24 files changed, 257 insertions, 175 deletions

diff --git a/fs/afs/file.c b/fs/afs/file.c
index 0d576987ec6..4975c9c193d 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -291,8 +291,8 @@ static int afs_file_releasepage(struct page *page, gfp_t gfp_flags)
 		cachefs_uncache_page(vnode->cache, page);
 #endif
 
-		pageio = (struct cachefs_page *) page->private;
-		page->private = 0;
+		pageio = (struct cachefs_page *) page_private(page);
+		set_page_private(page, 0);
 		ClearPagePrivate(page);
 
 		if (pageio)
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index dd9baabaf01..72011826f0c 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -318,7 +318,6 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 	current->mm->free_area_cache = current->mm->mmap_base;
 	current->mm->cached_hole_size = 0;
 
-	set_mm_counter(current->mm, rss, 0);
 	current->mm->mmap = NULL;
 	compute_creds(bprm);
  	current->flags &= ~PF_FORKNOEXEC;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index d4b15576e58..918ccc267e4 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -773,7 +773,6 @@ static int load_elf_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 
 	/* Do this so that we can load the interpreter, if need be.  We will
 	   change some of these later */
-	set_mm_counter(current->mm, rss, 0);
 	current->mm->free_area_cache = current->mm->mmap_base;
 	current->mm->cached_hole_size = 0;
 	retval = setup_arg_pages(bprm, randomize_stack_top(STACK_TOP),
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 134c9c0d1f5..dda87c4c82a 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -294,14 +294,7 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, struct pt_regs *regs
 				  &interp_params,
 				  &current->mm->start_stack,
 				  &current->mm->start_brk);
-#endif
-
-	/* do this so that we can load the interpreter, if need be
-	 * - we will change some of these later
-	 */
-	set_mm_counter(current->mm, rss, 0);
 
-#ifdef CONFIG_MMU
 	retval = setup_arg_pages(bprm, current->mm->start_stack, executable_stack);
 	if (retval < 0) {
 		send_sig(SIGKILL, current, 0);
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 7974efa107b..9d6625829b9 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -650,7 +650,6 @@ static int load_flat_file(struct linux_binprm * bprm,
 		current->mm->start_brk = datapos + data_len + bss_len;
 		current->mm->brk = (current->mm->start_brk + 3) & ~3;
 		current->mm->context.end_brk = memp + ksize((void *) memp) - stack_len;
-		set_mm_counter(current->mm, rss, 0);
 	}
 
 	if (flags & FLAT_FLAG_KTRACE)
diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c
index 227a2682d2b..00a91dc25d1 100644
--- a/fs/binfmt_som.c
+++ b/fs/binfmt_som.c
@@ -259,7 +259,6 @@ load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 	create_som_tables(bprm);
 
 	current->mm->start_stack = bprm->p;
-	set_mm_counter(current->mm, rss, 0);
 
 #if 0
 	printk("(start_brk) %08lx\n" , (unsigned long) current->mm->start_brk);
diff --git a/fs/buffer.c b/fs/buffer.c
index b1667986442..2066e4cb700 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -96,7 +96,7 @@ static void
 __clear_page_buffers(struct page *page)
 {
 	ClearPagePrivate(page);
-	page->private = 0;
+	set_page_private(page, 0);
 	page_cache_release(page);
 }
 
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index 3d1cce3653b..6a3df88accf 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -370,8 +370,8 @@ static int init_coda_psdev(void)
 	}		
 	devfs_mk_dir ("coda");
 	for (i = 0; i < MAX_CODADEVS; i++) {
-		class_device_create(coda_psdev_class, MKDEV(CODA_PSDEV_MAJOR,i),
-				NULL, "cfs%d", i);
+		class_device_create(coda_psdev_class, NULL,
+				MKDEV(CODA_PSDEV_MAJOR,i), NULL, "cfs%d", i);
 		err = devfs_mk_cdev(MKDEV(CODA_PSDEV_MAJOR, i),
 				S_IFCHR|S_IRUSR|S_IWUSR, "coda/%d", i);
 		if (err)
diff --git a/fs/compat.c b/fs/compat.c
index a719e158e00..8e71cdbecc7 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -1490,7 +1490,6 @@ int compat_do_execve(char * filename,
 		/* execve success */
 		security_bprm_free(bprm);
 		acct_update_integrals(current);
-		update_mem_hiwater(current);
 		kfree(bprm);
 		return retval;
 	}
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index e28a74203f3..a327e03753a 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -3050,6 +3050,7 @@ HANDLE_IOCTL(TIOCSSERIAL, serial_struct_ioctl)
 HANDLE_IOCTL(USBDEVFS_CONTROL32, do_usbdevfs_control)
 HANDLE_IOCTL(USBDEVFS_BULK32, do_usbdevfs_bulk)
 HANDLE_IOCTL(USBDEVFS_DISCSIGNAL32, do_usbdevfs_discsignal)
+COMPATIBLE_IOCTL(USBDEVFS_IOCTL32)
 /* i2c */
 HANDLE_IOCTL(I2C_FUNCS, w_long)
 HANDLE_IOCTL(I2C_RDWR, do_i2c_rdwr_ioctl)
diff --git a/fs/direct-io.c b/fs/direct-io.c
index 0d06097bc99..3931e7f1e6b 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -162,6 +162,7 @@ static int dio_refill_pages(struct dio *dio)
 	up_read(&current->mm->mmap_sem);
 
 	if (ret < 0 && dio->blocks_available && (dio->rw == WRITE)) {
+		struct page *page = ZERO_PAGE(dio->curr_user_address);
 		/*
 		 * A memory fault, but the filesystem has some outstanding
 		 * mapped blocks.  We need to use those blocks up to avoid
@@ -169,7 +170,8 @@ static int dio_refill_pages(struct dio *dio)
 		 */
 		if (dio->page_errors == 0)
 			dio->page_errors = ret;
-		dio->pages[0] = ZERO_PAGE(dio->curr_user_address);
+		page_cache_get(page);
+		dio->pages[0] = page;
 		dio->head = 0;
 		dio->tail = 1;
 		ret = 0;
diff --git a/fs/exec.c b/fs/exec.c
index d2208f7c87d..ba73797eb4c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -309,40 +309,36 @@ void install_arg_page(struct vm_area_struct *vma,
 	pud_t * pud;
 	pmd_t * pmd;
 	pte_t * pte;
+	spinlock_t *ptl;
 
 	if (unlikely(anon_vma_prepare(vma)))
-		goto out_sig;
+		goto out;
 
 	flush_dcache_page(page);
 	pgd = pgd_offset(mm, address);
-
-	spin_lock(&mm->page_table_lock);
 	pud = pud_alloc(mm, pgd, address);
 	if (!pud)
 		goto out;
 	pmd = pmd_alloc(mm, pud, address);
 	if (!pmd)
 		goto out;
-	pte = pte_alloc_map(mm, pmd, address);
+	pte = pte_alloc_map_lock(mm, pmd, address, &ptl);
 	if (!pte)
 		goto out;
 	if (!pte_none(*pte)) {
-		pte_unmap(pte);
+		pte_unmap_unlock(pte, ptl);
 		goto out;
 	}
-	inc_mm_counter(mm, rss);
+	inc_mm_counter(mm, anon_rss);
 	lru_cache_add_active(page);
 	set_pte_at(mm, address, pte, pte_mkdirty(pte_mkwrite(mk_pte(
 					page, vma->vm_page_prot))));
 	page_add_anon_rmap(page, vma, address);
-	pte_unmap(pte);
-	spin_unlock(&mm->page_table_lock);
+	pte_unmap_unlock(pte, ptl);
 
 	/* no need for flush_tlb */
 	return;
 out:
-	spin_unlock(&mm->page_table_lock);
-out_sig:
 	__free_page(page);
 	force_sig(SIGKILL, current);
 }
@@ -1207,7 +1203,6 @@ int do_execve(char * filename,
 		/* execve success */
 		security_bprm_free(bprm);
 		acct_update_integrals(current);
-		update_mem_hiwater(current);
 		kfree(bprm);
 		return retval;
 	}
diff --git a/fs/ext3/super.c b/fs/ext3/super.c
index 9e24ceb019f..097383c1115 100644
--- a/fs/ext3/super.c
+++ b/fs/ext3/super.c
@@ -510,19 +510,11 @@ static void ext3_clear_inode(struct inode *inode)
 	kfree(rsv);
 }
 
-static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
+static inline void ext3_show_quota_options(struct seq_file *seq, struct super_block *sb)
 {
-	struct super_block *sb = vfs->mnt_sb;
+#if defined(CONFIG_QUOTA)
 	struct ext3_sb_info *sbi = EXT3_SB(sb);
 
-	if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA)
-		seq_puts(seq, ",data=journal");
-	else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA)
-		seq_puts(seq, ",data=ordered");
-	else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
-		seq_puts(seq, ",data=writeback");
-
-#if defined(CONFIG_QUOTA)
 	if (sbi->s_jquota_fmt)
 		seq_printf(seq, ",jqfmt=%s",
 		(sbi->s_jquota_fmt == QFMT_VFS_OLD) ? "vfsold": "vfsv0");
@@ -539,6 +531,20 @@ static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
 	if (sbi->s_mount_opt & EXT3_MOUNT_GRPQUOTA)
 		seq_puts(seq, ",grpquota");
 #endif
+}
+
+static int ext3_show_options(struct seq_file *seq, struct vfsmount *vfs)
+{
+	struct super_block *sb = vfs->mnt_sb;
+
+	if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_JOURNAL_DATA)
+		seq_puts(seq, ",data=journal");
+	else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_ORDERED_DATA)
+		seq_puts(seq, ",data=ordered");
+	else if (test_opt(sb, DATA_FLAGS) == EXT3_MOUNT_WRITEBACK_DATA)
+		seq_puts(seq, ",data=writeback");
+
+	ext3_show_quota_options(seq, sb);
 
 	return 0;
 }
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 3a9b6d179cb..e026c807e6b 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -45,10 +45,58 @@ static struct backing_dev_info hugetlbfs_backing_dev_info = {
 
 int sysctl_hugetlb_shm_group;
 
+static void huge_pagevec_release(struct pagevec *pvec)
+{
+	int i;
+
+	for (i = 0; i < pagevec_count(pvec); ++i)
+		put_page(pvec->pages[i]);
+
+	pagevec_reinit(pvec);
+}
+
+/*
+ * huge_pages_needed tries to determine the number of new huge pages that
+ * will be required to fully populate this VMA.  This will be equal to
+ * the size of the VMA in huge pages minus the number of huge pages
+ * (covered by this VMA) that are found in the page cache.
+ *
+ * Result is in bytes to be compatible with is_hugepage_mem_enough()
+ */
+unsigned long
+huge_pages_needed(struct address_space *mapping, struct vm_area_struct *vma)
+{
+	int i;
+	struct pagevec pvec;
+	unsigned long start = vma->vm_start;
+	unsigned long end = vma->vm_end;
+	unsigned long hugepages = (end - start) >> HPAGE_SHIFT;
+	pgoff_t next = vma->vm_pgoff;
+	pgoff_t endpg = next + ((end - start) >> PAGE_SHIFT);
+
+	pagevec_init(&pvec, 0);
+	while (next < endpg) {
+		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE))
+			break;
+		for (i = 0; i < pagevec_count(&pvec); i++) {
+			struct page *page = pvec.pages[i];
+			if (page->index > next)
+				next = page->index;
+			if (page->index >= endpg)
+				break;
+			next++;
+			hugepages--;
+		}
+		huge_pagevec_release(&pvec);
+	}
+	return hugepages << HPAGE_SHIFT;
+}
+
 static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_dentry->d_inode;
 	struct address_space *mapping = inode->i_mapping;
+	unsigned long bytes;
 	loff_t len, vma_len;
 	int ret;
 
@@ -67,6 +115,10 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (vma->vm_end - vma->vm_start < HPAGE_SIZE)
 		return -EINVAL;
 
+	bytes = huge_pages_needed(mapping, vma);
+	if (!is_hugepage_mem_enough(bytes))
+		return -ENOMEM;
+
 	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
 
 	down(&inode->i_sem);
@@ -79,10 +131,8 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (!(vma->vm_flags & VM_WRITE) && len > inode->i_size)
 		goto out;
 
-	ret = hugetlb_prefault(mapping, vma);
-	if (ret)
-		goto out;
-
+	ret = 0;
+	hugetlb_prefault_arch_hook(vma->vm_mm);
 	if (inode->i_size < len)
 		inode->i_size = len;
 out:
@@ -92,7 +142,7 @@ out:
 }
 
 /*
- * Called under down_write(mmap_sem), page_table_lock is not held
+ * Called under down_write(mmap_sem).
  */
 
 #ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
@@ -171,16 +221,6 @@ static int hugetlbfs_commit_write(struct file *file,
 	return -EINVAL;
 }
 
-static void huge_pagevec_release(struct pagevec *pvec)
-{
-	int i;
-
-	for (i = 0; i < pagevec_count(pvec); ++i)
-		put_page(pvec->pages[i]);
-
-	pagevec_reinit(pvec);
-}
-
 static void truncate_huge_page(struct page *page)
 {
 	clear_page_dirty(page);
@@ -224,52 +264,35 @@ static void truncate_hugepages(struct address_space *mapping, loff_t lstart)
 
 static void hugetlbfs_delete_inode(struct inode *inode)
 {
-	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(inode->i_sb);
-
-	hlist_del_init(&inode->i_hash);
-	list_del_init(&inode->i_list);
-	list_del_init(&inode->i_sb_list);
-	inode->i_state |= I_FREEING;
-	inodes_stat.nr_inodes--;
-	spin_unlock(&inode_lock);
-
 	if (inode->i_data.nrpages)
 		truncate_hugepages(&inode->i_data, 0);
-
-	security_inode_delete(inode);
-
-	if (sbinfo->free_inodes >= 0) {
-		spin_lock(&sbinfo->stat_lock);
-		sbinfo->free_inodes++;
-		spin_unlock(&sbinfo->stat_lock);
-	}
-
 	clear_inode(inode);
-	destroy_inode(inode);
 }
 
 static void hugetlbfs_forget_inode(struct inode *inode)
 {
-	struct super_block *super_block = inode->i_sb;
-	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(super_block);
+	struct super_block *sb = inode->i_sb;
 
-	if (hlist_unhashed(&inode->i_hash))
-		goto out_truncate;
-
-	if (!(inode->i_state & (I_DIRTY|I_LOCK))) {
-		list_del(&inode->i_list);
-		list_add(&inode->i_list, &inode_unused);
-	}
-	inodes_stat.nr_unused++;
-	if (!super_block || (super_block->s_flags & MS_ACTIVE)) {
+	if (!hlist_unhashed(&inode->i_hash)) {
+		if (!(inode->i_state & (I_DIRTY|I_LOCK)))
+			list_move(&inode->i_list, &inode_unused);
+		inodes_stat.nr_unused++;
+		if (!sb || (sb->s_flags & MS_ACTIVE)) {
+			spin_unlock(&inode_lock);
+			return;
+		}
+		inode->i_state |= I_WILL_FREE;
 		spin_unlock(&inode_lock);
-		return;
+		/*
+		 * write_inode_now is a noop as we set BDI_CAP_NO_WRITEBACK
+		 * in our backing_dev_info.
+		 */
+		write_inode_now(inode, 1);
+		spin_lock(&inode_lock);
+		inode->i_state &= ~I_WILL_FREE;
+		inodes_stat.nr_unused--;
+		hlist_del_init(&inode->i_hash);
 	}
-
-	/* write_inode_now() ? */
-	inodes_stat.nr_unused--;
-	hlist_del_init(&inode->i_hash);
-out_truncate:
 	list_del_init(&inode->i_list);
 	list_del_init(&inode->i_sb_list);
 	inode->i_state |= I_FREEING;
@@ -277,13 +300,6 @@ out_truncate:
 	spin_unlock(&inode_lock);
 	if (inode->i_data.nrpages)
 		truncate_hugepages(&inode->i_data, 0);
-
-	if (sbinfo->free_inodes >= 0) {
-		spin_lock(&sbinfo->stat_lock);
-		sbinfo->free_inodes++;
-		spin_unlock(&sbinfo->stat_lock);
-	}
-
 	clear_inode(inode);
 	destroy_inode(inode);
 }
@@ -291,7 +307,7 @@ out_truncate:
 static void hugetlbfs_drop_inode(struct inode *inode)
 {
 	if (!inode->i_nlink)
-		hugetlbfs_delete_inode(inode);
+		generic_delete_inode(inode);
 	else
 		hugetlbfs_forget_inode(inode);
 }
@@ -308,7 +324,6 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, unsigned long h_pgoff)
 
 	vma_prio_tree_foreach(vma, &iter, root, h_pgoff, ULONG_MAX) {
 		unsigned long h_vm_pgoff;
-		unsigned long v_length;
 		unsigned long v_offset;
 
 		h_vm_pgoff = vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT);
@@ -319,11 +334,8 @@ hugetlb_vmtruncate_list(struct prio_tree_root *root, unsigned long h_pgoff)
 		if (h_vm_pgoff >= h_pgoff)
 			v_offset = 0;
 
-		v_length = vma->vm_end - vma->vm_start;
-
-		zap_hugepage_range(vma,
-				vma->vm_start + v_offset,
-				v_length - v_offset);
+		unmap_hugepage_range(vma,
+				vma->vm_start + v_offset, vma->vm_end);
 	}
 }
 
@@ -379,17 +391,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid,
 					gid_t gid, int mode, dev_t dev)
 {
 	struct inode *inode;
-	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(sb);
-
-	if (sbinfo->free_inodes >= 0) {
-		spin_lock(&sbinfo->stat_lock);
-		if (!sbinfo->free_inodes) {
-			spin_unlock(&sbinfo->stat_lock);
-			return NULL;
-		}
-		sbinfo->free_inodes--;
-		spin_unlock(&sbinfo->stat_lock);
-	}
 
 	inode = new_inode(sb);
 	if (inode) {
@@ -531,29 +532,51 @@ static void hugetlbfs_put_super(struct super_block *sb)
 	}
 }
 
+static inline int hugetlbfs_dec_free_inodes(struct hugetlbfs_sb_info *sbinfo)
+{
+	if (sbinfo->free_inodes >= 0) {
+		spin_lock(&sbinfo->stat_lock);
+		if (unlikely(!sbinfo->free_inodes)) {
+			spin_unlock(&sbinfo->stat_lock);
+			return 0;
+		}
+		sbinfo->free_inodes--;
+		spin_unlock(&sbinfo->stat_lock);
+	}
+
+	return 1;
+}
+
+static void hugetlbfs_inc_free_inodes(struct hugetlbfs_sb_info *sbinfo)
+{
+	if (sbinfo->free_inodes >= 0) {
+		spin_lock(&sbinfo->stat_lock);
+		sbinfo->free_inodes++;
+		spin_unlock(&sbinfo->stat_lock);
+	}
+}
+
+
 static kmem_cache_t *hugetlbfs_inode_cachep;
 
 static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
 {
+	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(sb);
 	struct hugetlbfs_inode_info *p;
 
+	if (unlikely(!hugetlbfs_dec_free_inodes(sbinfo)))
+		return NULL;
 	p = kmem_cache_alloc(hugetlbfs_inode_cachep, SLAB_KERNEL);
-	if (!p)
+	if (unlikely(!p)) {
+		hugetlbfs_inc_free_inodes(sbinfo);
 		return NULL;
+	}
 	return &p->vfs_inode;
 }
 
-static void init_once(void *foo, kmem_cache_t *cachep, unsigned long flags)
-{
-	struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo;
-
-	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
-	    SLAB_CTOR_CONSTRUCTOR)
-		inode_init_once(&ei->vfs_inode);
-}
-
 static void hugetlbfs_destroy_inode(struct inode *inode)
 {
+	hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb));
 	mpol_free_shared_policy(&HUGETLBFS_I(inode)->policy);
 	kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
 }
@@ -565,6 +588,16 @@ static struct address_space_operations hugetlbfs_aops = {
 	.set_page_dirty	= hugetlbfs_set_page_dirty,
 };
 
+
+static void init_once(void *foo, kmem_cache_t *cachep, unsigned long flags)
+{
+	struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo;
+
+	if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
+	    SLAB_CTOR_CONSTRUCTOR)
+		inode_init_once(&ei->vfs_inode);
+}
+
 struct file_operations hugetlbfs_file_operations = {
 	.mmap			= hugetlbfs_file_mmap,
 	.fsync			= simple_sync_file,
@@ -592,6 +625,7 @@ static struct super_operations hugetlbfs_ops = {
 	.alloc_inode    = hugetlbfs_alloc_inode,
 	.destroy_inode  = hugetlbfs_destroy_inode,
 	.statfs		= hugetlbfs_statfs,
+	.delete_inode	= hugetlbfs_delete_inode,
 	.drop_inode	= hugetlbfs_drop_inode,
 	.put_super	= hugetlbfs_put_super,
 };
diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
index eadf319bee2..68000a50ceb 100644
--- a/fs/jfs/jfs_dmap.c
+++ b/fs/jfs/jfs_dmap.c
@@ -74,7 +74,7 @@
 static void dbAllocBits(struct bmap * bmp, struct dmap * dp, s64 blkno,
 			int nblocks);
 static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval);
-static void dbBackSplit(dmtree_t * tp, int leafno);
+static int dbBackSplit(dmtree_t * tp, int leafno);
 static int dbJoin(dmtree_t * tp, int leafno, int newval);
 static void dbAdjTree(dmtree_t * tp, int leafno, int newval);
 static int dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc,
@@ -305,7 +305,6 @@ int dbSync(struct inode *ipbmap)
 	filemap_fdatawrite(ipbmap->i_mapping);
 	filemap_fdatawait(ipbmap->i_mapping);
 
-	ipbmap->i_state |= I_DIRTY;
 	diWriteSpecial(ipbmap, 0);
 
 	return (0);
@@ -2467,7 +2466,9 @@ dbAdjCtl(struct bmap * bmp, s64 blkno, int newval, int alloc, int level)
 		 * that it is at the front of a binary buddy system.
 		 */
 		if (oldval == NOFREE) {
-			dbBackSplit((dmtree_t *) dcp, leafno);
+			rc = dbBackSplit((dmtree_t *) dcp, leafno);
+			if (rc)
+				return rc;
 			oldval = dcp->stree[ti];
 		}
 		dbSplit((dmtree_t *) dcp, leafno, dcp->budmin, newval);
@@ -2627,7 +2628,7 @@ static void dbSplit(dmtree_t * tp, int leafno, int splitsz, int newval)
  *
  * serialization: IREAD_LOCK(ipbmap) or IWRITE_LOCK(ipbmap) held on entry/exit;
  */
-static void dbBackSplit(dmtree_t * tp, int leafno)
+static int dbBackSplit(dmtree_t * tp, int leafno)
 {
 	int budsz, bud, w, bsz, size;
 	int cursz;
@@ -2662,7 +2663,10 @@ static void dbBackSplit(dmtree_t * tp, int leafno)
 		 */
 		for (w = leafno, bsz = budsz;; bsz <<= 1,
 		     w = (w < bud) ? w : bud) {
-			assert(bsz < le32_to_cpu(tp->dmt_nleafs));
+			if (bsz >= le32_to_cpu(tp->dmt_nleafs)) {
+				jfs_err("JFS: block map error in dbBackSplit");
+				return -EIO;
+			}
 
 			/* determine the buddy.
 			 */
@@ -2681,7 +2685,11 @@ static void dbBackSplit(dmtree_t * tp, int leafno)
 		}
 	}
 
-	assert(leaf[leafno] == size);
+	if (leaf[leafno] != size) {
+		jfs_err("JFS: wrong leaf value in dbBackSplit");
+		return -EIO;
+	}
+	return 0;
 }
 
 
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index 4021d46da7e..28201b194f5 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -57,6 +57,12 @@
 #include "jfs_debug.h"
 
 /*
+ * __mark_inode_dirty expects inodes to be hashed.  Since we don't want
+ * special inodes in the fileset inode space, we hash them to a dummy head
+ */
+static HLIST_HEAD(aggregate_hash);
+
+/*
  * imap locks
  */
 /* iag free list lock */
@@ -491,6 +497,8 @@ struct inode *diReadSpecial(struct super_block *sb, ino_t inum, int secondary)
 	/* release the page */
 	release_metapage(mp);
 
+	hlist_add_head(&ip->i_hash, &aggregate_hash);
+
 	return (ip);
 }
 
@@ -514,8 +522,6 @@ void diWriteSpecial(struct inode *ip, int secondary)
 	ino_t inum = ip->i_ino;
 	struct metapage *mp;
 
-	ip->i_state &= ~I_DIRTY;
-
 	if (secondary)
 		address = addressPXD(&sbi->ait2) >> sbi->l2nbperpage;
 	else
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index eeb37d70e65..8a53981f9f2 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -86,7 +86,7 @@ struct meta_anchor {
 	atomic_t io_count;
 	struct metapage *mp[MPS_PER_PAGE];
 };
-#define mp_anchor(page) ((struct meta_anchor *)page->private)
+#define mp_anchor(page) ((struct meta_anchor *)page_private(page))
 
 static inline struct metapage *page_to_mp(struct page *page, uint offset)
 {
@@ -108,7 +108,7 @@ static inline int insert_metapage(struct page *page, struct metapage *mp)
 		if (!a)
 			return -ENOMEM;
 		memset(a, 0, sizeof(struct meta_anchor));
-		page->private = (unsigned long)a;
+		set_page_private(page, (unsigned long)a);
 		SetPagePrivate(page);
 		kmap(page);
 	}
@@ -136,7 +136,7 @@ static inline void remove_metapage(struct page *page, struct metapage *mp)
 	a->mp[index] = NULL;
 	if (--a->mp_count == 0) {
 		kfree(a);
-		page->private = 0;
+		set_page_private(page, 0);
 		ClearPagePrivate(page);
 		kunmap(page);
 	}
@@ -156,13 +156,13 @@ static inline void dec_io(struct page *page, void (*handler) (struct page *))
 #else
 static inline struct metapage *page_to_mp(struct page *page, uint offset)
 {
-	return PagePrivate(page) ? (struct metapage *)page->private : NULL;
+	return PagePrivate(page) ? (struct metapage *)page_private(page) : NULL;
 }
 
 static inline int insert_metapage(struct page *page, struct metapage *mp)
 {
 	if (mp) {
-		page->private = (unsigned long)mp;
+		set_page_private(page, (unsigned long)mp);
 		SetPagePrivate(page);
 		kmap(page);
 	}
@@ -171,7 +171,7 @@ static inline int insert_metapage(struct page *page, struct metapage *mp)
 
 static inline void remove_metapage(struct page *page, struct metapage *mp)
 {
-	page->private = 0;
+	set_page_private(page, 0);
 	ClearPagePrivate(page);
 	kunmap(page);
 }
@@ -395,6 +395,12 @@ static int metapage_writepage(struct page *page, struct writeback_control *wbc)
 
 		if (mp->nohomeok && !test_bit(META_forcewrite, &mp->flag)) {
 			redirty = 1;
+			/*
+			 * Make sure this page isn't blocked indefinitely.
+			 * If the journal isn't undergoing I/O, push it
+			 */
+			if (mp->log && !(mp->log->cflag & logGC_PAGEOUT))
+				jfs_flush_journal(mp->log, 0);
 			continue;
 		}
 
diff --git a/fs/jfs/jfs_txnmgr.c b/fs/jfs/jfs_txnmgr.c
index 9b71ed2674f..b660c93c92d 100644
--- a/fs/jfs/jfs_txnmgr.c
+++ b/fs/jfs/jfs_txnmgr.c
@@ -2396,7 +2396,6 @@ static void txUpdateMap(struct tblock * tblk)
 	 */
 	if (tblk->xflag & COMMIT_CREATE) {
 		diUpdatePMap(ipimap, tblk->ino, FALSE, tblk);
-		ipimap->i_state |= I_DIRTY;
 		/* update persistent block allocation map
 		 * for the allocation of inode extent;
 		 */
@@ -2407,7 +2406,6 @@ static void txUpdateMap(struct tblock * tblk)
 	} else if (tblk->xflag & COMMIT_DELETE) {
 		ip = tblk->u.ip;
 		diUpdatePMap(ipimap, ip->i_ino, TRUE, tblk);
-		ipimap->i_state |= I_DIRTY;
 		iput(ip);
 	}
 }
diff --git a/fs/jfs/jfs_xtree.c b/fs/jfs/jfs_xtree.c
index a7fe2f2b969..e72f4ebb6e9 100644
--- a/fs/jfs/jfs_xtree.c
+++ b/fs/jfs/jfs_xtree.c
@@ -3516,16 +3516,10 @@ s64 xtTruncate(tid_t tid, struct inode *ip, s64 newsize, int flag)
 	/* process entries backward from last index */
 	index = le16_to_cpu(p->header.nextindex) - 1;
 
-	if (p->header.flag & BT_INTERNAL)
-		goto getChild;
-
-	/*
-	 *      leaf page
-	 */
 
-	/* Since this is the rightmost leaf, and we may have already freed
-	 * a page that was formerly to the right, let's make sure that the
-	 * next pointer is zero.
+	/* Since this is the rightmost page at this level, and we may have
+	 * already freed a page that was formerly to the right, let's make
+	 * sure that the next pointer is zero.
 	 */
 	if (p->header.next) {
 		if (log)
@@ -3539,6 +3533,12 @@ s64 xtTruncate(tid_t tid, struct inode *ip, s64 newsize, int flag)
 		p->header.next = 0;
 	}
 
+	if (p->header.flag & BT_INTERNAL)
+		goto getChild;
+
+	/*
+	 *      leaf page
+	 */
 	freed = 0;
 
 	/* does region covered by leaf page precede Teof ? */
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 71bc34b96b2..4226af3ea91 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -442,6 +442,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 	inode->i_nlink = 1;
 	inode->i_size = sb->s_bdev->bd_inode->i_size;
 	inode->i_mapping->a_ops = &jfs_metapage_aops;
+	insert_inode_hash(inode);
 	mapping_set_gfp_mask(inode->i_mapping, GFP_NOFS);
 
 	sbi->direct_inode = inode;
diff --git a/fs/partitions/check.c b/fs/partitions/check.c
index 1e848648a32..9c06c5434ec 100644
--- a/fs/partitions/check.c
+++ b/fs/partitions/check.c
@@ -192,6 +192,7 @@ check_partition(struct gendisk *hd, struct block_device *bdev)
 struct part_attribute {
 	struct attribute attr;
 	ssize_t (*show)(struct hd_struct *,char *);
+	ssize_t (*store)(struct hd_struct *,const char *, size_t);
 };
 
 static ssize_t 
@@ -201,14 +202,33 @@ part_attr_show(struct kobject * kobj, struct attribute * attr, char * page)
 	struct part_attribute * part_attr = container_of(attr,struct part_attribute,attr);
 	ssize_t ret = 0;
 	if (part_attr->show)
-		ret = part_attr->show(p,page);
+		ret = part_attr->show(p, page);
+	return ret;
+}
+static ssize_t
+part_attr_store(struct kobject * kobj, struct attribute * attr,
+		const char *page, size_t count)
+{
+	struct hd_struct * p = container_of(kobj,struct hd_struct,kobj);
+	struct part_attribute * part_attr = container_of(attr,struct part_attribute,attr);
+	ssize_t ret = 0;
+
+	if (part_attr->store)
+		ret = part_attr->store(p, page, count);
 	return ret;
 }
 
 static struct sysfs_ops part_sysfs_ops = {
 	.show	=	part_attr_show,
+	.store	=	part_attr_store,
 };
 
+static ssize_t part_uevent_store(struct hd_struct * p,
+				 const char *page, size_t count)
+{
+	kobject_hotplug(&p->kobj, KOBJ_ADD);
+	return count;
+}
 static ssize_t part_dev_read(struct hd_struct * p, char *page)
 {
 	struct gendisk *disk = container_of(p->kobj.parent,struct gendisk,kobj);
@@ -229,6 +249,10 @@ static ssize_t part_stat_read(struct hd_struct * p, char *page)
 		       p->reads, (unsigned long long)p->read_sectors,
 		       p->writes, (unsigned long long)p->write_sectors);
 }
+static struct part_attribute part_attr_uevent = {
+	.attr = {.name = "uevent", .mode = S_IWUSR },
+	.store	= part_uevent_store
+};
 static struct part_attribute part_attr_dev = {
 	.attr = {.name = "dev", .mode = S_IRUGO },
 	.show	= part_dev_read
@@ -247,6 +271,7 @@ static struct part_attribute part_attr_stat = {
 };
 
 static struct attribute * default_attrs[] = {
+	&part_attr_uevent.attr,
 	&part_attr_dev.attr,
 	&part_attr_start.attr,
 	&part_attr_size.attr,
diff --git a/fs/proc/array.c b/fs/proc/array.c
index d84eecacbea..3e1239e4b30 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -438,7 +438,7 @@ static int do_task_stat(struct task_struct *task, char * buffer, int whole)
 		jiffies_to_clock_t(it_real_value),
 		start_time,
 		vsize,
-		mm ? get_mm_counter(mm, rss) : 0, /* you might want to shift this left 3 */
+		mm ? get_mm_rss(mm) : 0,
 	        rsslim,
 		mm ? mm->start_code : 0,
 		mm ? mm->end_code : 0,
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index c7ef3e48e35..d2fa42006d8 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -14,22 +14,41 @@
 char *task_mem(struct mm_struct *mm, char *buffer)
 {
 	unsigned long data, text, lib;
+	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
+
+	/*
+	 * Note: to minimize their overhead, mm maintains hiwater_vm and
+	 * hiwater_rss only when about to *lower* total_vm or rss.  Any
+	 * collector of these hiwater stats must therefore get total_vm
+	 * and rss too, which will usually be the higher.  Barriers? not
+	 * worth the effort, such snapshots can always be inconsistent.
+	 */
+	hiwater_vm = total_vm = mm->total_vm;
+	if (hiwater_vm < mm->hiwater_vm)
+		hiwater_vm = mm->hiwater_vm;
+	hiwater_rss = total_rss = get_mm_rss(mm);
+	if (hiwater_rss < mm->hiwater_rss)
+		hiwater_rss = mm->hiwater_rss;
 
 	data = mm->total_vm - mm->shared_vm - mm->stack_vm;
 	text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
 	lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
 	buffer += sprintf(buffer,
+		"VmPeak:\t%8lu kB\n"
 		"VmSize:\t%8lu kB\n"
 		"VmLck:\t%8lu kB\n"
+		"VmHWM:\t%8lu kB\n"
 		"VmRSS:\t%8lu kB\n"
 		"VmData:\t%8lu kB\n"
 		"VmStk:\t%8lu kB\n"
 		"VmExe:\t%8lu kB\n"
 		"VmLib:\t%8lu kB\n"
 		"VmPTE:\t%8lu kB\n",
-		(mm->total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
+		hiwater_vm << (PAGE_SHIFT-10),
+		(total_vm - mm->reserved_vm) << (PAGE_SHIFT-10),
 		mm->locked_vm << (PAGE_SHIFT-10),
-		get_mm_counter(mm, rss) << (PAGE_SHIFT-10),
+		hiwater_rss << (PAGE_SHIFT-10),
+		total_rss << (PAGE_SHIFT-10),
 		data << (PAGE_SHIFT-10),
 		mm->stack_vm << (PAGE_SHIFT-10), text, lib,
 		(PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10);
@@ -44,13 +63,11 @@ unsigned long task_vsize(struct mm_struct *mm)
 int task_statm(struct mm_struct *mm, int *shared, int *text,
 	       int *data, int *resident)
 {
-	int rss = get_mm_counter(mm, rss);
-
-	*shared = rss - get_mm_counter(mm, anon_rss);
+	*shared = get_mm_counter(mm, file_rss);
 	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
 								>> PAGE_SHIFT;
 	*data = mm->total_vm - mm->shared_vm;
-	*resident = rss;
+	*resident = *shared + get_mm_counter(mm, anon_rss);
 	return mm->total_vm;
 }
 
@@ -186,13 +203,14 @@ static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				struct mem_size_stats *mss)
 {
 	pte_t *pte, ptent;
+	spinlock_t *ptl;
 	unsigned long pfn;
 	struct page *page;
 
-	pte = pte_offset_map(pmd, addr);
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	do {
 		ptent = *pte;
-		if (pte_none(ptent) || !pte_present(ptent))
+		if (!pte_present(ptent))
 			continue;
 
 		mss->resident += PAGE_SIZE;
@@ -213,8 +231,8 @@ static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 				mss->private_clean += PAGE_SIZE;
 		}
 	} while (pte++, addr += PAGE_SIZE, addr != end);
-	pte_unmap(pte - 1);
-	cond_resched_lock(&vma->vm_mm->page_table_lock);
+	pte_unmap_unlock(pte - 1, ptl);
+	cond_resched();
 }
 
 static inline void smaps_pmd_range(struct vm_area_struct *vma, pud_t *pud,
@@ -268,17 +286,11 @@ static inline void smaps_pgd_range(struct vm_area_struct *vma,
 static int show_smap(struct seq_file *m, void *v)
 {
 	struct vm_area_struct *vma = v;
-	struct mm_struct *mm = vma->vm_mm;
 	struct mem_size_stats mss;
 
 	memset(&mss, 0, sizeof mss);
-
-	if (mm) {
-		spin_lock(&mm->page_table_lock);
+	if (vma->vm_mm)
 		smaps_pgd_range(vma, vma->vm_start, vma->vm_end, &mss);
-		spin_unlock(&mm->page_table_lock);
-	}
-
 	return show_map_internal(m, v, &mss);
 }
 
@@ -407,7 +419,6 @@ static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma)
 	for_each_node(i)
 		md->node[i] =0;
 
-	spin_lock(&mm->page_table_lock);
  	for (vaddr = vma->vm_start; vaddr < vma->vm_end; vaddr += PAGE_SIZE) {
 		page = follow_page(mm, vaddr, 0);
 		if (page) {
@@ -422,8 +433,8 @@ static struct numa_maps *get_numa_maps(const struct vm_area_struct *vma)
 				md->anon++;
 			md->node[page_to_nid(page)]++;
 		}
+		cond_resched();
 	}
-	spin_unlock(&mm->page_table_lock);
 	return md;
 }
 
@@ -469,7 +480,7 @@ static int show_numa_map(struct seq_file *m, void *v)
 		seq_printf(m, " interleave={");
 		first = 1;
 		for_each_node(n) {
-			if (test_bit(n, pol->v.nodes)) {
+			if (node_isset(n, pol->v.nodes)) {
 				if (!first)
 					seq_putc(m,',');
 				else
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index ba4767c04ad..4cd46abe843 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -181,8 +181,9 @@ set_page_region(
 	size_t		offset,
 	size_t		length)
 {
-	page->private |= page_region_mask(offset, length);
-	if (page->private == ~0UL)
+	set_page_private(page,
+		page_private(page) | page_region_mask(offset, length));
+	if (page_private(page) == ~0UL)
 		SetPageUptodate(page);
 }
 
@@ -194,7 +195,7 @@ test_page_region(
 {
 	unsigned long	mask = page_region_mask(offset, length);
 
-	return (mask && (page->private & mask) == mask);
+	return (mask && (page_private(page) & mask) == mask);
 }
 
 /*