @@ static int can_merge(struct ext4_free_da
 
 static noinline_for_stack int
 ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
-			  ext4_group_t group, ext4_grpblk_t block, int count)
+			struct ext4_free_data *new_entry)
 {
+	ext4_grpblk_t block;
+	struct ext4_free_data *entry;
 	struct ext4_group_info *db = e4b->bd_info;
 	struct super_block *sb = e4b->bd_sb;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_free_data *entry, *new_entry;
 	struct rb_node **n = &db->bb_free_root.rb_node, *node;
 	struct rb_node *parent = NULL, *new_node;
 
-
 	BUG_ON(e4b->bd_bitmap_page == NULL);
 	BUG_ON(e4b->bd_buddy_page == NULL);
 
-	new_entry  = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
-	new_entry->start_blk = block;
-	new_entry->group  = group;
-	new_entry->count = count;
-	new_entry->t_tid = handle->h_transaction->t_tid;
 	new_node = &new_entry->node;
+	block = new_entry->start_blk;
 
-	ext4_lock_group(sb, group);
 	if (!*n) {
 		/* first free block exent. We need to
 		   protect buddy cache from being freed,

@@ -4788,7 +4814,6 @@ ext4_mb_free_metadata(handle_t *handle, 
 	spin_lock(&sbi->s_md_lock);
 	list_add(&new_entry->list, &sbi->s_active_transaction);
 	spin_unlock(&sbi->s_md_lock);
-	ext4_unlock_group(sb, group);
 	return 0;
 }
 

@@ -4895,15 +4920,6 @@ do_more:
 			BUG_ON(!mb_test_bit(bit + i, bitmap_bh->b_data));
 	}
 #endif
-	mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data,
-			bit, count);
-
-	/* We dirtied the bitmap block */
-	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
-	err = ext4_journal_dirty_metadata(handle, bitmap_bh);
-	if (err)
-		goto error_return;
-
 	if (ac) {
 		ac->ac_b_ex.fe_group = block_group;
 		ac->ac_b_ex.fe_start = bit;

@@ -4915,11 +4931,29 @@ do_more:
 	if (err)
 		goto error_return;
 	if (metadata) {
-		/* blocks being freed are metadata. these blocks shouldn't
-		 * be used until this transaction is committed */
-		ext4_mb_free_metadata(handle, &e4b, block_group, bit, count);
+		struct ext4_free_data *new_entry;
+		/*
+		 * blocks being freed are metadata. these blocks shouldn't
+		 * be used until this transaction is committed
+		 */
+		new_entry  = kmem_cache_alloc(ext4_free_ext_cachep, GFP_NOFS);
+		new_entry->start_blk = bit;
+		new_entry->group  = block_group;
+		new_entry->count = count;
+		new_entry->t_tid = handle->h_transaction->t_tid;
+		ext4_lock_group(sb, block_group);
+		mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data,
+				bit, count);
+		ext4_mb_free_metadata(handle, &e4b, new_entry);
+		ext4_unlock_group(sb, block_group);
 	} else {
 		ext4_lock_group(sb, block_group);
+		/* need to update group_info->bb_free and bitmap
+		 * with group lock held. generate_buddy look at
+		 * them with group lock_held
+		 */
+		mb_clear_bits(sb_bgl_lock(sbi, block_group), bitmap_bh->b_data,
+				bit, count);
 		mb_free_blocks(inode, &e4b, bit, count);
 		ext4_mb_return_to_preallocation(inode, &e4b, block, count);
 		ext4_unlock_group(sb, block_group);

@@ -4942,6 +4976,10 @@ do_more:
 
 	*freed += count;
 
+	/* We dirtied the bitmap block */
+	BUFFER_TRACE(bitmap_bh, "dirtied bitmap block");
+	err = ext4_journal_dirty_metadata(handle, bitmap_bh);
+
 	/* And the group descriptor block */
 	BUFFER_TRACE(gd_bh, "dirtied group descriptor block");
 	ret = ext4_journal_dirty_metadata(handle, gd_bh);

@@ -1070,7 +1070,10 @@ static void mb_clear_bits(spinlock_t *lo
 			cur += 32;
 			continue;
 		}
-		mb_clear_bit_atomic(lock, cur, bm);
+		if (lock)
+			mb_clear_bit_atomic(lock, cur, bm);
+		else
+			mb_clear_bit(cur, bm);
 		cur++;
 	}
 }

@@ -1088,7 +1091,10 @@ static void mb_set_bits(spinlock_t *lock
 			cur += 32;
 			continue;
 		}
-		mb_set_bit_atomic(lock, cur, bm);
+		if (lock)
+			mb_set_bit_atomic(lock, cur, bm);
+		else
+			mb_set_bit(cur, bm);
 		cur++;
 	}
 }

@@ -3143,10 +3149,9 @@ ext4_mb_mark_diskspace_used(struct ext4_
 		}
 	}
 #endif
-	mb_set_bits(sb_bgl_lock(sbi, ac->ac_b_ex.fe_group), bitmap_bh->b_data,
-				ac->ac_b_ex.fe_start, ac->ac_b_ex.fe_len);

@@ -567,6 +567,77 @@ static int find_group_other(struct super
 }
 
 /*
+ * claim the inode from the inode bitmap. If the group
+ * is uninit we need to take the groups's sb_bgl_lock
+ * and clear the uninit flag. The inode bitmap update
+ * and group desc uninit flag clear should be done
+ * after holding sb_bgl_lock so that ext4_read_inode_bitmap
+ * doesn't race with the ext4_claim_inode
+ */
+static int ext4_claim_inode(struct super_block *sb,
+			struct buffer_head *inode_bitmap_bh,
+			unsigned long ino, ext4_group_t group, int mode)
+{
+	int free = 0, retval = 0;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_group_desc *gdp = ext4_get_group_desc(sb, group, NULL);
+
+	spin_lock(sb_bgl_lock(sbi, group));
+	if (ext4_set_bit(ino, inode_bitmap_bh->b_data)) {
+		/* not a free inode */
+		retval = 1;
+		goto err_ret;
+	}
+	ino++;
+	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
+			ino > EXT4_INODES_PER_GROUP(sb)) {
+		spin_unlock(sb_bgl_lock(sbi, group));
+		ext4_error(sb, __func__,
+			   "reserved inode or inode > inodes count - "
+			   "block_group = %lu, inode=%lu", group,
+			   ino + group * EXT4_INODES_PER_GROUP(sb));
+		return 1;
+	}
+	/* If we didn't allocate from within the initialized part of the inode
+	 * table then we need to initialize up to this inode. */
+	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
+
+		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
+			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
+			/* When marking the block group with
+			 * ~EXT4_BG_INODE_UNINIT we don't want to depend
+			 * on the value of bg_itable_unused even though
+			 * mke2fs could have initialized the same for us.
+			 * Instead we calculated the value below
+			 */
+
+			free = 0;
+		} else {
+			free = EXT4_INODES_PER_GROUP(sb) -
+				le16_to_cpu(gdp->bg_itable_unused);
+		}
+
+		/*
+		 * Check the relative inode number against the last used
+		 * relative inode number in this group. if it is greater
+		 * we need to  update the bg_itable_unused count
+		 *
+		 */
+		if (ino > free)
+			gdp->bg_itable_unused =
+				cpu_to_le16(EXT4_INODES_PER_GROUP(sb) - ino);
+	}
+	le16_add_cpu(&gdp->bg_free_inodes_count, -1);
+	if (S_ISDIR(mode)) {
+		le16_add_cpu(&gdp->bg_used_dirs_count, 1);
+	}
+	gdp->bg_checksum = ext4_group_desc_csum(sbi, group, gdp);
+err_ret:
+	spin_unlock(sb_bgl_lock(sbi, group));
+	return retval;
+}
+
+/*
  * There are two policies for allocating an inode.  If the new inode is
  * a directory, then a forward search is made for a block group with both
  * free space and a low directory-to-inode ratio; if that fails, then of

@@ -649,8 +720,12 @@ repeat_in_this_group:
 			if (err)
 				goto fail;
 
-			if (!ext4_set_bit_atomic(sb_bgl_lock(sbi, group),
-						ino, bitmap_bh->b_data)) {
+			BUFFER_TRACE(bh2, "get_write_access");
+			err = ext4_journal_get_write_access(handle, bh2);
+			if (err)
+				goto fail;
+			if (!ext4_claim_inode(sb, bitmap_bh,
+						ino, group, mode)) {
 				/* we won it */
 				BUFFER_TRACE(bitmap_bh,
 					"call ext4_journal_dirty_metadata");

@@ -658,10 +733,13 @@ repeat_in_this_group:
 								bitmap_bh);
 				if (err)
 					goto fail;
+				/* zero bit is inode number 1*/
+				ino++;
 				goto got;
 			}
 			/* we lost it */
 			jbd2_journal_release_buffer(handle, bitmap_bh);
+			jbd2_journal_release_buffer(handle, bh2);
 
 			if (++ino < EXT4_INODES_PER_GROUP(sb))
 				goto repeat_in_this_group;

@@ -681,21 +759,6 @@ repeat_in_this_group:
 	goto out;
 
 got:
-	ino++;
-	if ((group == 0 && ino < EXT4_FIRST_INO(sb)) ||
-	    ino > EXT4_INODES_PER_GROUP(sb)) {
-		ext4_error(sb, __func__,
-			   "reserved inode or inode > inodes count - "
-			   "block_group = %lu, inode=%lu", group,
-			   ino + group * EXT4_INODES_PER_GROUP(sb));
-		err = -EIO;
-		goto fail;
-	}
-
-	BUFFER_TRACE(bh2, "get_write_access");
-	err = ext4_journal_get_write_access(handle, bh2);
-	if (err) goto fail;
-
 	/* We may have to initialize the block bitmap if it isn't already */
 	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM) &&
 	    gdp->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {

@@ -730,47 +793,10 @@ got:
 		if (err)
 			goto fail;
 	}
-
-	spin_lock(sb_bgl_lock(sbi, group));
-	/* If we didn't allocate from within the initialized part of the inode
-	 * table then we need to initialize up to this inode. */
-	if (EXT4_HAS_RO_COMPAT_FEATURE(sb, EXT4_FEATURE_RO_COMPAT_GDT_CSUM)) {
-		if (gdp->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
-			gdp->bg_flags &= cpu_to_le16(~EXT4_BG_INODE_UNINIT);
-
-			/* When marking the block group with
-			 * ~EXT4_BG_INODE_UNINIT we don't want to depend
-			 * on the value of bg_itable_unused even though
-			 * mke2fs could have initialized the same for us.
-			 * Instead we calculated the value below
-			 */
-
-			free = 0;
-		} else {
-			free = EXT4_INODES_PER_GROUP(sb) -
-				le16_to_cpu(gdp->bg_itable_unused);
-		}
-
-		/*
-		 * Check the relative inode number against the last used
-		 * relative inode number in this group. if it is greater
-		 * we need to  update the bg_itable_unused count
-		 *
-		 */
-		if (ino > free)
-			gdp->bg_itable_unused =
-				cpu_to_le16(EXT4_INODES_PER_GROUP(sb) - ino);
-	}

@@ -329,6 +329,7 @@ enum jbd_state_bits {
 	BH_State,		/* Pins most journal_head state */
 	BH_JournalHead,		/* Pins bh->b_private and jh->b_bh */
 	BH_Unshadow,		/* Dummy bit, for BJ_Shadow wakeup filtering */
+	BH_JBDPrivateStart,	/* First bit available for private use by FS */
 };
 
 BUFFER_FNS(JBD, jbd)

@@ -319,18 +319,41 @@ ext4_read_block_bitmap(struct super_bloc
 			    block_group, bitmap_blk);
 		return NULL;
 	}
-	if (bh_uptodate_or_lock(bh))
+
+	if (bitmap_uptodate(bh))
 		return bh;
 
+	lock_buffer(bh);
+	if (bitmap_uptodate(bh)) {
+		unlock_buffer(bh);
+		return bh;
+	}
 	spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 		ext4_init_block_bitmap(sb, bh, block_group, desc);
+		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
 		spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
 		return bh;
 	}
 	spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+	if (buffer_uptodate(bh)) {
+		/*
+		 * if not uninit if bh is uptodate,
+		 * bitmap is also uptodate
+		 */
+		set_bitmap_uptodate(bh);
+		unlock_buffer(bh);
+		return bh;
+	}
+	/*
+	 * submit the buffer_head for read. We can
+	 * safely mark the bitmap as uptodate now.
+	 * We do it here so the bitmap uptodate bit
+	 * get set with buffer lock held.
+	 */
+	set_bitmap_uptodate(bh);
 	if (bh_submit_read(bh) < 0) {
 		put_bh(bh);
 		ext4_error(sb, __func__,

@@ -19,6 +19,7 @@
 #include <linux/types.h>
 #include <linux/blkdev.h>
 #include <linux/magic.h>
+#include <linux/jbd2.h>
 #include "ext4_i.h"
 
 /*

@@ -1250,6 +1251,23 @@ extern int ext4_get_blocks_wrap(handle_t
 			sector_t block, unsigned long max_blocks,
 			struct buffer_head *bh, int create,
 			int extend_disksize, int flag);
+/*
+ * Add new method to test wether block and inode bitmaps are properly
+ * initialized. With uninit_bg reading the block from disk is not enough
+ * to mark the bitmap uptodate. We need to also zero-out the bitmap
+ */
+#define BH_BITMAP_UPTODATE BH_JBDPrivateStart
+
+static inline int bitmap_uptodate(struct buffer_head *bh)
+{
+	return (buffer_uptodate(bh) &&
+		test_bit(BH_BITMAP_UPTODATE, &(bh)->b_state));
+}
+static inline void set_bitmap_uptodate(struct buffer_head *bh)
+{
+	set_bit(BH_BITMAP_UPTODATE, &(bh)->b_state);
+}
+
 #endif	/* __KERNEL__ */
 
 #endif	/* _EXT4_H */

@@ -115,18 +115,40 @@ ext4_read_inode_bitmap(struct super_bloc
 			    block_group, bitmap_blk);
 		return NULL;
 	}
-	if (bh_uptodate_or_lock(bh))
+	if (bitmap_uptodate(bh))
 		return bh;
 
+	lock_buffer(bh);
+	if (bitmap_uptodate(bh)) {
+		unlock_buffer(bh);
+		return bh;
+	}
 	spin_lock(sb_bgl_lock(EXT4_SB(sb), block_group));
 	if (desc->bg_flags & cpu_to_le16(EXT4_BG_INODE_UNINIT)) {
 		ext4_init_inode_bitmap(sb, bh, block_group, desc);
+		set_bitmap_uptodate(bh);
 		set_buffer_uptodate(bh);
 		unlock_buffer(bh);
 		spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
 		return bh;
 	}
 	spin_unlock(sb_bgl_lock(EXT4_SB(sb), block_group));
+	if (buffer_uptodate(bh)) {
+		/*
+		 * if not uninit if bh is uptodate,
+		 * bitmap is also uptodate
+		 */
+		set_bitmap_uptodate(bh);
+		unlock_buffer(bh);
+		return bh;
+	}
+	/*
+	 * submit the buffer_head for read. We can
+	 * safely mark the bitmap as uptodate now.
+	 * We do it here so the bitmap uptodate bit
+	 * get set with buffer lock held.
+	 */
+	set_bitmap_uptodate(bh);
 	if (bh_submit_read(bh) < 0) {
 		put_bh(bh);
 		ext4_error(sb, __func__,

@@ -796,20 +796,42 @@ static int ext4_mb_init_cache(struct pag
 		if (bh[i] == NULL)
 			goto out;
 
-		if (bh_uptodate_or_lock(bh[i]))
+		if (bitmap_uptodate(bh[i]))
 			continue;
 
+ 		lock_buffer(bh[i]);
+		if (bitmap_uptodate(bh[i])) {
+			unlock_buffer(bh[i]);
+			continue;
+		}
 		spin_lock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
 		if (desc->bg_flags & cpu_to_le16(EXT4_BG_BLOCK_UNINIT)) {
 			ext4_init_block_bitmap(sb, bh[i],
 						first_group + i, desc);
+			set_bitmap_uptodate(bh[i]);
 			set_buffer_uptodate(bh[i]);
 			unlock_buffer(bh[i]);
 			spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
 			continue;
 		}
 		spin_unlock(sb_bgl_lock(EXT4_SB(sb), first_group + i));
+		if (buffer_uptodate(bh[i])) {
+			/*
+			 * if not uninit if bh is uptodate,
+			 * bitmap is also uptodate
+			 */
+			set_bitmap_uptodate(bh[i]);
+			unlock_buffer(bh[i]);
+			continue;
+		}
 		get_bh(bh[i]);
+		/*
+		 * submit the buffer_head for read. We can
+		 * safely mark the bitmap as uptodate now.
+		 * We do it here so the bitmap uptodate bit
+		 * get set with buffer lock held.
+		 */
+		set_bitmap_uptodate(bh[i]);
 		bh[i]->b_end_io = end_buffer_read_sync;
 		submit_bh(READ, bh[i]);
 		mb_debug("read bitmap for group %lu\n", first_group + i);

@@ -84,7 +84,7 @@ unsigned ext4_init_inode_bitmap(struct s
 	}
 
 	memset(bh->b_data, 0, (EXT4_INODES_PER_GROUP(sb) + 7) / 8);
-	mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), EXT4_BLOCKS_PER_GROUP(sb),
+	mark_bitmap_end(EXT4_INODES_PER_GROUP(sb), sb->s_blocksize * 8,
 			bh->b_data);
 
 	return EXT4_INODES_PER_GROUP(sb);

@@ -3148,8 +3148,8 @@ ext4_mb_mark_diskspace_used(struct ext4_
 	    in_range(block + len - 1, ext4_inode_table(sb, gdp),
 		     EXT4_SB(sb)->s_itb_per_group)) {
 		ext4_error(sb, __func__,
-			   "Allocating block in system zone - block = %llu",
-			   block);
+			   "Allocating block %llu in system zone of %d group\n",
+			   block, ac->ac_b_ex.fe_group);
 		/* File system mounted not to panic on error
 		 * Fix the bitmap and repeat the block allocation
 		 * We leak some of the blocks here.

@@ -284,11 +284,9 @@ static int setup_new_group_blocks(struct
 	if ((err = extend_or_restart_transaction(handle, 2, bh)))
 		goto exit_bh;
 
-	mark_bitmap_end(input->blocks_count, EXT4_BLOCKS_PER_GROUP(sb),
-			bh->b_data);
+	mark_bitmap_end(input->blocks_count, sb->s_blocksize * 8, bh->b_data);
 	ext4_journal_dirty_metadata(handle, bh);
 	brelse(bh);

@@ -1054,7 +1054,8 @@ static void ext4_mb_release_desc(struct 
 	if (e4b->bd_buddy_page)
 		page_cache_release(e4b->bd_buddy_page);
 	/* Done with the buddy cache */
-	up_read(e4b->alloc_semp);
+	if (e4b->alloc_semp)
+		up_read(e4b->alloc_semp);
 }
 
 

@@ -1374,7 +1375,9 @@ static void ext4_mb_use_best_found(struc
 	get_page(ac->ac_bitmap_page);
 	ac->ac_buddy_page = e4b->bd_buddy_page;
 	get_page(ac->ac_buddy_page);
-
+	/* on allocation we use ac to track the held semaphore */
+	ac->alloc_semp =  e4b->alloc_semp;
+	e4b->alloc_semp = NULL;
 	/* store last allocated for subsequent stream allocation */
 	if ((ac->ac_flags & EXT4_MB_HINT_DATA)) {
 		spin_lock(&sbi->s_md_lock);

@@ -3148,7 +3151,7 @@ ext4_mb_mark_diskspace_used(struct ext4_
 	    in_range(block + len - 1, ext4_inode_table(sb, gdp),
 		     EXT4_SB(sb)->s_itb_per_group)) {
 		ext4_error(sb, __func__,
-			   "Allocating block %llu in system zone of %d group\n",
+			   "Allocating block %llu in system zone of %lu group\n",
 			   block, ac->ac_b_ex.fe_group);
 		/* File system mounted not to panic on error
 		 * Fix the bitmap and repeat the block allocation

@@ -4399,6 +4402,7 @@ ext4_mb_initialize_context(struct ext4_a
 	ac->ac_pa = NULL;
 	ac->ac_bitmap_page = NULL;
 	ac->ac_buddy_page = NULL;
+	ac->alloc_semp = NULL;
 	ac->ac_lg = NULL;
 
 	/* we have to define context: we'll we work with a file or

@@ -4579,6 +4583,8 @@ static int ext4_mb_release_context(struc
 		}
 		ext4_mb_put_pa(ac, ac->ac_sb, pa);
 	}
+	if (ac->alloc_semp)
+		up_read(ac->alloc_semp);
 	if (ac->ac_bitmap_page)
 		page_cache_release(ac->ac_bitmap_page);
 	if (ac->ac_buddy_page)

@@ -4682,10 +4688,14 @@ repeat:
 				ac->ac_o_ex.fe_len < ac->ac_b_ex.fe_len)
 			ext4_mb_new_preallocation(ac);
 	}
-
 	if (likely(ac->ac_status == AC_STATUS_FOUND)) {
 		*errp = ext4_mb_mark_diskspace_used(ac, handle);
 		if (*errp ==  -EAGAIN) {
+			/*
+			 * drop the reference that we took
+			 * in ext4_mb_use_best_found
+			 */
+			ext4_mb_release_context(ac);
 			ac->ac_b_ex.fe_group = 0;
 			ac->ac_b_ex.fe_start = 0;
 			ac->ac_b_ex.fe_len = 0;

@@ -213,6 +213,11 @@ struct ext4_allocation_context {
 	__u8 ac_op;		/* operation, for history only */
 	struct page *ac_bitmap_page;
 	struct page *ac_buddy_page;
+	/*
+	 * pointer to the held semaphore upon successful
+	 * block allocation
+	 */
+	struct rw_semaphore *alloc_semp;
 	struct ext4_prealloc_space *ac_pa;
 	struct ext4_locality_group *ac_lg;
 };

@@ -848,6 +848,8 @@ static int ext4_mb_init_cache(struct pag
 
 	err = 0;
 	first_block = page->index * blocks_per_page;
+	/* init the page  */
+	memset(page_address(page), 0xff, PAGE_CACHE_SIZE);
 	for (i = 0; i < blocks_per_page; i++) {
 		int group;
 		struct ext4_group_info *grinfo;

@@ -874,7 +876,6 @@ static int ext4_mb_init_cache(struct pag
 			BUG_ON(incore == NULL);
 			mb_debug("put buddy for group %u in page %lu/%x\n",
 				group, page->index, i * blocksize);
-			memset(data, 0xff, blocksize);
 			grinfo = ext4_get_group_info(sb, group);
 			grinfo->bb_fragments = 0;
 			memset(grinfo->bb_counters, 0,

@@ -1916,8 +1916,8 @@ static int ext4_fill_super(struct super_
 	struct inode *root;
 	int ret = -EINVAL;
 	int blocksize;
-	int db_count;
-	int i;
+	unsigned int db_count;
+	unsigned int i;
 	int needs_recovery;
 	__le32 features;
 	__u64 blocks_count;

@@ -2207,20 +2207,30 @@ static int ext4_fill_super(struct super_
 	if (EXT4_BLOCKS_PER_GROUP(sb) == 0)
 		goto cantfind_ext4;
 
-	/* ensure blocks_count calculation below doesn't sign-extend */
-	if (ext4_blocks_count(es) + EXT4_BLOCKS_PER_GROUP(sb) <
-	    le32_to_cpu(es->s_first_data_block) + 1) {
-		printk(KERN_WARNING "EXT4-fs: bad geometry: block count %llu, "
-		       "first data block %u, blocks per group %lu\n",
-			ext4_blocks_count(es),
-			le32_to_cpu(es->s_first_data_block),
-			EXT4_BLOCKS_PER_GROUP(sb));
+	/*
+	 * It makes no sense for the first data block to be beyond the end
+	 * of the filesystem.
+	 */
+	if (le32_to_cpu(es->s_first_data_block) >= ext4_blocks_count(es)) {
+		printk(KERN_WARNING "EXT4-fs: bad geometry: first data"
+		       "block %u is beyond end of filesystem (%llu)\n",
+		       le32_to_cpu(es->s_first_data_block),
+		       ext4_blocks_count(es));
 		goto failed_mount;
 	}
 	blocks_count = (ext4_blocks_count(es) -
 			le32_to_cpu(es->s_first_data_block) +
 			EXT4_BLOCKS_PER_GROUP(sb) - 1);
 	do_div(blocks_count, EXT4_BLOCKS_PER_GROUP(sb));
+	if (blocks_count > ((uint64_t)1<<32) - EXT4_DESC_PER_BLOCK(sb)) {
+		printk(KERN_WARNING "EXT4-fs: groups count too large: %u "
+		       "(block count %llu, first data block %u, "
+		       "blocks per group %lu)\n", sbi->s_groups_count,
+		       ext4_blocks_count(es),
+		       le32_to_cpu(es->s_first_data_block),
+		       EXT4_BLOCKS_PER_GROUP(sb));
+		goto failed_mount;
+	}
 	sbi->s_groups_count = blocks_count;
 	db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
 		   EXT4_DESC_PER_BLOCK(sb);

@@ -1174,8 +1174,11 @@ static inline void ext4_r_blocks_count_s
 
 static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
 {
-	return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
-		le32_to_cpu(raw_inode->i_size_lo);
+	if (S_ISREG(le16_to_cpu(raw_inode->i_mode)))
+		return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
+			le32_to_cpu(raw_inode->i_size_lo);
+	else
+		return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
 }
 
 static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)

@@ -351,9 +351,9 @@ static int ext4_block_to_path(struct ino
 		final = ptrs;
 	} else {
 		ext4_warning(inode->i_sb, "ext4_block_to_path",
-				"block %lu > max",
+				"block %lu > max in inode %lu",
 				i_block + direct_blocks +
-				indirect_blocks + double_blocks);
+				indirect_blocks + double_blocks, inode->i_ino);
 	}
 	if (boundary)
 		*boundary = final - 1 - (i_block & (ptrs - 1));

@@ -1382,7 +1382,7 @@ static int make_indexed_dir(handle_t *ha
 	struct fake_dirent *fde;
 
 	blocksize =  dir->i_sb->s_blocksize;
-	dxtrace(printk("Creating index\n"));
+	dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
 	retval = ext4_journal_get_write_access(handle, bh);
 	if (retval) {
 		ext4_std_error(dir->i_sb, retval);

@@ -1391,6 +1391,20 @@ static int make_indexed_dir(handle_t *ha
 	}
 	root = (struct dx_root *) bh->b_data;
 
+	/* The 0th block becomes the root, move the dirents out */
+	fde = &root->dotdot;
+	de = (struct ext4_dir_entry_2 *)((char *)fde +
+		ext4_rec_len_from_disk(fde->rec_len));
+	if ((char *) de >= (((char *) root) + blocksize)) {
+		ext4_error(dir->i_sb, __func__,
+			   "invalid rec_len for '..' in inode %lu",
+			   dir->i_ino);
+		brelse(bh);
+		return -EIO;
+	}
+	len = ((char *) root) + blocksize - (char *) de;
+
+	/* Allocate new block for the 0th block's dirents */
 	bh2 = ext4_append (handle, dir, &block, &retval);
 	if (!(bh2)) {
 		brelse(bh);

@@ -1399,11 +1413,6 @@ static int make_indexed_dir(handle_t *ha
 	EXT4_I(dir)->i_flags |= EXT4_INDEX_FL;
 	data1 = bh2->b_data;
 
-	/* The 0th block becomes the root, move the dirents out */
-	fde = &root->dotdot;
-	de = (struct ext4_dir_entry_2 *)((char *)fde +
-		ext4_rec_len_from_disk(fde->rec_len));
-	len = ((char *) root) + blocksize - (char *) de;
 	memcpy (data1, de, len);
 	de = (struct ext4_dir_entry_2 *) data1;
 	top = data1 + len;

@@ -308,7 +308,8 @@ void buffer_assertion_failure(struct buf
 		int val = (expr);					     \
 		if (!val) {						     \
 			printk(KERN_ERR					     \
-				"EXT3-fs unexpected failure: %s;\n",# expr); \
+			       "JBD2 unexpected failure: %s: %s;\n",	     \
+			       __func__, #expr);			     \
 			printk(KERN_ERR why "\n");			     \
 		}							     \
 		val;							     \

@@ -860,11 +860,13 @@ int ext4_group_add(struct super_block *s
 	gdp = (struct ext4_group_desc *)((char *)primary->b_data +
 					 gdb_off * EXT4_DESC_SIZE(sb));
 
+	memset(gdp, 0, EXT4_DESC_SIZE(sb));
 	ext4_block_bitmap_set(sb, gdp, input->block_bitmap); /* LV FIXME */
 	ext4_inode_bitmap_set(sb, gdp, input->inode_bitmap); /* LV FIXME */
 	ext4_inode_table_set(sb, gdp, input->inode_table); /* LV FIXME */
 	gdp->bg_free_blocks_count = cpu_to_le16(input->free_blocks_count);
 	gdp->bg_free_inodes_count = cpu_to_le16(EXT4_INODES_PER_GROUP(sb));
+	gdp->bg_flags = cpu_to_le16(EXT4_BG_INODE_ZEROED);
 	gdp->bg_checksum = ext4_group_desc_csum(sbi, input->group, gdp);
 
 	/*