procfs: introduce the /proc/<pid>/map_files/ directory

This one behaves similarly to the /proc/<pid>/fd/ one - it contains
symlinks one for each mapping with file, the name of a symlink is
"vma->vm_start-vma->vm_end", the target is the file.  Opening a symlink
results in a file that point exactly to the same inode as them vma's one.

For example the ls -l of some arbitrary /proc/<pid>/map_files/

 | lr-x------ 1 root root 64 Aug 26 06:40 7f8f80403000-7f8f80404000 -> /lib64/libc-2.5.so
 | lr-x------ 1 root root 64 Aug 26 06:40 7f8f8061e000-7f8f80620000 -> /lib64/libselinux.so.1
 | lr-x------ 1 root root 64 Aug 26 06:40 7f8f80826000-7f8f80827000 -> /lib64/libacl.so.1.1.0
 | lr-x------ 1 root root 64 Aug 26 06:40 7f8f80a2f000-7f8f80a30000 -> /lib64/librt-2.5.so
 | lr-x------ 1 root root 64 Aug 26 06:40 7f8f80a30000-7f8f80a4c000 -> /lib64/ld-2.5.so

This *helps* checkpointing process in three ways:

1. When dumping a task mappings we do know exact file that is mapped
   by particular region.  We do this by opening
   /proc/$pid/map_files/$address symlink the way we do with file
   descriptors.

2. This also helps in determining which anonymous shared mappings are
   shared with each other by comparing the inodes of them.

3. When restoring a set of processes in case two of them has a mapping
   shared, we map the memory by the 1st one and then open its
   /proc/$pid/map_files/$address file and map it by the 2nd task.

Using /proc/$pid/maps for this is quite inconvenient since it brings
repeatable re-reading and reparsing for this text file which slows down
restore procedure significantly.  Also as being pointed in (3) it is a way
easier to use top level shared mapping in children as
/proc/$pid/map_files/$address when needed.

[akpm@linux-foundation.org: coding-style fixes]
[gorcunov@openvz.org: make map_files depend on CHECKPOINT_RESTORE]
Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Reviewed-by: Vasiliy Kulikov <segoon@openwall.com>
Reviewed-by: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Tejun Heo <tj@kernel.org>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Pavel Machek <pavel@ucw.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 367 insertions, 0 deletions

diff --git a/fs/proc/base.c b/fs/proc/base.c
index e31d95055c6..4d755fed3ec 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -83,6 +83,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/fs_struct.h>
 #include <linux/slab.h>
+#include <linux/flex_array.h>
 #ifdef CONFIG_HARDWALL
 #include <asm/hardwall.h>
 #endif
@@ -134,6 +135,8 @@ struct pid_entry {
 		NULL, &proc_single_file_operations,	\
 		{ .proc_show = show } )
 
+static int proc_fd_permission(struct inode *inode, int mask);
+
 /*
  * Count the number of hardlinks for the pid_entry table, excluding the .
  * and .. links.
@@ -2046,6 +2049,355 @@ static const struct file_operations proc_fd_operations = {
 	.llseek		= default_llseek,
 };
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+
+/*
+ * dname_to_vma_addr - maps a dentry name into two unsigned longs
+ * which represent vma start and end addresses.
+ */
+static int dname_to_vma_addr(struct dentry *dentry,
+			     unsigned long *start, unsigned long *end)
+{
+	if (sscanf(dentry->d_name.name, "%lx-%lx", start, end) != 2)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int map_files_d_revalidate(struct dentry *dentry, struct nameidata *nd)
+{
+	unsigned long vm_start, vm_end;
+	bool exact_vma_exists = false;
+	struct mm_struct *mm = NULL;
+	struct task_struct *task;
+	const struct cred *cred;
+	struct inode *inode;
+	int status = 0;
+
+	if (nd && nd->flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	if (!capable(CAP_SYS_ADMIN)) {
+		status = -EACCES;
+		goto out_notask;
+	}
+
+	inode = dentry->d_inode;
+	task = get_proc_task(inode);
+	if (!task)
+		goto out_notask;
+
+	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+		goto out;
+
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out;
+
+	if (!dname_to_vma_addr(dentry, &vm_start, &vm_end)) {
+		down_read(&mm->mmap_sem);
+		exact_vma_exists = !!find_exact_vma(mm, vm_start, vm_end);
+		up_read(&mm->mmap_sem);
+	}
+
+	mmput(mm);
+
+	if (exact_vma_exists) {
+		if (task_dumpable(task)) {
+			rcu_read_lock();
+			cred = __task_cred(task);
+			inode->i_uid = cred->euid;
+			inode->i_gid = cred->egid;
+			rcu_read_unlock();
+		} else {
+			inode->i_uid = 0;
+			inode->i_gid = 0;
+		}
+		security_task_to_inode(task, inode);
+		status = 1;
+	}
+
+out:
+	put_task_struct(task);
+
+out_notask:
+	if (status <= 0)
+		d_drop(dentry);
+
+	return status;
+}
+
+static const struct dentry_operations tid_map_files_dentry_operations = {
+	.d_revalidate	= map_files_d_revalidate,
+	.d_delete	= pid_delete_dentry,
+};
+
+static int proc_map_files_get_link(struct dentry *dentry, struct path *path)
+{
+	unsigned long vm_start, vm_end;
+	struct vm_area_struct *vma;
+	struct task_struct *task;
+	struct mm_struct *mm;
+	int rc;
+
+	rc = -ENOENT;
+	task = get_proc_task(dentry->d_inode);
+	if (!task)
+		goto out;
+
+	mm = get_task_mm(task);
+	put_task_struct(task);
+	if (!mm)
+		goto out;
+
+	rc = dname_to_vma_addr(dentry, &vm_start, &vm_end);
+	if (rc)
+		goto out_mmput;
+
+	down_read(&mm->mmap_sem);
+	vma = find_exact_vma(mm, vm_start, vm_end);
+	if (vma && vma->vm_file) {
+		*path = vma->vm_file->f_path;
+		path_get(path);
+		rc = 0;
+	}
+	up_read(&mm->mmap_sem);
+
+out_mmput:
+	mmput(mm);
+out:
+	return rc;
+}
+
+struct map_files_info {
+	struct file	*file;
+	unsigned long	len;
+	unsigned char	name[4*sizeof(long)+2]; /* max: %lx-%lx\0 */
+};
+
+static struct dentry *
+proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
+			   struct task_struct *task, const void *ptr)
+{
+	const struct file *file = ptr;
+	struct proc_inode *ei;
+	struct inode *inode;
+
+	if (!file)
+		return ERR_PTR(-ENOENT);
+
+	inode = proc_pid_make_inode(dir->i_sb, task);
+	if (!inode)
+		return ERR_PTR(-ENOENT);
+
+	ei = PROC_I(inode);
+	ei->op.proc_get_link = proc_map_files_get_link;
+
+	inode->i_op = &proc_pid_link_inode_operations;
+	inode->i_size = 64;
+	inode->i_mode = S_IFLNK;
+
+	if (file->f_mode & FMODE_READ)
+		inode->i_mode |= S_IRUSR;
+	if (file->f_mode & FMODE_WRITE)
+		inode->i_mode |= S_IWUSR;
+
+	d_set_d_op(dentry, &tid_map_files_dentry_operations);
+	d_add(dentry, inode);
+
+	return NULL;
+}
+
+static struct dentry *proc_map_files_lookup(struct inode *dir,
+		struct dentry *dentry, struct nameidata *nd)
+{
+	unsigned long vm_start, vm_end;
+	struct vm_area_struct *vma;
+	struct task_struct *task;
+	struct dentry *result;
+	struct mm_struct *mm;
+
+	result = ERR_PTR(-EACCES);
+	if (!capable(CAP_SYS_ADMIN))
+		goto out;
+
+	result = ERR_PTR(-ENOENT);
+	task = get_proc_task(dir);
+	if (!task)
+		goto out;
+
+	result = ERR_PTR(-EACCES);
+	if (lock_trace(task))
+		goto out_put_task;
+
+	result = ERR_PTR(-ENOENT);
+	if (dname_to_vma_addr(dentry, &vm_start, &vm_end))
+		goto out_unlock;
+
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out_unlock;
+
+	down_read(&mm->mmap_sem);
+	vma = find_exact_vma(mm, vm_start, vm_end);
+	if (!vma)
+		goto out_no_vma;
+
+	result = proc_map_files_instantiate(dir, dentry, task, vma->vm_file);
+
+out_no_vma:
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+out_unlock:
+	unlock_trace(task);
+out_put_task:
+	put_task_struct(task);
+out:
+	return result;
+}
+
+static const struct inode_operations proc_map_files_inode_operations = {
+	.lookup		= proc_map_files_lookup,
+	.permission	= proc_fd_permission,
+	.setattr	= proc_setattr,
+};
+
+static int
+proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+	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;
+	int ret;
+
+	ret = -EACCES;
+	if (!capable(CAP_SYS_ADMIN))
+		goto out;
+
+	ret = -ENOENT;
+	task = get_proc_task(inode);
+	if (!task)
+		goto out;
+
+	ret = -EACCES;
+	if (lock_trace(task))
+		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_unlock;
+		filp->f_pos++;
+	case 1:
+		ino = parent_ino(dentry);
+		if (filldir(dirent, "..", 2, 1, ino, DT_DIR) < 0)
+			goto out_unlock;
+		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_unlock;
+		down_read(&mm->mmap_sem);
+
+		nr_files = 0;
+
+		/*
+		 * 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().
+		 */
+
+		for (vma = mm->mmap, pos = 2; vma; vma = vma->vm_next) {
+			if (vma->vm_file && ++pos > filp->f_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_unlock;
+			}
+			for (i = 0, vma = mm->mmap, pos = 2; vma;
+					vma = vma->vm_next) {
+				if (!vma->vm_file)
+					continue;
+				if (++pos <= filp->f_pos)
+					continue;
+
+				get_file(vma->vm_file);
+				info.file = vma->vm_file;
+				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();
+			}
+		}
+		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, p->file);
+			if (ret)
+				break;
+			filp->f_pos++;
+			fput(p->file);
+		}
+		for (; i < nr_files; i++) {
+			/*
+			 * In case of error don't forget
+			 * to put rest of file refs.
+			 */
+			p = flex_array_get(fa, i);
+			fput(p->file);
+		}
+		if (fa)
+			flex_array_free(fa);
+		mmput(mm);
+	}
+	}
+
+out_unlock:
+	unlock_trace(task);
+out_put_task:
+	put_task_struct(task);
+out:
+	return ret;
+}
+
+static const struct file_operations proc_map_files_operations = {
+	.read		= generic_read_dir,
+	.readdir	= proc_map_files_readdir,
+	.llseek		= default_llseek,
+};
+
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+
 /*
  * /proc/pid/fd needs a special permission handler so that a process can still
  * access /proc/self/fd after it has executed a setuid().
@@ -2661,6 +3013,9 @@ static const struct inode_operations proc_task_inode_operations;
 static const struct pid_entry tgid_base_stuff[] = {
 	DIR("task",       S_IRUGO|S_IXUGO, proc_task_inode_operations, proc_task_operations),
 	DIR("fd",         S_IRUSR|S_IXUSR, proc_fd_inode_operations, proc_fd_operations),
+#ifdef CONFIG_CHECKPOINT_RESTORE
+	DIR("map_files",  S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations),
+#endif
 	DIR("fdinfo",     S_IRUSR|S_IXUSR, proc_fdinfo_inode_operations, proc_fdinfo_operations),
 	DIR("ns",	  S_IRUSR|S_IXUGO, proc_ns_dir_inode_operations, proc_ns_dir_operations),
 #ifdef CONFIG_NET
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 5568553a41f..6eba2cc016c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1482,6 +1482,18 @@ static inline unsigned long vma_pages(struct vm_area_struct *vma)
 	return (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
 }
 
+/* Look up the first VMA which exactly match the interval vm_start ... vm_end */
+static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm,
+				unsigned long vm_start, unsigned long vm_end)
+{
+	struct vm_area_struct *vma = find_vma(mm, vm_start);
+
+	if (vma && (vma->vm_start != vm_start || vma->vm_end != vm_end))
+		vma = NULL;
+
+	return vma;
+}
+
 #ifdef CONFIG_MMU
 pgprot_t vm_get_page_prot(unsigned long vm_flags);
 #else