13 files changed, 938 insertions, 795 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index c3834dad09b3..1485e38daaa3 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -1681,46 +1681,34 @@ const struct dentry_operations pid_dentry_operations =
  * reported by readdir in sync with the inode numbers reported
  * by stat.
  */
-int proc_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
+bool proc_fill_cache(struct file *file, struct dir_context *ctx,
 	const char *name, int len,
 	instantiate_t instantiate, struct task_struct *task, const void *ptr)
 {
-	struct dentry *child, *dir = filp->f_path.dentry;
+	struct dentry *child, *dir = file->f_path.dentry;
+	struct qstr qname = QSTR_INIT(name, len);
 	struct inode *inode;
-	struct qstr qname;
-	ino_t ino = 0;
-	unsigned type = DT_UNKNOWN;
-
-	qname.name = name;
-	qname.len  = len;
-	qname.hash = full_name_hash(name, len);
+	unsigned type;
+	ino_t ino;
 
-	child = d_lookup(dir, &qname);
+	child = d_hash_and_lookup(dir, &qname);
 	if (!child) {
-		struct dentry *new;
-		new = d_alloc(dir, &qname);
-		if (new) {
-			child = instantiate(dir->d_inode, new, task, ptr);
-			if (child)
-				dput(new);
-			else
-				child = new;
+		child = d_alloc(dir, &qname);
+		if (!child)
+			goto end_instantiate;
+		if (instantiate(dir->d_inode, child, task, ptr) < 0) {
+			dput(child);
+			goto end_instantiate;
 		}
 	}
-	if (!child || IS_ERR(child) || !child->d_inode)
-		goto end_instantiate;
 	inode = child->d_inode;
-	if (inode) {
-		ino = inode->i_ino;
-		type = inode->i_mode >> 12;
-	}
+	ino = inode->i_ino;
+	type = inode->i_mode >> 12;
 	dput(child);
+	return dir_emit(ctx, name, len, ino, type);
+
 end_instantiate:
-	if (!ino)
-		ino = find_inode_number(dir, &qname);
-	if (!ino)
-		ino = 1;
-	return filldir(dirent, name, len, filp->f_pos, ino, type);
+	return dir_emit(ctx, name, len, 1, DT_UNKNOWN);
 }
 
 #ifdef CONFIG_CHECKPOINT_RESTORE
@@ -1846,7 +1834,7 @@ struct map_files_info {
 	unsigned char	name[4*sizeof(long)+2]; /* max: %lx-%lx\0 */
 };
 
-static struct dentry *
+static int
 proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
 			   struct task_struct *task, const void *ptr)
 {
@@ -1856,7 +1844,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
 
 	inode = proc_pid_make_inode(dir->i_sb, task);
 	if (!inode)
-		return ERR_PTR(-ENOENT);
+		return -ENOENT;
 
 	ei = PROC_I(inode);
 	ei->op.proc_get_link = proc_map_files_get_link;
@@ -1873,7 +1861,7 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
 	d_set_d_op(dentry, &tid_map_files_dentry_operations);
 	d_add(dentry, inode);
 
-	return NULL;
+	return 0;
 }
 
 static struct dentry *proc_map_files_lookup(struct inode *dir,
@@ -1882,23 +1870,23 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
 	unsigned long vm_start, vm_end;
 	struct vm_area_struct *vma;
 	struct task_struct *task;
-	struct dentry *result;
+	int result;
 	struct mm_struct *mm;
 
-	result = ERR_PTR(-EPERM);
+	result = -EPERM;
 	if (!capable(CAP_SYS_ADMIN))
 		goto out;
 
-	result = ERR_PTR(-ENOENT);
+	result = -ENOENT;
 	task = get_proc_task(dir);
 	if (!task)
 		goto out;
 
-	result = ERR_PTR(-EACCES);
+	result = -EACCES;
 	if (!ptrace_may_access(task, PTRACE_MODE_READ))
 		goto out_put_task;
 
-	result = ERR_PTR(-ENOENT);
+	result = -ENOENT;
 	if (dname_to_vma_addr(dentry, &vm_start, &vm_end))
 		goto out_put_task;
 
@@ -1921,7 +1909,7 @@ out_no_vma:
 out_put_task:
 	put_task_struct(task);
 out:
-	return result;
+	return ERR_PTR(result);
 }
 
 static const struct inode_operations proc_map_files_inode_operations = {
@@ -1931,14 +1919,15 @@ static const struct inode_operations proc_map_files_inode_operations = {
 };
 
 static int
-proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir)
+proc_map_files_readdir(struct file *file, struct dir_context *ctx)
 {
-	struct dentry *dentry = filp->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
 	struct vm_area_struct *vma;
 	struct task_struct *task;
 	struct mm_struct *mm;
-	ino_t ino;
+	unsigned long nr_files, pos, i;
+	struct flex_array *fa = NULL;
+	struct map_files_info info;
+	struct map_files_info *p;
 	int ret;
 
 	ret = -EPERM;
@@ -1946,7 +1935,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		goto out;
 
 	ret = -ENOENT;
-	task = get_proc_task(inode);
+	task = get_proc_task(file_inode(file));
 	if (!task)
 		goto out;
 
@@ -1955,91 +1944,73 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir)
 		goto out_put_task;
 
 	ret = 0;
-	switch (filp->f_pos) {
-	case 0:
-		ino = inode->i_ino;
-		if (filldir(dirent, ".", 1, 0, ino, DT_DIR) < 0)
-			goto out_put_task;
-		filp->f_pos++;
-	case 1:
-		ino = parent_ino(dentry);
-		if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0)
-			goto out_put_task;
-		filp->f_pos++;
-	default:
-	{
-		unsigned long nr_files, pos, i;
-		struct flex_array *fa = NULL;
-		struct map_files_info info;
-		struct map_files_info *p;
-
-		mm = get_task_mm(task);
-		if (!mm)
-			goto out_put_task;
-		down_read(&mm->mmap_sem);
+	if (!dir_emit_dots(file, ctx))
+		goto out_put_task;
 
-		nr_files = 0;
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out_put_task;
+	down_read(&mm->mmap_sem);
 
-		/*
-		 * We need two passes here:
-		 *
-		 *  1) Collect vmas of mapped files with mmap_sem taken
-		 *  2) Release mmap_sem and instantiate entries
-		 *
-		 * otherwise we get lockdep complained, since filldir()
-		 * routine might require mmap_sem taken in might_fault().
-		 */
+	nr_files = 0;
 
-		for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) {
-			if (vma->vm_file && ++pos > filp->f_pos)
-				nr_files++;
-		}
+	/*
+	 * We need two passes here:
+	 *
+	 *  1) Collect vmas of mapped files with mmap_sem taken
+	 *  2) Release mmap_sem and instantiate entries
+	 *
+	 * otherwise we get lockdep complained, since filldir()
+	 * routine might require mmap_sem taken in might_fault().
+	 */
 
-		if (nr_files) {
-			fa = flex_array_alloc(sizeof(info), nr_files,
-						GFP_KERNEL);
-			if (!fa || flex_array_prealloc(fa, 0, nr_files,
-							GFP_KERNEL)) {
-				ret = -ENOMEM;
-				if (fa)
-					flex_array_free(fa);
-				up_read(&mm->mmap_sem);
-				mmput(mm);
-				goto out_put_task;
-			}
-			for (i = 0, vma = mm->mmap, pos = 2; vma;
-					vma = vma->vm_next) {
-				if (!vma->vm_file)
-					continue;
-				if (++pos <= filp->f_pos)
-					continue;
-
-				info.mode = vma->vm_file->f_mode;
-				info.len = snprintf(info.name,
-						sizeof(info.name), "%lx-%lx",
-						vma->vm_start, vma->vm_end);
-				if (flex_array_put(fa, i++, &info, GFP_KERNEL))
-					BUG();
-			}
+	for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) {
+		if (vma->vm_file && ++pos > ctx->pos)
+			nr_files++;
+	}
+
+	if (nr_files) {
+		fa = flex_array_alloc(sizeof(info), nr_files,
+					GFP_KERNEL);
+		if (!fa || flex_array_prealloc(fa, 0, nr_files,
+						GFP_KERNEL)) {
+			ret = -ENOMEM;
+			if (fa)
+				flex_array_free(fa);
+			up_read(&mm->mmap_sem);
+			mmput(mm);
+			goto out_put_task;
 		}
-		up_read(&mm->mmap_sem);
-
-		for (i = 0; i < nr_files; i++) {
-			p = flex_array_get(fa, i);
-			ret = proc_fill_cache(filp, dirent, filldir,
-					      p->name, p->len,
-					      proc_map_files_instantiate,
-					      task,
-					      (void *)(unsigned long)p->mode);
-			if (ret)
-				break;
-			filp->f_pos++;
+		for (i = 0, vma = mm->mmap, pos = 2; vma;
+				vma = vma->vm_next) {
+			if (!vma->vm_file)
+				continue;
+			if (++pos <= ctx->pos)
+				continue;
+
+			info.mode = vma->vm_file->f_mode;
+			info.len = snprintf(info.name,
+					sizeof(info.name), "%lx-%lx",
+					vma->vm_start, vma->vm_end);
+			if (flex_array_put(fa, i++, &info, GFP_KERNEL))
+				BUG();
 		}
-		if (fa)
-			flex_array_free(fa);
-		mmput(mm);
 	}
+	up_read(&mm->mmap_sem);
+
+	for (i = 0; i < nr_files; i++) {
+		p = flex_array_get(fa, i);
+		if (!proc_fill_cache(file, ctx,
+				      p->name, p->len,
+				      proc_map_files_instantiate,
+				      task,
+				      (void *)(unsigned long)p->mode))
+			break;
+		ctx->pos++;
 	}
+	if (fa)
+		flex_array_free(fa);
+	mmput(mm);
 
 out_put_task:
 	put_task_struct(task);
@@ -2049,7 +2020,7 @@ out:
 
 static const struct file_operations proc_map_files_operations = {
 	.read		= generic_read_dir,
-	.readdir	= proc_map_files_readdir,
+	.iterate	= proc_map_files_readdir,
 	.llseek		= default_llseek,
 };
 
@@ -2152,13 +2123,12 @@ static const struct file_operations proc_timers_operations = {
 };
 #endif /* CONFIG_CHECKPOINT_RESTORE */
 
-static struct dentry *proc_pident_instantiate(struct inode *dir,
+static int proc_pident_instantiate(struct inode *dir,
 	struct dentry *dentry, struct task_struct *task, const void *ptr)
 {
 	const struct pid_entry *p = ptr;
 	struct inode *inode;
 	struct proc_inode *ei;
-	struct dentry *error = ERR_PTR(-ENOENT);
 
 	inode = proc_pid_make_inode(dir->i_sb, task);
 	if (!inode)
@@ -2177,9 +2147,9 @@ static struct dentry *proc_pident_instantiate(struct inode *dir,
 	d_add(dentry, inode);
 	/* Close the race of the process dying before we return the dentry */
 	if (pid_revalidate(dentry, 0))
-		error = NULL;
+		return 0;
 out:
-	return error;
+	return -ENOENT;
 }
 
 static struct dentry *proc_pident_lookup(struct inode *dir, 
@@ -2187,11 +2157,11 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
 					 const struct pid_entry *ents,
 					 unsigned int nents)
 {
-	struct dentry *error;
+	int error;
 	struct task_struct *task = get_proc_task(dir);
 	const struct pid_entry *p, *last;
 
-	error = ERR_PTR(-ENOENT);
+	error = -ENOENT;
 
 	if (!task)
 		goto out_no_task;
@@ -2214,70 +2184,33 @@ static struct dentry *proc_pident_lookup(struct inode *dir,
 out:
 	put_task_struct(task);
 out_no_task:
-	return error;
-}
-
-static int proc_pident_fill_cache(struct file *filp, void *dirent,
-	filldir_t filldir, struct task_struct *task, const struct pid_entry *p)
-{
-	return proc_fill_cache(filp, dirent, filldir, p->name, p->len,
-				proc_pident_instantiate, task, p);
+	return ERR_PTR(error);
 }
 
-static int proc_pident_readdir(struct file *filp,
-		void *dirent, filldir_t filldir,
+static int proc_pident_readdir(struct file *file, struct dir_context *ctx,
 		const struct pid_entry *ents, unsigned int nents)
 {
-	int i;
-	struct dentry *dentry = filp->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
-	struct task_struct *task = get_proc_task(inode);
-	const struct pid_entry *p, *last;
-	ino_t ino;
-	int ret;
+	struct task_struct *task = get_proc_task(file_inode(file));
+	const struct pid_entry *p;
 
-	ret = -ENOENT;
 	if (!task)
-		goto out_no_task;
+		return -ENOENT;
 
-	ret = 0;
-	i = filp->f_pos;
-	switch (i) {
-	case 0:
-		ino = inode->i_ino;
-		if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
-			goto out;
-		i++;
-		filp->f_pos++;
-		/* fall through */
-	case 1:
-		ino = parent_ino(dentry);
-		if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
-			goto out;
-		i++;
-		filp->f_pos++;
-		/* fall through */
-	default:
-		i -= 2;
-		if (i >= nents) {
-			ret = 1;
-			goto out;
-		}
-		p = ents + i;
-		last = &ents[nents - 1];
-		while (p <= last) {
-			if (proc_pident_fill_cache(filp, dirent, filldir, task, p) < 0)
-				goto out;
-			filp->f_pos++;
-			p++;
-		}
-	}
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+
+	if (ctx->pos >= nents + 2)
+		goto out;
 
-	ret = 1;
+	for (p = ents + (ctx->pos - 2); p <= ents + nents - 1; p++) {
+		if (!proc_fill_cache(file, ctx, p->name, p->len,
+				proc_pident_instantiate, task, p))
+			break;
+		ctx->pos++;
+	}
 out:
 	put_task_struct(task);
-out_no_task:
-	return ret;
+	return 0;
 }
 
 #ifdef CONFIG_SECURITY
@@ -2362,16 +2295,15 @@ static const struct pid_entry attr_dir_stuff[] = {
 	REG("sockcreate", S_IRUGO|S_IWUGO, proc_pid_attr_operations),
 };
 
-static int proc_attr_dir_readdir(struct file * filp,
-			     void * dirent, filldir_t filldir)
+static int proc_attr_dir_readdir(struct file *file, struct dir_context *ctx)
 {
-	return proc_pident_readdir(filp,dirent,filldir,
-				   attr_dir_stuff,ARRAY_SIZE(attr_dir_stuff));
+	return proc_pident_readdir(file, ctx, 
+				   attr_dir_stuff, ARRAY_SIZE(attr_dir_stuff));
 }
 
 static const struct file_operations proc_attr_dir_operations = {
 	.read		= generic_read_dir,
-	.readdir	= proc_attr_dir_readdir,
+	.iterate	= proc_attr_dir_readdir,
 	.llseek		= default_llseek,
 };
 
@@ -2725,16 +2657,15 @@ static const struct pid_entry tgid_base_stuff[] = {
 #endif
 };
 
-static int proc_tgid_base_readdir(struct file * filp,
-			     void * dirent, filldir_t filldir)
+static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
 {
-	return proc_pident_readdir(filp,dirent,filldir,
-				   tgid_base_stuff,ARRAY_SIZE(tgid_base_stuff));
+	return proc_pident_readdir(file, ctx,
+				   tgid_base_stuff, ARRAY_SIZE(tgid_base_stuff));
 }
 
 static const struct file_operations proc_tgid_base_operations = {
 	.read		= generic_read_dir,
-	.readdir	= proc_tgid_base_readdir,
+	.iterate	= proc_tgid_base_readdir,
 	.llseek		= default_llseek,
 };
 
@@ -2836,11 +2767,10 @@ void proc_flush_task(struct task_struct *task)
 	}
 }
 
-static struct dentry *proc_pid_instantiate(struct inode *dir,
-					   struct dentry * dentry,
-					   struct task_struct *task, const void *ptr)
+static int proc_pid_instantiate(struct inode *dir,
+				   struct dentry * dentry,
+				   struct task_struct *task, const void *ptr)
 {
-	struct dentry *error = ERR_PTR(-ENOENT);
 	struct inode *inode;
 
 	inode = proc_pid_make_inode(dir->i_sb, task);
@@ -2860,14 +2790,14 @@ static struct dentry *proc_pid_instantiate(struct inode *dir,
 	d_add(dentry, inode);
 	/* Close the race of the process dying before we return the dentry */
 	if (pid_revalidate(dentry, 0))
-		error = NULL;
+		return 0;
 out:
-	return error;
+	return -ENOENT;
 }
 
 struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
 {
-	struct dentry *result = NULL;
+	int result = 0;
 	struct task_struct *task;
 	unsigned tgid;
 	struct pid_namespace *ns;
@@ -2888,7 +2818,7 @@ struct dentry *proc_pid_lookup(struct inode *dir, struct dentry * dentry, unsign
 	result = proc_pid_instantiate(dir, dentry, task, NULL);
 	put_task_struct(task);
 out:
-	return result;
+	return ERR_PTR(result);
 }
 
 /*
@@ -2936,58 +2866,42 @@ retry:
 
 #define TGID_OFFSET (FIRST_PROCESS_ENTRY + 1)
 
-static int proc_pid_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
-	struct tgid_iter iter)
-{
-	char name[PROC_NUMBUF];
-	int len = snprintf(name, sizeof(name), "%d", iter.tgid);
-	return proc_fill_cache(filp, dirent, filldir, name, len,
-				proc_pid_instantiate, iter.task, NULL);
-}
-
-static int fake_filldir(void *buf, const char *name, int namelen,
-			loff_t offset, u64 ino, unsigned d_type)
-{
-	return 0;
-}
-
 /* for the /proc/ directory itself, after non-process stuff has been done */
-int proc_pid_readdir(struct file * filp, void * dirent, filldir_t filldir)
+int proc_pid_readdir(struct file *file, struct dir_context *ctx)
 {
 	struct tgid_iter iter;
-	struct pid_namespace *ns;
-	filldir_t __filldir;
-	loff_t pos = filp->f_pos;
+	struct pid_namespace *ns = file->f_dentry->d_sb->s_fs_info;
+	loff_t pos = ctx->pos;
 
 	if (pos >= PID_MAX_LIMIT + TGID_OFFSET)
-		goto out;
+		return 0;
 
 	if (pos == TGID_OFFSET - 1) {
-		if (proc_fill_cache(filp, dirent, filldir, "self", 4,
-					NULL, NULL, NULL) < 0)
-			goto out;
+		struct inode *inode = ns->proc_self->d_inode;
+		if (!dir_emit(ctx, "self", 4, inode->i_ino, DT_LNK))
+			return 0;
 		iter.tgid = 0;
 	} else {
 		iter.tgid = pos - TGID_OFFSET;
 	}
 	iter.task = NULL;
-	ns = filp->f_dentry->d_sb->s_fs_info;
 	for (iter = next_tgid(ns, iter);
 	     iter.task;
 	     iter.tgid += 1, iter = next_tgid(ns, iter)) {
-		if (has_pid_permissions(ns, iter.task, 2))
-			__filldir = filldir;
-		else
-			__filldir = fake_filldir;
+		char name[PROC_NUMBUF];
+		int len;
+		if (!has_pid_permissions(ns, iter.task, 2))
+			continue;
 
-		filp->f_pos = iter.tgid + TGID_OFFSET;
-		if (proc_pid_fill_cache(filp, dirent, __filldir, iter) < 0) {
+		len = snprintf(name, sizeof(name), "%d", iter.tgid);
+		ctx->pos = iter.tgid + TGID_OFFSET;
+		if (!proc_fill_cache(file, ctx, name, len,
+				     proc_pid_instantiate, iter.task, NULL)) {
 			put_task_struct(iter.task);
-			goto out;
+			return 0;
 		}
 	}
-	filp->f_pos = PID_MAX_LIMIT + TGID_OFFSET;
-out:
+	ctx->pos = PID_MAX_LIMIT + TGID_OFFSET;
 	return 0;
 }
 
@@ -3075,11 +2989,10 @@ static const struct pid_entry tid_base_stuff[] = {
 #endif
 };
 
-static int proc_tid_base_readdir(struct file * filp,
-			     void * dirent, filldir_t filldir)
+static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx)
 {
-	return proc_pident_readdir(filp,dirent,filldir,
-				   tid_base_stuff,ARRAY_SIZE(tid_base_stuff));
+	return proc_pident_readdir(file, ctx,
+				   tid_base_stuff, ARRAY_SIZE(tid_base_stuff));
 }
 
 static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
@@ -3090,7 +3003,7 @@ static struct dentry *proc_tid_base_lookup(struct inode *dir, struct dentry *den
 
 static const struct file_operations proc_tid_base_operations = {
 	.read		= generic_read_dir,
-	.readdir	= proc_tid_base_readdir,
+	.iterate	= proc_tid_base_readdir,
 	.llseek		= default_llseek,
 };
 
@@ -3100,10 +3013,9 @@ static const struct inode_operations proc_tid_base_inode_operations = {
 	.setattr	= proc_setattr,
 };
 
-static struct dentry *proc_task_instantiate(struct inode *dir,
+static int proc_task_instantiate(struct inode *dir,
 	struct dentry *dentry, struct task_struct *task, const void *ptr)
 {
-	struct dentry *error = ERR_PTR(-ENOENT);
 	struct inode *inode;
 	inode = proc_pid_make_inode(dir->i_sb, task);
 
@@ -3122,14 +3034,14 @@ static struct dentry *proc_task_instantiate(struct inode *dir,
 	d_add(dentry, inode);
 	/* Close the race of the process dying before we return the dentry */
 	if (pid_revalidate(dentry, 0))
-		error = NULL;
+		return 0;
 out:
-	return error;
+	return -ENOENT;
 }
 
 static struct dentry *proc_task_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
 {
-	struct dentry *result = ERR_PTR(-ENOENT);
+	int result = -ENOENT;
 	struct task_struct *task;
 	struct task_struct *leader = get_proc_task(dir);
 	unsigned tid;
@@ -3159,7 +3071,7 @@ out_drop_task:
 out:
 	put_task_struct(leader);
 out_no_task:
-	return result;
+	return ERR_PTR(result);
 }
 
 /*
@@ -3231,30 +3143,16 @@ static struct task_struct *next_tid(struct task_struct *start)
 	return pos;
 }
 
-static int proc_task_fill_cache(struct file *filp, void *dirent, filldir_t filldir,
-	struct task_struct *task, int tid)
-{
-	char name[PROC_NUMBUF];
-	int len = snprintf(name, sizeof(name), "%d", tid);
-	return proc_fill_cache(filp, dirent, filldir, name, len,
-				proc_task_instantiate, task, NULL);
-}
-
 /* for the /proc/TGID/task/ directories */
-static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldir)
+static int proc_task_readdir(struct file *file, struct dir_context *ctx)
 {
-	struct dentry *dentry = filp->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
 	struct task_struct *leader = NULL;
-	struct task_struct *task;
-	int retval = -ENOENT;
-	ino_t ino;
-	int tid;
+	struct task_struct *task = get_proc_task(file_inode(file));
 	struct pid_namespace *ns;
+	int tid;
 
-	task = get_proc_task(inode);
 	if (!task)
-		goto out_no_task;
+		return -ENOENT;
 	rcu_read_lock();
 	if (pid_alive(task)) {
 		leader = task->group_leader;
@@ -3263,46 +3161,36 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi
 	rcu_read_unlock();
 	put_task_struct(task);
 	if (!leader)
-		goto out_no_task;
-	retval = 0;
+		return -ENOENT;
 
-	switch ((unsigned long)filp->f_pos) {
-	case 0:
-		ino = inode->i_ino;
-		if (filldir(dirent, ".", 1, filp->f_pos, ino, DT_DIR) < 0)
-			goto out;
-		filp->f_pos++;
-		/* fall through */
-	case 1:
-		ino = parent_ino(dentry);
-		if (filldir(dirent, "..", 2, filp->f_pos, ino, DT_DIR) < 0)
-			goto out;
-		filp->f_pos++;
-		/* fall through */
-	}
+	if (!dir_emit_dots(file, ctx))
+		goto out;
 
 	/* f_version caches the tgid value that the last readdir call couldn't
 	 * return. lseek aka telldir automagically resets f_version to 0.
 	 */
-	ns = filp->f_dentry->d_sb->s_fs_info;
-	tid = (int)filp->f_version;
-	filp->f_version = 0;
-	for (task = first_tid(leader, tid, filp->f_pos - 2, ns);
+	ns = file->f_dentry->d_sb->s_fs_info;
+	tid = (int)file->f_version;
+	file->f_version = 0;
+	for (task = first_tid(leader, tid, ctx->pos - 2, ns);
 	     task;
-	     task = next_tid(task), filp->f_pos++) {
+	     task = next_tid(task), ctx->pos++) {
+		char name[PROC_NUMBUF];
+		int len;
 		tid = task_pid_nr_ns(task, ns);
-		if (proc_task_fill_cache(filp, dirent, filldir, task, tid) < 0) {
+		len = snprintf(name, sizeof(name), "%d", tid);
+		if (!proc_fill_cache(file, ctx, name, len,
+				proc_task_instantiate, task, NULL)) {
 			/* returning this tgid failed, save it as the first
 			 * pid for the next readir call */
-			filp->f_version = (u64)tid;
+			file->f_version = (u64)tid;
 			put_task_struct(task);
 			break;
 		}
 	}
 out:
 	put_task_struct(leader);
-out_no_task:
-	return retval;
+	return 0;
 }
 
 static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
@@ -3328,6 +3216,6 @@ static const struct inode_operations proc_task_inode_operations = {
 
 static const struct file_operations proc_task_operations = {
 	.read		= generic_read_dir,
-	.readdir	= proc_task_readdir,
+	.iterate	= proc_task_readdir,
 	.llseek		= default_llseek,
 };
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index d7a4a28ef630..75f2890abbd8 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -167,11 +167,10 @@ static int proc_fd_link(struct dentry *dentry, struct path *path)
 	return ret;
 }
 
-static struct dentry *
+static int
 proc_fd_instantiate(struct inode *dir, struct dentry *dentry,
 		    struct task_struct *task, const void *ptr)
 {
-	struct dentry *error = ERR_PTR(-ENOENT);
 	unsigned fd = (unsigned long)ptr;
 	struct proc_inode *ei;
 	struct inode *inode;
@@ -194,9 +193,9 @@ proc_fd_instantiate(struct inode *dir, struct dentry *dentry,
 
 	/* Close the race of the process dying before we return the dentry */
 	if (tid_fd_revalidate(dentry, 0))
-		error = NULL;
+		return 0;
  out:
-	return error;
+	return -ENOENT;
 }
 
 static struct dentry *proc_lookupfd_common(struct inode *dir,
@@ -204,7 +203,7 @@ static struct dentry *proc_lookupfd_common(struct inode *dir,
 					   instantiate_t instantiate)
 {
 	struct task_struct *task = get_proc_task(dir);
-	struct dentry *result = ERR_PTR(-ENOENT);
+	int result = -ENOENT;
 	unsigned fd = name_to_int(dentry);
 
 	if (!task)
@@ -216,77 +215,61 @@ static struct dentry *proc_lookupfd_common(struct inode *dir,
 out:
 	put_task_struct(task);
 out_no_task:
-	return result;
+	return ERR_PTR(result);
 }
 
-static int proc_readfd_common(struct file * filp, void * dirent,
-			      filldir_t filldir, instantiate_t instantiate)
+static int proc_readfd_common(struct file *file, struct dir_context *ctx,
+			      instantiate_t instantiate)
 {
-	struct dentry *dentry = filp->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
-	struct task_struct *p = get_proc_task(inode);
+	struct task_struct *p = get_proc_task(file_inode(file));
 	struct files_struct *files;
-	unsigned int fd, ino;
-	int retval;
+	unsigned int fd;
 
-	retval = -ENOENT;
 	if (!p)
-		goto out_no_task;
-	retval = 0;
-
-	fd = filp->f_pos;
-	switch (fd) {
-		case 0:
-			if (filldir(dirent, ".", 1, 0, inode->i_ino, DT_DIR) < 0)
-				goto out;
-			filp->f_pos++;
-		case 1:
-			ino = parent_ino(dentry);
-			if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0)
-				goto out;
-			filp->f_pos++;
-		default:
-			files = get_files_struct(p);
-			if (!files)
-				goto out;
-			rcu_read_lock();
-			for (fd = filp->f_pos - 2;
-			     fd < files_fdtable(files)->max_fds;
-			     fd++, filp->f_pos++) {
-				char name[PROC_NUMBUF];
-				int len;
-				int rv;
-
-				if (!fcheck_files(files, fd))
-					continue;
-				rcu_read_unlock();
+		return -ENOENT;
 
-				len = snprintf(name, sizeof(name), "%d", fd);
-				rv = proc_fill_cache(filp, dirent, filldir,
-						     name, len, instantiate, p,
-						     (void *)(unsigned long)fd);
-				if (rv < 0)
-					goto out_fd_loop;
-				rcu_read_lock();
-			}
-			rcu_read_unlock();
-out_fd_loop:
-			put_files_struct(files);
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+	files = get_files_struct(p);
+	if (!files)
+		goto out;
+
+	rcu_read_lock();
+	for (fd = ctx->pos - 2;
+	     fd < files_fdtable(files)->max_fds;
+	     fd++, ctx->pos++) {
+		char name[PROC_NUMBUF];
+		int len;
+
+		if (!fcheck_files(files, fd))
+			continue;
+		rcu_read_unlock();
+
+		len = snprintf(name, sizeof(name), "%d", fd);
+		if (!proc_fill_cache(file, ctx,
+				     name, len, instantiate, p,
+				     (void *)(unsigned long)fd))
+			goto out_fd_loop;
+		rcu_read_lock();
 	}
+	rcu_read_unlock();
+out_fd_loop:
+	put_files_struct(files);
 out:
 	put_task_struct(p);
-out_no_task:
-	return retval;
+	return 0;
 }
 
-static int proc_readfd(struct file *filp, void *dirent, filldir_t filldir)
+static int proc_readfd(struct file *file, struct dir_context *ctx)
 {
-	return proc_readfd_common(filp, dirent, filldir, proc_fd_instantiate);
+	return proc_readfd_common(file, ctx, proc_fd_instantiate);
 }
 
 const struct file_operations proc_fd_operations = {
 	.read		= generic_read_dir,
-	.readdir	= proc_readfd,
+	.iterate	= proc_readfd,
 	.llseek		= default_llseek,
 };
 
@@ -316,11 +299,10 @@ const struct inode_operations proc_fd_inode_operations = {
 	.setattr	= proc_setattr,
 };
 
-static struct dentry *
+static int
 proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry,
 			struct task_struct *task, const void *ptr)
 {
-	struct dentry *error = ERR_PTR(-ENOENT);
 	unsigned fd = (unsigned long)ptr;
 	struct proc_inode *ei;
 	struct inode *inode;
@@ -340,9 +322,9 @@ proc_fdinfo_instantiate(struct inode *dir, struct dentry *dentry,
 
 	/* Close the race of the process dying before we return the dentry */
 	if (tid_fd_revalidate(dentry, 0))
-		error = NULL;
+		return 0;
  out:
-	return error;
+	return -ENOENT;
 }
 
 static struct dentry *
@@ -351,9 +333,9 @@ proc_lookupfdinfo(struct inode *dir, struct dentry *dentry, unsigned int flags)
 	return proc_lookupfd_common(dir, dentry, proc_fdinfo_instantiate);
 }
 
-static int proc_readfdinfo(struct file *filp, void *dirent, filldir_t filldir)
+static int proc_readfdinfo(struct file *file, struct dir_context *ctx)
 {
-	return proc_readfd_common(filp, dirent, filldir,
+	return proc_readfd_common(file, ctx,
 				  proc_fdinfo_instantiate);
 }
 
@@ -364,6 +346,6 @@ const struct inode_operations proc_fdinfo_inode_operations = {
 
 const struct file_operations proc_fdinfo_operations = {
 	.read		= generic_read_dir,
-	.readdir	= proc_readfdinfo,
+	.iterate	= proc_readfdinfo,
 	.llseek		= default_llseek,
 };
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index a2596afffae6..94441a407337 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -233,76 +233,52 @@ struct dentry *proc_lookup(struct inode *dir, struct dentry *dentry,
  * value of the readdir() call, as long as it's non-negative
  * for success..
  */
-int proc_readdir_de(struct proc_dir_entry *de, struct file *filp, void *dirent,
-		filldir_t filldir)
+int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
+		    struct dir_context *ctx)
 {
-	unsigned int ino;
 	int i;
-	struct inode *inode = file_inode(filp);
-	int ret = 0;
-
-	ino = inode->i_ino;
-	i = filp->f_pos;
-	switch (i) {
-		case 0:
-			if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
-				goto out;
-			i++;
-			filp->f_pos++;
-			/* fall through */
-		case 1:
-			if (filldir(dirent, "..", 2, i,
-				    parent_ino(filp->f_path.dentry),
-				    DT_DIR) < 0)
-				goto out;
-			i++;
-			filp->f_pos++;
-			/* fall through */
-		default:
-			spin_lock(&proc_subdir_lock);
-			de = de->subdir;
-			i -= 2;
-			for (;;) {
-				if (!de) {
-					ret = 1;
-					spin_unlock(&proc_subdir_lock);
-					goto out;
-				}
-				if (!i)
-					break;
-				de = de->next;
-				i--;
-			}
 
-			do {
-				struct proc_dir_entry *next;
-
-				/* filldir passes info to user space */
-				pde_get(de);
-				spin_unlock(&proc_subdir_lock);
-				if (filldir(dirent, de->name, de->namelen, filp->f_pos,
-					    de->low_ino, de->mode >> 12) < 0) {
-					pde_put(de);
-					goto out;
-				}
-				spin_lock(&proc_subdir_lock);
-				filp->f_pos++;
-				next = de->next;
-				pde_put(de);
-				de = next;
-			} while (de);
+	if (!dir_emit_dots(file, ctx))
+		return 0;
+
+	spin_lock(&proc_subdir_lock);
+	de = de->subdir;
+	i = ctx->pos - 2;
+	for (;;) {
+		if (!de) {
 			spin_unlock(&proc_subdir_lock);
+			return 0;
+		}
+		if (!i)
+			break;
+		de = de->next;
+		i--;
 	}
-	ret = 1;
-out:
-	return ret;	
+
+	do {
+		struct proc_dir_entry *next;
+		pde_get(de);
+		spin_unlock(&proc_subdir_lock);
+		if (!dir_emit(ctx, de->name, de->namelen,
+			    de->low_ino, de->mode >> 12)) {
+			pde_put(de);
+			return 0;
+		}
+		spin_lock(&proc_subdir_lock);
+		ctx->pos++;
+		next = de->next;
+		pde_put(de);
+		de = next;
+	} while (de);
+	spin_unlock(&proc_subdir_lock);
+	return 0;
 }
 
-int proc_readdir(struct file *filp, void *dirent, filldir_t filldir)
+int proc_readdir(struct file *file, struct dir_context *ctx)
 {
-	struct inode *inode = file_inode(filp);
+	struct inode *inode = file_inode(file);
 
-	return proc_readdir_de(PDE(inode), filp, dirent, filldir);
+	return proc_readdir_de(PDE(inode), file, ctx);
 }
 
 /*
@@ -313,7 +289,7 @@ int proc_readdir(struct file *filp, void *dirent, filldir_t filldir)
 static const struct file_operations proc_dir_operations = {
 	.llseek			= generic_file_llseek,
 	.read			= generic_read_dir,
-	.readdir		= proc_readdir,
+	.iterate		= proc_readdir,
 };
 
 /*
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index d600fb098b6a..651d09a11dde 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -165,14 +165,14 @@ extern int proc_setattr(struct dentry *, struct iattr *);
 extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *);
 extern int pid_revalidate(struct dentry *, unsigned int);
 extern int pid_delete_dentry(const struct dentry *);
-extern int proc_pid_readdir(struct file *, void *, filldir_t);
+extern int proc_pid_readdir(struct file *, struct dir_context *);
 extern struct dentry *proc_pid_lookup(struct inode *, struct dentry *, unsigned int);
 extern loff_t mem_lseek(struct file *, loff_t, int);
 
 /* Lookups */
-typedef struct dentry *instantiate_t(struct inode *, struct dentry *,
+typedef int instantiate_t(struct inode *, struct dentry *,
 				     struct task_struct *, const void *);
-extern int proc_fill_cache(struct file *, void *, filldir_t, const char *, int,
+extern bool proc_fill_cache(struct file *, struct dir_context *, const char *, int,
 			   instantiate_t, struct task_struct *, const void *);
 
 /*
@@ -183,8 +183,8 @@ extern spinlock_t proc_subdir_lock;
 extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int);
 extern struct dentry *proc_lookup_de(struct proc_dir_entry *, struct inode *,
 				     struct dentry *);
-extern int proc_readdir(struct file *, void *, filldir_t);
-extern int proc_readdir_de(struct proc_dir_entry *, struct file *, void *, filldir_t);
+extern int proc_readdir(struct file *, struct dir_context *);
+extern int proc_readdir_de(struct proc_dir_entry *, struct file *, struct dir_context *);
 
 static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde)
 {
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 0a22194e5d58..06ea155e1a59 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -408,7 +408,7 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff)
 	prpsinfo.pr_zomb	= 0;
 
 	strcpy(prpsinfo.pr_fname, "vmlinux");
-	strncpy(prpsinfo.pr_psargs, saved_command_line, ELF_PRARGSZ);
+	strlcpy(prpsinfo.pr_psargs, saved_command_line, sizeof(prpsinfo.pr_psargs));
 
 	nhdr->p_filesz	+= notesize(&notes[1]);
 	bufp = storenote(&notes[1], bufp);
diff --git a/fs/proc/kmsg.c b/fs/proc/kmsg.c
index bd4b5a740ff1..bdfabdaefdce 100644
--- a/fs/proc/kmsg.c
+++ b/fs/proc/kmsg.c
@@ -21,12 +21,12 @@ extern wait_queue_head_t log_wait;
 
 static int kmsg_open(struct inode * inode, struct file * file)
 {
-	return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_FILE);
+	return do_syslog(SYSLOG_ACTION_OPEN, NULL, 0, SYSLOG_FROM_PROC);
 }
 
 static int kmsg_release(struct inode * inode, struct file * file)
 {
-	(void) do_syslog(SYSLOG_ACTION_CLOSE, NULL, 0, SYSLOG_FROM_FILE);
+	(void) do_syslog(SYSLOG_ACTION_CLOSE, NULL, 0, SYSLOG_FROM_PROC);
 	return 0;
 }
 
@@ -34,15 +34,15 @@ static ssize_t kmsg_read(struct file *file, char __user *buf,
 			 size_t count, loff_t *ppos)
 {
 	if ((file->f_flags & O_NONBLOCK) &&
-	    !do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_FILE))
+	    !do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC))
 		return -EAGAIN;
-	return do_syslog(SYSLOG_ACTION_READ, buf, count, SYSLOG_FROM_FILE);
+	return do_syslog(SYSLOG_ACTION_READ, buf, count, SYSLOG_FROM_PROC);
 }
 
 static unsigned int kmsg_poll(struct file *file, poll_table *wait)
 {
 	poll_wait(file, &log_wait, wait);
-	if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_FILE))
+	if (do_syslog(SYSLOG_ACTION_SIZE_UNREAD, NULL, 0, SYSLOG_FROM_PROC))
 		return POLLIN | POLLRDNORM;
 	return 0;
 }
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 54bdc6701e9f..49a7fff2e83a 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -187,13 +187,12 @@ static const struct inode_operations proc_ns_link_inode_operations = {
 	.setattr	= proc_setattr,
 };
 
-static struct dentry *proc_ns_instantiate(struct inode *dir,
+static int proc_ns_instantiate(struct inode *dir,
 	struct dentry *dentry, struct task_struct *task, const void *ptr)
 {
 	const struct proc_ns_operations *ns_ops = ptr;
 	struct inode *inode;
 	struct proc_inode *ei;
-	struct dentry *error = ERR_PTR(-ENOENT);
 
 	inode = proc_pid_make_inode(dir->i_sb, task);
 	if (!inode)
@@ -208,90 +207,52 @@ static struct dentry *proc_ns_instantiate(struct inode *dir,
 	d_add(dentry, inode);
 	/* Close the race of the process dying before we return the dentry */
 	if (pid_revalidate(dentry, 0))
-		error = NULL;
+		return 0;
 out:
-	return error;
-}
-
-static int proc_ns_fill_cache(struct file *filp, void *dirent,
-	filldir_t filldir, struct task_struct *task,
-	const struct proc_ns_operations *ops)
-{
-	return proc_fill_cache(filp, dirent, filldir,
-				ops->name, strlen(ops->name),
-				proc_ns_instantiate, task, ops);
+	return -ENOENT;
 }
 
-static int proc_ns_dir_readdir(struct file *filp, void *dirent,
-				filldir_t filldir)
+static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx)
 {
-	int i;
-	struct dentry *dentry = filp->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
-	struct task_struct *task = get_proc_task(inode);
+	struct task_struct *task = get_proc_task(file_inode(file));
 	const struct proc_ns_operations **entry, **last;
-	ino_t ino;
-	int ret;
 
-	ret = -ENOENT;
 	if (!task)
-		goto out_no_task;
+		return -ENOENT;
 
-	ret = 0;
-	i = filp->f_pos;
-	switch (i) {
-	case 0:
-		ino = inode->i_ino;
-		if (filldir(dirent, ".", 1, i, ino, DT_DIR) < 0)
-			goto out;
-		i++;
-		filp->f_pos++;
-		/* fall through */
-	case 1:
-		ino = parent_ino(dentry);
-		if (filldir(dirent, "..", 2, i, ino, DT_DIR) < 0)
-			goto out;
-		i++;
-		filp->f_pos++;
-		/* fall through */
-	default:
-		i -= 2;
-		if (i >= ARRAY_SIZE(ns_entries)) {
-			ret = 1;
-			goto out;
-		}
-		entry = ns_entries + i;
-		last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
-		while (entry <= last) {
-			if (proc_ns_fill_cache(filp, dirent, filldir,
-						task, *entry) < 0)
-				goto out;
-			filp->f_pos++;
-			entry++;
-		}
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+	if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries))
+		goto out;
+	entry = ns_entries + (ctx->pos - 2);
+	last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
+	while (entry <= last) {
+		const struct proc_ns_operations *ops = *entry;
+		if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name),
+				     proc_ns_instantiate, task, ops))
+			break;
+		ctx->pos++;
+		entry++;
 	}
-
-	ret = 1;
 out:
 	put_task_struct(task);
-out_no_task:
-	return ret;
+	return 0;
 }
 
 const struct file_operations proc_ns_dir_operations = {
 	.read		= generic_read_dir,
-	.readdir	= proc_ns_dir_readdir,
+	.iterate	= proc_ns_dir_readdir,
 };
 
 static struct dentry *proc_ns_dir_lookup(struct inode *dir,
 				struct dentry *dentry, unsigned int flags)
 {
-	struct dentry *error;
+	int error;
 	struct task_struct *task = get_proc_task(dir);
 	const struct proc_ns_operations **entry, **last;
 	unsigned int len = dentry->d_name.len;
 
-	error = ERR_PTR(-ENOENT);
+	error = -ENOENT;
 
 	if (!task)
 		goto out_no_task;
@@ -310,7 +271,7 @@ static struct dentry *proc_ns_dir_lookup(struct inode *dir,
 out:
 	put_task_struct(task);
 out_no_task:
-	return error;
+	return ERR_PTR(error);
 }
 
 const struct inode_operations proc_ns_dir_inode_operations = {
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 986e83220d56..4677bb7dc7c2 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -160,16 +160,15 @@ const struct inode_operations proc_net_inode_operations = {
 	.getattr	= proc_tgid_net_getattr,
 };
 
-static int proc_tgid_net_readdir(struct file *filp, void *dirent,
-		filldir_t filldir)
+static int proc_tgid_net_readdir(struct file *file, struct dir_context *ctx)
 {
 	int ret;
 	struct net *net;
 
 	ret = -EINVAL;
-	net = get_proc_task_net(file_inode(filp));
+	net = get_proc_task_net(file_inode(file));
 	if (net != NULL) {
-		ret = proc_readdir_de(net->proc_net, filp, dirent, filldir);
+		ret = proc_readdir_de(net->proc_net, file, ctx);
 		put_net(net);
 	}
 	return ret;
@@ -178,7 +177,7 @@ static int proc_tgid_net_readdir(struct file *filp, void *dirent,
 const struct file_operations proc_net_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
-	.readdir	= proc_tgid_net_readdir,
+	.iterate	= proc_tgid_net_readdir,
 };
 
 static __net_init int proc_net_ns_init(struct net *net)
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index ac05f33a0dde..71290463a1d3 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -573,12 +573,12 @@ out:
 	return ret;
 }
 
-static int proc_sys_fill_cache(struct file *filp, void *dirent,
-				filldir_t filldir,
+static bool proc_sys_fill_cache(struct file *file,
+				struct dir_context *ctx,
 				struct ctl_table_header *head,
 				struct ctl_table *table)
 {
-	struct dentry *child, *dir = filp->f_path.dentry;
+	struct dentry *child, *dir = file->f_path.dentry;
 	struct inode *inode;
 	struct qstr qname;
 	ino_t ino = 0;
@@ -595,38 +595,38 @@ static int proc_sys_fill_cache(struct file *filp, void *dirent,
 			inode = proc_sys_make_inode(dir->d_sb, head, table);
 			if (!inode) {
 				dput(child);
-				return -ENOMEM;
+				return false;
 			} else {
 				d_set_d_op(child, &proc_sys_dentry_operations);
 				d_add(child, inode);
 			}
 		} else {
-			return -ENOMEM;
+			return false;
 		}
 	}
 	inode = child->d_inode;
 	ino  = inode->i_ino;
 	type = inode->i_mode >> 12;
 	dput(child);
-	return !!filldir(dirent, qname.name, qname.len, filp->f_pos, ino, type);
+	return dir_emit(ctx, qname.name, qname.len, ino, type);
 }
 
-static int proc_sys_link_fill_cache(struct file *filp, void *dirent,
-				    filldir_t filldir,
+static bool proc_sys_link_fill_cache(struct file *file,
+				    struct dir_context *ctx,
 				    struct ctl_table_header *head,
 				    struct ctl_table *table)
 {
-	int err, ret = 0;
+	bool ret = true;
 	head = sysctl_head_grab(head);
 
 	if (S_ISLNK(table->mode)) {
 		/* It is not an error if we can not follow the link ignore it */
-		err = sysctl_follow_link(&head, &table, current->nsproxy);
+		int err = sysctl_follow_link(&head, &table, current->nsproxy);
 		if (err)
 			goto out;
 	}
 
-	ret = proc_sys_fill_cache(filp, dirent, filldir, head, table);
+	ret = proc_sys_fill_cache(file, ctx, head, table);
 out:
 	sysctl_head_finish(head);
 	return ret;
@@ -634,67 +634,50 @@ out:
 
 static int scan(struct ctl_table_header *head, ctl_table *table,
 		unsigned long *pos, struct file *file,
-		void *dirent, filldir_t filldir)
+		struct dir_context *ctx)
 {
-	int res;
+	bool res;
 
-	if ((*pos)++ < file->f_pos)
-		return 0;
+	if ((*pos)++ < ctx->pos)
+		return true;
 
 	if (unlikely(S_ISLNK(table->mode)))
-		res = proc_sys_link_fill_cache(file, dirent, filldir, head, table);
+		res = proc_sys_link_fill_cache(file, ctx, head, table);
 	else
-		res = proc_sys_fill_cache(file, dirent, filldir, head, table);
+		res = proc_sys_fill_cache(file, ctx, head, table);
 
-	if (res == 0)
-		file->f_pos = *pos;
+	if (res)
+		ctx->pos = *pos;
 
 	return res;
 }
 
-static int proc_sys_readdir(struct file *filp, void *dirent, filldir_t filldir)
+static int proc_sys_readdir(struct file *file, struct dir_context *ctx)
 {
-	struct dentry *dentry = filp->f_path.dentry;
-	struct inode *inode = dentry->d_inode;
-	struct ctl_table_header *head = grab_header(inode);
+	struct ctl_table_header *head = grab_header(file_inode(file));
 	struct ctl_table_header *h = NULL;
 	struct ctl_table *entry;
 	struct ctl_dir *ctl_dir;
 	unsigned long pos;
-	int ret = -EINVAL;
 
 	if (IS_ERR(head))
 		return PTR_ERR(head);
 
 	ctl_dir = container_of(head, struct ctl_dir, header);
 
-	ret = 0;
-	/* Avoid a switch here: arm builds fail with missing __cmpdi2 */
-	if (filp->f_pos == 0) {
-		if (filldir(dirent, ".", 1, filp->f_pos,
-				inode->i_ino, DT_DIR) < 0)
-			goto out;
-		filp->f_pos++;
-	}
-	if (filp->f_pos == 1) {
-		if (filldir(dirent, "..", 2, filp->f_pos,
-				parent_ino(dentry), DT_DIR) < 0)
-			goto out;
-		filp->f_pos++;
-	}
+	if (!dir_emit_dots(file, ctx))
+		return 0;
+
 	pos = 2;
 
 	for (first_entry(ctl_dir, &h, &entry); h; next_entry(&h, &entry)) {
-		ret = scan(h, entry, &pos, filp, dirent, filldir);
-		if (ret) {
+		if (!scan(h, entry, &pos, file, ctx)) {
 			sysctl_head_finish(h);
 			break;
 		}
 	}
-	ret = 1;
-out:
 	sysctl_head_finish(head);
-	return ret;
+	return 0;
 }
 
 static int proc_sys_permission(struct inode *inode, int mask)
@@ -769,7 +752,7 @@ static const struct file_operations proc_sys_file_operations = {
 
 static const struct file_operations proc_sys_dir_file_operations = {
 	.read		= generic_read_dir,
-	.readdir	= proc_sys_readdir,
+	.iterate	= proc_sys_readdir,
 	.llseek		= generic_file_llseek,
 };
 
@@ -813,15 +796,16 @@ static int sysctl_is_seen(struct ctl_table_header *p)
 	return res;
 }
 
-static int proc_sys_compare(const struct dentry *parent,
-		const struct inode *pinode,
-		const struct dentry *dentry, const struct inode *inode,
+static int proc_sys_compare(const struct dentry *parent, const struct dentry *dentry,
 		unsigned int len, const char *str, const struct qstr *name)
 {
 	struct ctl_table_header *head;
+	struct inode *inode;
+
 	/* Although proc doesn't have negative dentries, rcu-walk means
 	 * that inode here can be NULL */
 	/* AV: can it, indeed? */
+	inode = ACCESS_ONCE(dentry->d_inode);
 	if (!inode)
 		return 1;
 	if (name->len != len)
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 41a6ea93f486..229e366598da 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -202,21 +202,14 @@ static struct dentry *proc_root_lookup(struct inode * dir, struct dentry * dentr
 	return proc_pid_lookup(dir, dentry, flags);
 }
 
-static int proc_root_readdir(struct file * filp,
-	void * dirent, filldir_t filldir)
+static int proc_root_readdir(struct file *file, struct dir_context *ctx)
 {
-	unsigned int nr = filp->f_pos;
-	int ret;
-
-	if (nr < FIRST_PROCESS_ENTRY) {
-		int error = proc_readdir(filp, dirent, filldir);
-		if (error <= 0)
-			return error;
-		filp->f_pos = FIRST_PROCESS_ENTRY;
+	if (ctx->pos < FIRST_PROCESS_ENTRY) {
+		proc_readdir(file, ctx);
+		ctx->pos = FIRST_PROCESS_ENTRY;
 	}
 
-	ret = proc_pid_readdir(filp, dirent, filldir);
-	return ret;
+	return proc_pid_readdir(file, ctx);
 }
 
 /*
@@ -226,7 +219,7 @@ static int proc_root_readdir(struct file * filp,
  */
 static const struct file_operations proc_root_operations = {
 	.read		 = generic_read_dir,
-	.readdir	 = proc_root_readdir,
+	.iterate	 = proc_root_readdir,
 	.llseek		= default_llseek,
 };
 
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 3e636d864d56..dbf61f6174f0 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -11,6 +11,7 @@
 #include <linux/rmap.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/elf.h>
 #include <asm/uaccess.h>
@@ -688,10 +689,58 @@ const struct file_operations proc_tid_smaps_operations = {
 	.release	= seq_release_private,
 };
 
+/*
+ * We do not want to have constant page-shift bits sitting in
+ * pagemap entries and are about to reuse them some time soon.
+ *
+ * Here's the "migration strategy":
+ * 1. when the system boots these bits remain what they are,
+ *    but a warning about future change is printed in log;
+ * 2. once anyone clears soft-dirty bits via clear_refs file,
+ *    these flag is set to denote, that user is aware of the
+ *    new API and those page-shift bits change their meaning.
+ *    The respective warning is printed in dmesg;
+ * 3. In a couple of releases we will remove all the mentions
+ *    of page-shift in pagemap entries.
+ */
+
+static bool soft_dirty_cleared __read_mostly;
+
+enum clear_refs_types {
+	CLEAR_REFS_ALL = 1,
+	CLEAR_REFS_ANON,
+	CLEAR_REFS_MAPPED,
+	CLEAR_REFS_SOFT_DIRTY,
+	CLEAR_REFS_LAST,
+};
+
+struct clear_refs_private {
+	struct vm_area_struct *vma;
+	enum clear_refs_types type;
+};
+
+static inline void clear_soft_dirty(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *pte)
+{
+#ifdef CONFIG_MEM_SOFT_DIRTY
+	/*
+	 * The soft-dirty tracker uses #PF-s to catch writes
+	 * to pages, so write-protect the pte as well. See the
+	 * Documentation/vm/soft-dirty.txt for full description
+	 * of how soft-dirty works.
+	 */
+	pte_t ptent = *pte;
+	ptent = pte_wrprotect(ptent);
+	ptent = pte_clear_flags(ptent, _PAGE_SOFT_DIRTY);
+	set_pte_at(vma->vm_mm, addr, pte, ptent);
+#endif
+}
+
 static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 				unsigned long end, struct mm_walk *walk)
 {
-	struct vm_area_struct *vma = walk->private;
+	struct clear_refs_private *cp = walk->private;
+	struct vm_area_struct *vma = cp->vma;
 	pte_t *pte, ptent;
 	spinlock_t *ptl;
 	struct page *page;
@@ -706,6 +755,11 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 		if (!pte_present(ptent))
 			continue;
 
+		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
+			clear_soft_dirty(vma, addr, pte);
+			continue;
+		}
+
 		page = vm_normal_page(vma, addr, ptent);
 		if (!page)
 			continue;
@@ -719,10 +773,6 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 	return 0;
 }
 
-#define CLEAR_REFS_ALL 1
-#define CLEAR_REFS_ANON 2
-#define CLEAR_REFS_MAPPED 3
-
 static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				size_t count, loff_t *ppos)
 {
@@ -730,7 +780,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 	char buffer[PROC_NUMBUF];
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
-	int type;
+	enum clear_refs_types type;
+	int itype;
 	int rv;
 
 	memset(buffer, 0, sizeof(buffer));
@@ -738,23 +789,37 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		count = sizeof(buffer) - 1;
 	if (copy_from_user(buffer, buf, count))
 		return -EFAULT;
-	rv = kstrtoint(strstrip(buffer), 10, &type);
+	rv = kstrtoint(strstrip(buffer), 10, &itype);
 	if (rv < 0)
 		return rv;
-	if (type < CLEAR_REFS_ALL || type > CLEAR_REFS_MAPPED)
+	type = (enum clear_refs_types)itype;
+	if (type < CLEAR_REFS_ALL || type >= CLEAR_REFS_LAST)
 		return -EINVAL;
+
+	if (type == CLEAR_REFS_SOFT_DIRTY) {
+		soft_dirty_cleared = true;
+		pr_warn_once("The pagemap bits 55-60 has changed their meaning! "
+				"See the linux/Documentation/vm/pagemap.txt for details.\n");
+	}
+
 	task = get_proc_task(file_inode(file));
 	if (!task)
 		return -ESRCH;
 	mm = get_task_mm(task);
 	if (mm) {
+		struct clear_refs_private cp = {
+			.type = type,
+		};
 		struct mm_walk clear_refs_walk = {
 			.pmd_entry = clear_refs_pte_range,
 			.mm = mm,
+			.private = &cp,
 		};
 		down_read(&mm->mmap_sem);
+		if (type == CLEAR_REFS_SOFT_DIRTY)
+			mmu_notifier_invalidate_range_start(mm, 0, -1);
 		for (vma = mm->mmap; vma; vma = vma->vm_next) {
-			clear_refs_walk.private = vma;
+			cp.vma = vma;
 			if (is_vm_hugetlb_page(vma))
 				continue;
 			/*
@@ -773,6 +838,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			walk_page_range(vma->vm_start, vma->vm_end,
 					&clear_refs_walk);
 		}
+		if (type == CLEAR_REFS_SOFT_DIRTY)
+			mmu_notifier_invalidate_range_end(mm, 0, -1);
 		flush_tlb_mm(mm);
 		up_read(&mm->mmap_sem);
 		mmput(mm);
@@ -794,6 +861,7 @@ typedef struct {
 struct pagemapread {
 	int pos, len;
 	pagemap_entry_t *buffer;
+	bool v2;
 };
 
 #define PAGEMAP_WALK_SIZE	(PMD_SIZE)
@@ -807,14 +875,17 @@ struct pagemapread {
 #define PM_PSHIFT_BITS      6
 #define PM_PSHIFT_OFFSET    (PM_STATUS_OFFSET - PM_PSHIFT_BITS)
 #define PM_PSHIFT_MASK      (((1LL << PM_PSHIFT_BITS) - 1) << PM_PSHIFT_OFFSET)
-#define PM_PSHIFT(x)        (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
+#define __PM_PSHIFT(x)      (((u64) (x) << PM_PSHIFT_OFFSET) & PM_PSHIFT_MASK)
 #define PM_PFRAME_MASK      ((1LL << PM_PSHIFT_OFFSET) - 1)
 #define PM_PFRAME(x)        ((x) & PM_PFRAME_MASK)
+/* in "new" pagemap pshift bits are occupied with more status bits */
+#define PM_STATUS2(v2, x)   (__PM_PSHIFT(v2 ? x : PAGE_SHIFT))
 
+#define __PM_SOFT_DIRTY      (1LL)
 #define PM_PRESENT          PM_STATUS(4LL)
 #define PM_SWAP             PM_STATUS(2LL)
 #define PM_FILE             PM_STATUS(1LL)
-#define PM_NOT_PRESENT      PM_PSHIFT(PAGE_SHIFT)
+#define PM_NOT_PRESENT(v2)  PM_STATUS2(v2, 0)
 #define PM_END_OF_BUFFER    1
 
 static inline pagemap_entry_t make_pme(u64 val)
@@ -837,7 +908,7 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 	struct pagemapread *pm = walk->private;
 	unsigned long addr;
 	int err = 0;
-	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
 
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
 		err = add_to_pagemap(addr, &pme, pm);
@@ -847,11 +918,12 @@ static int pagemap_pte_hole(unsigned long start, unsigned long end,
 	return err;
 }
 
-static void pte_to_pagemap_entry(pagemap_entry_t *pme,
+static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 		struct vm_area_struct *vma, unsigned long addr, pte_t pte)
 {
 	u64 frame, flags;
 	struct page *page = NULL;
+	int flags2 = 0;
 
 	if (pte_present(pte)) {
 		frame = pte_pfn(pte);
@@ -866,19 +938,21 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme,
 		if (is_migration_entry(entry))
 			page = migration_entry_to_page(entry);
 	} else {
-		*pme = make_pme(PM_NOT_PRESENT);
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2));
 		return;
 	}
 
 	if (page && !PageAnon(page))
 		flags |= PM_FILE;
+	if (pte_soft_dirty(pte))
+		flags2 |= __PM_SOFT_DIRTY;
 
-	*pme = make_pme(PM_PFRAME(frame) | PM_PSHIFT(PAGE_SHIFT) | flags);
+	*pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
-					pmd_t pmd, int offset)
+static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
+		pmd_t pmd, int offset, int pmd_flags2)
 {
 	/*
 	 * Currently pmd for thp is always present because thp can not be
@@ -887,13 +961,13 @@ static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
 	 */
 	if (pmd_present(pmd))
 		*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
-				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
+				| PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT);
 	else
-		*pme = make_pme(PM_NOT_PRESENT);
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2));
 }
 #else
-static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme,
-						pmd_t pmd, int offset)
+static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
+		pmd_t pmd, int offset, int pmd_flags2)
 {
 }
 #endif
@@ -905,17 +979,20 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 	struct pagemapread *pm = walk->private;
 	pte_t *pte;
 	int err = 0;
-	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT);
+	pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
 
 	/* find the first VMA at or above 'addr' */
 	vma = find_vma(walk->mm, addr);
 	if (vma && pmd_trans_huge_lock(pmd, vma) == 1) {
+		int pmd_flags2;
+
+		pmd_flags2 = (pmd_soft_dirty(*pmd) ? __PM_SOFT_DIRTY : 0);
 		for (; addr != end; addr += PAGE_SIZE) {
 			unsigned long offset;
 
 			offset = (addr & ~PAGEMAP_WALK_MASK) >>
 					PAGE_SHIFT;
-			thp_pmd_to_pagemap_entry(&pme, *pmd, offset);
+			thp_pmd_to_pagemap_entry(&pme, pm, *pmd, offset, pmd_flags2);
 			err = add_to_pagemap(addr, &pme, pm);
 			if (err)
 				break;
@@ -932,7 +1009,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		 * and need a new, higher one */
 		if (vma && (addr >= vma->vm_end)) {
 			vma = find_vma(walk->mm, addr);
-			pme = make_pme(PM_NOT_PRESENT);
+			pme = make_pme(PM_NOT_PRESENT(pm->v2));
 		}
 
 		/* check that 'vma' actually covers this address,
@@ -940,7 +1017,7 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 		if (vma && (vma->vm_start <= addr) &&
 		    !is_vm_hugetlb_page(vma)) {
 			pte = pte_offset_map(pmd, addr);
-			pte_to_pagemap_entry(&pme, vma, addr, *pte);
+			pte_to_pagemap_entry(&pme, pm, vma, addr, *pte);
 			/* unmap before userspace copy */
 			pte_unmap(pte);
 		}
@@ -955,14 +1032,14 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 }
 
 #ifdef CONFIG_HUGETLB_PAGE
-static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme,
+static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
 					pte_t pte, int offset)
 {
 	if (pte_present(pte))
 		*pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)
-				| PM_PSHIFT(PAGE_SHIFT) | PM_PRESENT);
+				| PM_STATUS2(pm->v2, 0) | PM_PRESENT);
 	else
-		*pme = make_pme(PM_NOT_PRESENT);
+		*pme = make_pme(PM_NOT_PRESENT(pm->v2));
 }
 
 /* This function walks within one hugetlb entry in the single call */
@@ -976,7 +1053,7 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
 
 	for (; addr != end; addr += PAGE_SIZE) {
 		int offset = (addr & ~hmask) >> PAGE_SHIFT;
-		huge_pte_to_pagemap_entry(&pme, *pte, offset);
+		huge_pte_to_pagemap_entry(&pme, pm, *pte, offset);
 		err = add_to_pagemap(addr, &pme, pm);
 		if (err)
 			return err;
@@ -1038,6 +1115,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	if (!count)
 		goto out_task;
 
+	pm.v2 = soft_dirty_cleared;
 	pm.len = PM_ENTRY_BYTES * (PAGEMAP_WALK_SIZE >> PAGE_SHIFT);
 	pm.buffer = kmalloc(pm.len, GFP_TEMPORARY);
 	ret = -ENOMEM;
@@ -1110,9 +1188,18 @@ out:
 	return ret;
 }
 
+static int pagemap_open(struct inode *inode, struct file *file)
+{
+	pr_warn_once("Bits 55-60 of /proc/PID/pagemap entries are about "
+			"to stop being page-shift some time soon. See the "
+			"linux/Documentation/vm/pagemap.txt for details.\n");
+	return 0;
+}
+
 const struct file_operations proc_pagemap_operations = {
 	.llseek		= mem_lseek, /* borrow this */
 	.read		= pagemap_read,
+	.open		= pagemap_open,
 };
 #endif /* CONFIG_PROC_PAGE_MONITOR */
 
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 9610ac772d7e..061894625903 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -20,8 +20,7 @@ static int uptime_proc_show(struct seq_file *m, void *v)
 	for_each_possible_cpu(i)
 		idletime += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
 
-	do_posix_clock_monotonic_gettime(&uptime);
-	monotonic_to_bootbased(&uptime);
+	get_monotonic_boottime(&uptime);
 	nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC;
 	idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
 	idle.tv_nsec = rem;
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 17f7e080d7ff..28503172f2e4 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -20,6 +20,7 @@
 #include <linux/init.h>
 #include <linux/crash_dump.h>
 #include <linux/list.h>
+#include <linux/vmalloc.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include "internal.h"
@@ -32,6 +33,10 @@ static LIST_HEAD(vmcore_list);
 /* Stores the pointer to the buffer containing kernel elf core headers. */
 static char *elfcorebuf;
 static size_t elfcorebuf_sz;
+static size_t elfcorebuf_sz_orig;
+
+static char *elfnotes_buf;
+static size_t elfnotes_sz;
 
 /* Total size of vmcore file. */
 static u64 vmcore_size;
@@ -118,27 +123,6 @@ static ssize_t read_from_oldmem(char *buf, size_t count,
 	return read;
 }
 
-/* Maps vmcore file offset to respective physical address in memroy. */
-static u64 map_offset_to_paddr(loff_t offset, struct list_head *vc_list,
-					struct vmcore **m_ptr)
-{
-	struct vmcore *m;
-	u64 paddr;
-
-	list_for_each_entry(m, vc_list, list) {
-		u64 start, end;
-		start = m->offset;
-		end = m->offset + m->size - 1;
-		if (offset >= start && offset <= end) {
-			paddr = m->paddr + offset - start;
-			*m_ptr = m;
-			return paddr;
-		}
-	}
-	*m_ptr = NULL;
-	return 0;
-}
-
 /* Read from the ELF header and then the crash dump. On error, negative value is
  * returned otherwise number of bytes read are returned.
  */
@@ -147,8 +131,8 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 {
 	ssize_t acc = 0, tmp;
 	size_t tsz;
-	u64 start, nr_bytes;
-	struct vmcore *curr_m = NULL;
+	u64 start;
+	struct vmcore *m = NULL;
 
 	if (buflen == 0 || *fpos >= vmcore_size)
 		return 0;
@@ -159,9 +143,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 
 	/* Read ELF core header */
 	if (*fpos < elfcorebuf_sz) {
-		tsz = elfcorebuf_sz - *fpos;
-		if (buflen < tsz)
-			tsz = buflen;
+		tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen);
 		if (copy_to_user(buffer, elfcorebuf + *fpos, tsz))
 			return -EFAULT;
 		buflen -= tsz;
@@ -174,39 +156,161 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 			return acc;
 	}
 
-	start = map_offset_to_paddr(*fpos, &vmcore_list, &curr_m);
-	if (!curr_m)
-        	return -EINVAL;
-
-	while (buflen) {
-		tsz = min_t(size_t, buflen, PAGE_SIZE - (start & ~PAGE_MASK));
+	/* Read Elf note segment */
+	if (*fpos < elfcorebuf_sz + elfnotes_sz) {
+		void *kaddr;
 
-		/* Calculate left bytes in current memory segment. */
-		nr_bytes = (curr_m->size - (start - curr_m->paddr));
-		if (tsz > nr_bytes)
-			tsz = nr_bytes;
-
-		tmp = read_from_oldmem(buffer, tsz, &start, 1);
-		if (tmp < 0)
-			return tmp;
+		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen);
+		kaddr = elfnotes_buf + *fpos - elfcorebuf_sz;
+		if (copy_to_user(buffer, kaddr, tsz))
+			return -EFAULT;
 		buflen -= tsz;
 		*fpos += tsz;
 		buffer += tsz;
 		acc += tsz;
-		if (start >= (curr_m->paddr + curr_m->size)) {
-			if (curr_m->list.next == &vmcore_list)
-				return acc;	/*EOF*/
-			curr_m = list_entry(curr_m->list.next,
-						struct vmcore, list);
-			start = curr_m->paddr;
+
+		/* leave now if filled buffer already */
+		if (buflen == 0)
+			return acc;
+	}
+
+	list_for_each_entry(m, &vmcore_list, list) {
+		if (*fpos < m->offset + m->size) {
+			tsz = min_t(size_t, m->offset + m->size - *fpos, buflen);
+			start = m->paddr + *fpos - m->offset;
+			tmp = read_from_oldmem(buffer, tsz, &start, 1);
+			if (tmp < 0)
+				return tmp;
+			buflen -= tsz;
+			*fpos += tsz;
+			buffer += tsz;
+			acc += tsz;
+
+			/* leave now if filled buffer already */
+			if (buflen == 0)
+				return acc;
 		}
 	}
+
 	return acc;
 }
 
+/**
+ * alloc_elfnotes_buf - allocate buffer for ELF note segment in
+ *                      vmalloc memory
+ *
+ * @notes_sz: size of buffer
+ *
+ * If CONFIG_MMU is defined, use vmalloc_user() to allow users to mmap
+ * the buffer to user-space by means of remap_vmalloc_range().
+ *
+ * If CONFIG_MMU is not defined, use vzalloc() since mmap_vmcore() is
+ * disabled and there's no need to allow users to mmap the buffer.
+ */
+static inline char *alloc_elfnotes_buf(size_t notes_sz)
+{
+#ifdef CONFIG_MMU
+	return vmalloc_user(notes_sz);
+#else
+	return vzalloc(notes_sz);
+#endif
+}
+
+/*
+ * Disable mmap_vmcore() if CONFIG_MMU is not defined. MMU is
+ * essential for mmap_vmcore() in order to map physically
+ * non-contiguous objects (ELF header, ELF note segment and memory
+ * regions in the 1st kernel pointed to by PT_LOAD entries) into
+ * virtually contiguous user-space in ELF layout.
+ */
+#ifdef CONFIG_MMU
+static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
+{
+	size_t size = vma->vm_end - vma->vm_start;
+	u64 start, end, len, tsz;
+	struct vmcore *m;
+
+	start = (u64)vma->vm_pgoff << PAGE_SHIFT;
+	end = start + size;
+
+	if (size > vmcore_size || end > vmcore_size)
+		return -EINVAL;
+
+	if (vma->vm_flags & (VM_WRITE | VM_EXEC))
+		return -EPERM;
+
+	vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
+	vma->vm_flags |= VM_MIXEDMAP;
+
+	len = 0;
+
+	if (start < elfcorebuf_sz) {
+		u64 pfn;
+
+		tsz = min(elfcorebuf_sz - (size_t)start, size);
+		pfn = __pa(elfcorebuf + start) >> PAGE_SHIFT;
+		if (remap_pfn_range(vma, vma->vm_start, pfn, tsz,
+				    vma->vm_page_prot))
+			return -EAGAIN;
+		size -= tsz;
+		start += tsz;
+		len += tsz;
+
+		if (size == 0)
+			return 0;
+	}
+
+	if (start < elfcorebuf_sz + elfnotes_sz) {
+		void *kaddr;
+
+		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)start, size);
+		kaddr = elfnotes_buf + start - elfcorebuf_sz;
+		if (remap_vmalloc_range_partial(vma, vma->vm_start + len,
+						kaddr, tsz))
+			goto fail;
+		size -= tsz;
+		start += tsz;
+		len += tsz;
+
+		if (size == 0)
+			return 0;
+	}
+
+	list_for_each_entry(m, &vmcore_list, list) {
+		if (start < m->offset + m->size) {
+			u64 paddr = 0;
+
+			tsz = min_t(size_t, m->offset + m->size - start, size);
+			paddr = m->paddr + start - m->offset;
+			if (remap_pfn_range(vma, vma->vm_start + len,
+					    paddr >> PAGE_SHIFT, tsz,
+					    vma->vm_page_prot))
+				goto fail;
+			size -= tsz;
+			start += tsz;
+			len += tsz;
+
+			if (size == 0)
+				return 0;
+		}
+	}
+
+	return 0;
+fail:
+	do_munmap(vma->vm_mm, vma->vm_start, len);
+	return -EAGAIN;
+}
+#else
+static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
+{
+	return -ENOSYS;
+}
+#endif
+
 static const struct file_operations proc_vmcore_operations = {
 	.read		= read_vmcore,
 	.llseek		= default_llseek,
+	.mmap		= mmap_vmcore,
 };
 
 static struct vmcore* __init get_new_element(void)
@@ -214,61 +318,40 @@ static struct vmcore* __init get_new_element(void)
 	return kzalloc(sizeof(struct vmcore), GFP_KERNEL);
 }
 
-static u64 __init get_vmcore_size_elf64(char *elfptr)
+static u64 __init get_vmcore_size(size_t elfsz, size_t elfnotesegsz,
+				  struct list_head *vc_list)
 {
-	int i;
-	u64 size;
-	Elf64_Ehdr *ehdr_ptr;
-	Elf64_Phdr *phdr_ptr;
-
-	ehdr_ptr = (Elf64_Ehdr *)elfptr;
-	phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr));
-	size = sizeof(Elf64_Ehdr) + ((ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr));
-	for (i = 0; i < ehdr_ptr->e_phnum; i++) {
-		size += phdr_ptr->p_memsz;
-		phdr_ptr++;
-	}
-	return size;
-}
-
-static u64 __init get_vmcore_size_elf32(char *elfptr)
-{
-	int i;
 	u64 size;
-	Elf32_Ehdr *ehdr_ptr;
-	Elf32_Phdr *phdr_ptr;
+	struct vmcore *m;
 
-	ehdr_ptr = (Elf32_Ehdr *)elfptr;
-	phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr));
-	size = sizeof(Elf32_Ehdr) + ((ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr));
-	for (i = 0; i < ehdr_ptr->e_phnum; i++) {
-		size += phdr_ptr->p_memsz;
-		phdr_ptr++;
+	size = elfsz + elfnotesegsz;
+	list_for_each_entry(m, vc_list, list) {
+		size += m->size;
 	}
 	return size;
 }
 
-/* Merges all the PT_NOTE headers into one. */
-static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
-						struct list_head *vc_list)
+/**
+ * update_note_header_size_elf64 - update p_memsz member of each PT_NOTE entry
+ *
+ * @ehdr_ptr: ELF header
+ *
+ * This function updates p_memsz member of each PT_NOTE entry in the
+ * program header table pointed to by @ehdr_ptr to real size of ELF
+ * note segment.
+ */
+static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr)
 {
-	int i, nr_ptnote=0, rc=0;
-	char *tmp;
-	Elf64_Ehdr *ehdr_ptr;
-	Elf64_Phdr phdr, *phdr_ptr;
+	int i, rc=0;
+	Elf64_Phdr *phdr_ptr;
 	Elf64_Nhdr *nhdr_ptr;
-	u64 phdr_sz = 0, note_off;
 
-	ehdr_ptr = (Elf64_Ehdr *)elfptr;
-	phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr));
+	phdr_ptr = (Elf64_Phdr *)(ehdr_ptr + 1);
 	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
-		int j;
 		void *notes_section;
-		struct vmcore *new;
 		u64 offset, max_sz, sz, real_sz = 0;
 		if (phdr_ptr->p_type != PT_NOTE)
 			continue;
-		nr_ptnote++;
 		max_sz = phdr_ptr->p_memsz;
 		offset = phdr_ptr->p_offset;
 		notes_section = kmalloc(max_sz, GFP_KERNEL);
@@ -280,7 +363,7 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
 			return rc;
 		}
 		nhdr_ptr = notes_section;
-		for (j = 0; j < max_sz; j += sz) {
+		while (real_sz < max_sz) {
 			if (nhdr_ptr->n_namesz == 0)
 				break;
 			sz = sizeof(Elf64_Nhdr) +
@@ -289,26 +372,122 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
 			real_sz += sz;
 			nhdr_ptr = (Elf64_Nhdr*)((char*)nhdr_ptr + sz);
 		}
-
-		/* Add this contiguous chunk of notes section to vmcore list.*/
-		new = get_new_element();
-		if (!new) {
-			kfree(notes_section);
-			return -ENOMEM;
-		}
-		new->paddr = phdr_ptr->p_offset;
-		new->size = real_sz;
-		list_add_tail(&new->list, vc_list);
-		phdr_sz += real_sz;
 		kfree(notes_section);
+		phdr_ptr->p_memsz = real_sz;
+	}
+
+	return 0;
+}
+
+/**
+ * get_note_number_and_size_elf64 - get the number of PT_NOTE program
+ * headers and sum of real size of their ELF note segment headers and
+ * data.
+ *
+ * @ehdr_ptr: ELF header
+ * @nr_ptnote: buffer for the number of PT_NOTE program headers
+ * @sz_ptnote: buffer for size of unique PT_NOTE program header
+ *
+ * This function is used to merge multiple PT_NOTE program headers
+ * into a unique single one. The resulting unique entry will have
+ * @sz_ptnote in its phdr->p_mem.
+ *
+ * It is assumed that program headers with PT_NOTE type pointed to by
+ * @ehdr_ptr has already been updated by update_note_header_size_elf64
+ * and each of PT_NOTE program headers has actual ELF note segment
+ * size in its p_memsz member.
+ */
+static int __init get_note_number_and_size_elf64(const Elf64_Ehdr *ehdr_ptr,
+						 int *nr_ptnote, u64 *sz_ptnote)
+{
+	int i;
+	Elf64_Phdr *phdr_ptr;
+
+	*nr_ptnote = *sz_ptnote = 0;
+
+	phdr_ptr = (Elf64_Phdr *)(ehdr_ptr + 1);
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		if (phdr_ptr->p_type != PT_NOTE)
+			continue;
+		*nr_ptnote += 1;
+		*sz_ptnote += phdr_ptr->p_memsz;
+	}
+
+	return 0;
+}
+
+/**
+ * copy_notes_elf64 - copy ELF note segments in a given buffer
+ *
+ * @ehdr_ptr: ELF header
+ * @notes_buf: buffer into which ELF note segments are copied
+ *
+ * This function is used to copy ELF note segment in the 1st kernel
+ * into the buffer @notes_buf in the 2nd kernel. It is assumed that
+ * size of the buffer @notes_buf is equal to or larger than sum of the
+ * real ELF note segment headers and data.
+ *
+ * It is assumed that program headers with PT_NOTE type pointed to by
+ * @ehdr_ptr has already been updated by update_note_header_size_elf64
+ * and each of PT_NOTE program headers has actual ELF note segment
+ * size in its p_memsz member.
+ */
+static int __init copy_notes_elf64(const Elf64_Ehdr *ehdr_ptr, char *notes_buf)
+{
+	int i, rc=0;
+	Elf64_Phdr *phdr_ptr;
+
+	phdr_ptr = (Elf64_Phdr*)(ehdr_ptr + 1);
+
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		u64 offset;
+		if (phdr_ptr->p_type != PT_NOTE)
+			continue;
+		offset = phdr_ptr->p_offset;
+		rc = read_from_oldmem(notes_buf, phdr_ptr->p_memsz, &offset, 0);
+		if (rc < 0)
+			return rc;
+		notes_buf += phdr_ptr->p_memsz;
 	}
 
+	return 0;
+}
+
+/* Merges all the PT_NOTE headers into one. */
+static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
+					   char **notes_buf, size_t *notes_sz)
+{
+	int i, nr_ptnote=0, rc=0;
+	char *tmp;
+	Elf64_Ehdr *ehdr_ptr;
+	Elf64_Phdr phdr;
+	u64 phdr_sz = 0, note_off;
+
+	ehdr_ptr = (Elf64_Ehdr *)elfptr;
+
+	rc = update_note_header_size_elf64(ehdr_ptr);
+	if (rc < 0)
+		return rc;
+
+	rc = get_note_number_and_size_elf64(ehdr_ptr, &nr_ptnote, &phdr_sz);
+	if (rc < 0)
+		return rc;
+
+	*notes_sz = roundup(phdr_sz, PAGE_SIZE);
+	*notes_buf = alloc_elfnotes_buf(*notes_sz);
+	if (!*notes_buf)
+		return -ENOMEM;
+
+	rc = copy_notes_elf64(ehdr_ptr, *notes_buf);
+	if (rc < 0)
+		return rc;
+
 	/* Prepare merged PT_NOTE program header. */
 	phdr.p_type    = PT_NOTE;
 	phdr.p_flags   = 0;
 	note_off = sizeof(Elf64_Ehdr) +
 			(ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf64_Phdr);
-	phdr.p_offset  = note_off;
+	phdr.p_offset  = roundup(note_off, PAGE_SIZE);
 	phdr.p_vaddr   = phdr.p_paddr = 0;
 	phdr.p_filesz  = phdr.p_memsz = phdr_sz;
 	phdr.p_align   = 0;
@@ -322,6 +501,8 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
 	i = (nr_ptnote - 1) * sizeof(Elf64_Phdr);
 	*elfsz = *elfsz - i;
 	memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf64_Ehdr)-sizeof(Elf64_Phdr)));
+	memset(elfptr + *elfsz, 0, i);
+	*elfsz = roundup(*elfsz, PAGE_SIZE);
 
 	/* Modify e_phnum to reflect merged headers. */
 	ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;
@@ -329,27 +510,27 @@ static int __init merge_note_headers_elf64(char *elfptr, size_t *elfsz,
 	return 0;
 }
 
-/* Merges all the PT_NOTE headers into one. */
-static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
-						struct list_head *vc_list)
+/**
+ * update_note_header_size_elf32 - update p_memsz member of each PT_NOTE entry
+ *
+ * @ehdr_ptr: ELF header
+ *
+ * This function updates p_memsz member of each PT_NOTE entry in the
+ * program header table pointed to by @ehdr_ptr to real size of ELF
+ * note segment.
+ */
+static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr)
 {
-	int i, nr_ptnote=0, rc=0;
-	char *tmp;
-	Elf32_Ehdr *ehdr_ptr;
-	Elf32_Phdr phdr, *phdr_ptr;
+	int i, rc=0;
+	Elf32_Phdr *phdr_ptr;
 	Elf32_Nhdr *nhdr_ptr;
-	u64 phdr_sz = 0, note_off;
 
-	ehdr_ptr = (Elf32_Ehdr *)elfptr;
-	phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr));
+	phdr_ptr = (Elf32_Phdr *)(ehdr_ptr + 1);
 	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
-		int j;
 		void *notes_section;
-		struct vmcore *new;
 		u64 offset, max_sz, sz, real_sz = 0;
 		if (phdr_ptr->p_type != PT_NOTE)
 			continue;
-		nr_ptnote++;
 		max_sz = phdr_ptr->p_memsz;
 		offset = phdr_ptr->p_offset;
 		notes_section = kmalloc(max_sz, GFP_KERNEL);
@@ -361,7 +542,7 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
 			return rc;
 		}
 		nhdr_ptr = notes_section;
-		for (j = 0; j < max_sz; j += sz) {
+		while (real_sz < max_sz) {
 			if (nhdr_ptr->n_namesz == 0)
 				break;
 			sz = sizeof(Elf32_Nhdr) +
@@ -370,26 +551,122 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
 			real_sz += sz;
 			nhdr_ptr = (Elf32_Nhdr*)((char*)nhdr_ptr + sz);
 		}
-
-		/* Add this contiguous chunk of notes section to vmcore list.*/
-		new = get_new_element();
-		if (!new) {
-			kfree(notes_section);
-			return -ENOMEM;
-		}
-		new->paddr = phdr_ptr->p_offset;
-		new->size = real_sz;
-		list_add_tail(&new->list, vc_list);
-		phdr_sz += real_sz;
 		kfree(notes_section);
+		phdr_ptr->p_memsz = real_sz;
+	}
+
+	return 0;
+}
+
+/**
+ * get_note_number_and_size_elf32 - get the number of PT_NOTE program
+ * headers and sum of real size of their ELF note segment headers and
+ * data.
+ *
+ * @ehdr_ptr: ELF header
+ * @nr_ptnote: buffer for the number of PT_NOTE program headers
+ * @sz_ptnote: buffer for size of unique PT_NOTE program header
+ *
+ * This function is used to merge multiple PT_NOTE program headers
+ * into a unique single one. The resulting unique entry will have
+ * @sz_ptnote in its phdr->p_mem.
+ *
+ * It is assumed that program headers with PT_NOTE type pointed to by
+ * @ehdr_ptr has already been updated by update_note_header_size_elf32
+ * and each of PT_NOTE program headers has actual ELF note segment
+ * size in its p_memsz member.
+ */
+static int __init get_note_number_and_size_elf32(const Elf32_Ehdr *ehdr_ptr,
+						 int *nr_ptnote, u64 *sz_ptnote)
+{
+	int i;
+	Elf32_Phdr *phdr_ptr;
+
+	*nr_ptnote = *sz_ptnote = 0;
+
+	phdr_ptr = (Elf32_Phdr *)(ehdr_ptr + 1);
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		if (phdr_ptr->p_type != PT_NOTE)
+			continue;
+		*nr_ptnote += 1;
+		*sz_ptnote += phdr_ptr->p_memsz;
+	}
+
+	return 0;
+}
+
+/**
+ * copy_notes_elf32 - copy ELF note segments in a given buffer
+ *
+ * @ehdr_ptr: ELF header
+ * @notes_buf: buffer into which ELF note segments are copied
+ *
+ * This function is used to copy ELF note segment in the 1st kernel
+ * into the buffer @notes_buf in the 2nd kernel. It is assumed that
+ * size of the buffer @notes_buf is equal to or larger than sum of the
+ * real ELF note segment headers and data.
+ *
+ * It is assumed that program headers with PT_NOTE type pointed to by
+ * @ehdr_ptr has already been updated by update_note_header_size_elf32
+ * and each of PT_NOTE program headers has actual ELF note segment
+ * size in its p_memsz member.
+ */
+static int __init copy_notes_elf32(const Elf32_Ehdr *ehdr_ptr, char *notes_buf)
+{
+	int i, rc=0;
+	Elf32_Phdr *phdr_ptr;
+
+	phdr_ptr = (Elf32_Phdr*)(ehdr_ptr + 1);
+
+	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		u64 offset;
+		if (phdr_ptr->p_type != PT_NOTE)
+			continue;
+		offset = phdr_ptr->p_offset;
+		rc = read_from_oldmem(notes_buf, phdr_ptr->p_memsz, &offset, 0);
+		if (rc < 0)
+			return rc;
+		notes_buf += phdr_ptr->p_memsz;
 	}
 
+	return 0;
+}
+
+/* Merges all the PT_NOTE headers into one. */
+static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
+					   char **notes_buf, size_t *notes_sz)
+{
+	int i, nr_ptnote=0, rc=0;
+	char *tmp;
+	Elf32_Ehdr *ehdr_ptr;
+	Elf32_Phdr phdr;
+	u64 phdr_sz = 0, note_off;
+
+	ehdr_ptr = (Elf32_Ehdr *)elfptr;
+
+	rc = update_note_header_size_elf32(ehdr_ptr);
+	if (rc < 0)
+		return rc;
+
+	rc = get_note_number_and_size_elf32(ehdr_ptr, &nr_ptnote, &phdr_sz);
+	if (rc < 0)
+		return rc;
+
+	*notes_sz = roundup(phdr_sz, PAGE_SIZE);
+	*notes_buf = alloc_elfnotes_buf(*notes_sz);
+	if (!*notes_buf)
+		return -ENOMEM;
+
+	rc = copy_notes_elf32(ehdr_ptr, *notes_buf);
+	if (rc < 0)
+		return rc;
+
 	/* Prepare merged PT_NOTE program header. */
 	phdr.p_type    = PT_NOTE;
 	phdr.p_flags   = 0;
 	note_off = sizeof(Elf32_Ehdr) +
 			(ehdr_ptr->e_phnum - nr_ptnote +1) * sizeof(Elf32_Phdr);
-	phdr.p_offset  = note_off;
+	phdr.p_offset  = roundup(note_off, PAGE_SIZE);
 	phdr.p_vaddr   = phdr.p_paddr = 0;
 	phdr.p_filesz  = phdr.p_memsz = phdr_sz;
 	phdr.p_align   = 0;
@@ -403,6 +680,8 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
 	i = (nr_ptnote - 1) * sizeof(Elf32_Phdr);
 	*elfsz = *elfsz - i;
 	memmove(tmp, tmp+i, ((*elfsz)-sizeof(Elf32_Ehdr)-sizeof(Elf32_Phdr)));
+	memset(elfptr + *elfsz, 0, i);
+	*elfsz = roundup(*elfsz, PAGE_SIZE);
 
 	/* Modify e_phnum to reflect merged headers. */
 	ehdr_ptr->e_phnum = ehdr_ptr->e_phnum - nr_ptnote + 1;
@@ -414,6 +693,7 @@ static int __init merge_note_headers_elf32(char *elfptr, size_t *elfsz,
  * the new offset fields of exported program headers. */
 static int __init process_ptload_program_headers_elf64(char *elfptr,
 						size_t elfsz,
+						size_t elfnotes_sz,
 						struct list_head *vc_list)
 {
 	int i;
@@ -425,32 +705,38 @@ static int __init process_ptload_program_headers_elf64(char *elfptr,
 	ehdr_ptr = (Elf64_Ehdr *)elfptr;
 	phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */
 
-	/* First program header is PT_NOTE header. */
-	vmcore_off = sizeof(Elf64_Ehdr) +
-			(ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr) +
-			phdr_ptr->p_memsz; /* Note sections */
+	/* Skip Elf header, program headers and Elf note segment. */
+	vmcore_off = elfsz + elfnotes_sz;
 
 	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		u64 paddr, start, end, size;
+
 		if (phdr_ptr->p_type != PT_LOAD)
 			continue;
 
+		paddr = phdr_ptr->p_offset;
+		start = rounddown(paddr, PAGE_SIZE);
+		end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE);
+		size = end - start;
+
 		/* Add this contiguous chunk of memory to vmcore list.*/
 		new = get_new_element();
 		if (!new)
 			return -ENOMEM;
-		new->paddr = phdr_ptr->p_offset;
-		new->size = phdr_ptr->p_memsz;
+		new->paddr = start;
+		new->size = size;
 		list_add_tail(&new->list, vc_list);
 
 		/* Update the program header offset. */
-		phdr_ptr->p_offset = vmcore_off;
-		vmcore_off = vmcore_off + phdr_ptr->p_memsz;
+		phdr_ptr->p_offset = vmcore_off + (paddr - start);
+		vmcore_off = vmcore_off + size;
 	}
 	return 0;
 }
 
 static int __init process_ptload_program_headers_elf32(char *elfptr,
 						size_t elfsz,
+						size_t elfnotes_sz,
 						struct list_head *vc_list)
 {
 	int i;
@@ -462,43 +748,44 @@ static int __init process_ptload_program_headers_elf32(char *elfptr,
 	ehdr_ptr = (Elf32_Ehdr *)elfptr;
 	phdr_ptr = (Elf32_Phdr*)(elfptr + sizeof(Elf32_Ehdr)); /* PT_NOTE hdr */
 
-	/* First program header is PT_NOTE header. */
-	vmcore_off = sizeof(Elf32_Ehdr) +
-			(ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr) +
-			phdr_ptr->p_memsz; /* Note sections */
+	/* Skip Elf header, program headers and Elf note segment. */
+	vmcore_off = elfsz + elfnotes_sz;
 
 	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		u64 paddr, start, end, size;
+
 		if (phdr_ptr->p_type != PT_LOAD)
 			continue;
 
+		paddr = phdr_ptr->p_offset;
+		start = rounddown(paddr, PAGE_SIZE);
+		end = roundup(paddr + phdr_ptr->p_memsz, PAGE_SIZE);
+		size = end - start;
+
 		/* Add this contiguous chunk of memory to vmcore list.*/
 		new = get_new_element();
 		if (!new)
 			return -ENOMEM;
-		new->paddr = phdr_ptr->p_offset;
-		new->size = phdr_ptr->p_memsz;
+		new->paddr = start;
+		new->size = size;
 		list_add_tail(&new->list, vc_list);
 
 		/* Update the program header offset */
-		phdr_ptr->p_offset = vmcore_off;
-		vmcore_off = vmcore_off + phdr_ptr->p_memsz;
+		phdr_ptr->p_offset = vmcore_off + (paddr - start);
+		vmcore_off = vmcore_off + size;
 	}
 	return 0;
 }
 
 /* Sets offset fields of vmcore elements. */
-static void __init set_vmcore_list_offsets_elf64(char *elfptr,
-						struct list_head *vc_list)
+static void __init set_vmcore_list_offsets(size_t elfsz, size_t elfnotes_sz,
+					   struct list_head *vc_list)
 {
 	loff_t vmcore_off;
-	Elf64_Ehdr *ehdr_ptr;
 	struct vmcore *m;
 
-	ehdr_ptr = (Elf64_Ehdr *)elfptr;
-
-	/* Skip Elf header and program headers. */
-	vmcore_off = sizeof(Elf64_Ehdr) +
-			(ehdr_ptr->e_phnum) * sizeof(Elf64_Phdr);
+	/* Skip Elf header, program headers and Elf note segment. */
+	vmcore_off = elfsz + elfnotes_sz;
 
 	list_for_each_entry(m, vc_list, list) {
 		m->offset = vmcore_off;
@@ -506,24 +793,12 @@ static void __init set_vmcore_list_offsets_elf64(char *elfptr,
 	}
 }
 
-/* Sets offset fields of vmcore elements. */
-static void __init set_vmcore_list_offsets_elf32(char *elfptr,
-						struct list_head *vc_list)
+static void free_elfcorebuf(void)
 {
-	loff_t vmcore_off;
-	Elf32_Ehdr *ehdr_ptr;
-	struct vmcore *m;
-
-	ehdr_ptr = (Elf32_Ehdr *)elfptr;
-
-	/* Skip Elf header and program headers. */
-	vmcore_off = sizeof(Elf32_Ehdr) +
-			(ehdr_ptr->e_phnum) * sizeof(Elf32_Phdr);
-
-	list_for_each_entry(m, vc_list, list) {
-		m->offset = vmcore_off;
-		vmcore_off += m->size;
-	}
+	free_pages((unsigned long)elfcorebuf, get_order(elfcorebuf_sz_orig));
+	elfcorebuf = NULL;
+	vfree(elfnotes_buf);
+	elfnotes_buf = NULL;
 }
 
 static int __init parse_crash_elf64_headers(void)
@@ -554,31 +829,32 @@ static int __init parse_crash_elf64_headers(void)
 	}
 
 	/* Read in all elf headers. */
-	elfcorebuf_sz = sizeof(Elf64_Ehdr) + ehdr.e_phnum * sizeof(Elf64_Phdr);
-	elfcorebuf = kmalloc(elfcorebuf_sz, GFP_KERNEL);
+	elfcorebuf_sz_orig = sizeof(Elf64_Ehdr) +
+				ehdr.e_phnum * sizeof(Elf64_Phdr);
+	elfcorebuf_sz = elfcorebuf_sz_orig;
+	elfcorebuf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+					      get_order(elfcorebuf_sz_orig));
 	if (!elfcorebuf)
 		return -ENOMEM;
 	addr = elfcorehdr_addr;
-	rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz, &addr, 0);
-	if (rc < 0) {
-		kfree(elfcorebuf);
-		return rc;
-	}
+	rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz_orig, &addr, 0);
+	if (rc < 0)
+		goto fail;
 
 	/* Merge all PT_NOTE headers into one. */
-	rc = merge_note_headers_elf64(elfcorebuf, &elfcorebuf_sz, &vmcore_list);
-	if (rc) {
-		kfree(elfcorebuf);
-		return rc;
-	}
+	rc = merge_note_headers_elf64(elfcorebuf, &elfcorebuf_sz,
+				      &elfnotes_buf, &elfnotes_sz);
+	if (rc)
+		goto fail;
 	rc = process_ptload_program_headers_elf64(elfcorebuf, elfcorebuf_sz,
-							&vmcore_list);
-	if (rc) {
-		kfree(elfcorebuf);
-		return rc;
-	}
-	set_vmcore_list_offsets_elf64(elfcorebuf, &vmcore_list);
+						  elfnotes_sz, &vmcore_list);
+	if (rc)
+		goto fail;
+	set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
 	return 0;
+fail:
+	free_elfcorebuf();
+	return rc;
 }
 
 static int __init parse_crash_elf32_headers(void)
@@ -609,31 +885,31 @@ static int __init parse_crash_elf32_headers(void)
 	}
 
 	/* Read in all elf headers. */
-	elfcorebuf_sz = sizeof(Elf32_Ehdr) + ehdr.e_phnum * sizeof(Elf32_Phdr);
-	elfcorebuf = kmalloc(elfcorebuf_sz, GFP_KERNEL);
+	elfcorebuf_sz_orig = sizeof(Elf32_Ehdr) + ehdr.e_phnum * sizeof(Elf32_Phdr);
+	elfcorebuf_sz = elfcorebuf_sz_orig;
+	elfcorebuf = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO,
+					      get_order(elfcorebuf_sz_orig));
 	if (!elfcorebuf)
 		return -ENOMEM;
 	addr = elfcorehdr_addr;
-	rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz, &addr, 0);
-	if (rc < 0) {
-		kfree(elfcorebuf);
-		return rc;
-	}
+	rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz_orig, &addr, 0);
+	if (rc < 0)
+		goto fail;
 
 	/* Merge all PT_NOTE headers into one. */
-	rc = merge_note_headers_elf32(elfcorebuf, &elfcorebuf_sz, &vmcore_list);
-	if (rc) {
-		kfree(elfcorebuf);
-		return rc;
-	}
+	rc = merge_note_headers_elf32(elfcorebuf, &elfcorebuf_sz,
+				      &elfnotes_buf, &elfnotes_sz);
+	if (rc)
+		goto fail;
 	rc = process_ptload_program_headers_elf32(elfcorebuf, elfcorebuf_sz,
-								&vmcore_list);
-	if (rc) {
-		kfree(elfcorebuf);
-		return rc;
-	}
-	set_vmcore_list_offsets_elf32(elfcorebuf, &vmcore_list);
+						  elfnotes_sz, &vmcore_list);
+	if (rc)
+		goto fail;
+	set_vmcore_list_offsets(elfcorebuf_sz, elfnotes_sz, &vmcore_list);
 	return 0;
+fail:
+	free_elfcorebuf();
+	return rc;
 }
 
 static int __init parse_crash_elf_headers(void)
@@ -655,20 +931,19 @@ static int __init parse_crash_elf_headers(void)
 		rc = parse_crash_elf64_headers();
 		if (rc)
 			return rc;
-
-		/* Determine vmcore size. */
-		vmcore_size = get_vmcore_size_elf64(elfcorebuf);
 	} else if (e_ident[EI_CLASS] == ELFCLASS32) {
 		rc = parse_crash_elf32_headers();
 		if (rc)
 			return rc;
-
-		/* Determine vmcore size. */
-		vmcore_size = get_vmcore_size_elf32(elfcorebuf);
 	} else {
 		pr_warn("Warning: Core image elf header is not sane\n");
 		return -EINVAL;
 	}
+
+	/* Determine vmcore size. */
+	vmcore_size = get_vmcore_size(elfcorebuf_sz, elfnotes_sz,
+				      &vmcore_list);
+
 	return 0;
 }
 
@@ -711,7 +986,6 @@ void vmcore_cleanup(void)
 		list_del(&m->list);
 		kfree(m);
 	}
-	kfree(elfcorebuf);
-	elfcorebuf = NULL;
+	free_elfcorebuf();
 }
 EXPORT_SYMBOL_GPL(vmcore_cleanup);