Re: [patch 2/2] fs, proc: Introduce the /proc/<pid>/map_files/ directory v6

[Cyrill Gorcunov <gorcunov@gmail.com>]

On Wed, Aug 31, 2011 at 03:10:23PM -0700, Andrew Morton wrote:
> 
> This function would benefit from a code comment.
> 
> Given that it's pretty generic (indeed there might be open-coded code
> which already does this elsewhere), perhaps it should be in mm/mmap.c
> as a kernel-wide utility function.  That will add a little overhead to
> CONFIG_PROC_FS=n builds, which doesn't seem terribly important.
> 

Andrew, here is an attempt to address concerns. Please review.
Complains are welcome as always!

	Cyrill
---
fs, proc: Introduce the /proc/<pid>/map_files/ directory v9

From: Pavel Emelyanov <xemul@parallels.com>

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 process 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.

v2: (spotted by Tejun Heo)
 - /proc/<pid>/mfd changed to /proc/<pid>/map_files
 - find_vma helper is used instead of linear search
 - routines are re-grouped
 - d_revalidate is set now

v3:
 - d_revalidate reworked, now it should drops no longer valid dentries (Tejun Heo)
 - ptrace_may_access added into proc_map_files_lookup (Vasiliy Kulikov)
 - because of filldir (which eventually might need to lock mmap_sem)
   the proc_map_files_readdir() was reworked to call proc_fill_cache()
   with unlocked mmap_sem

v4: (feedback by Tejun Heo and Vasiliy Kulikov)
 - instead of saving data in proc_inode we rather make a dentry name
   to keep both vm_start and vm_end accordingly
 - d_revalidate now honor task credentials

v5: (feedback by Kirill A. Shutemov)
 - don't forget to release mmap_sem on error path

v6:
 - sizeof get used in map_files_info which shrink member
   a bit on x86-32 (by Kirill A. Shutemov)
 - map_name_to_addr returns -EINVAL instead of -1
   which is more appropriate (by Tejun Heo)

v7:
 - add [get/set]attr handlers for
   proc_map_files_inode_operations (by Vasiliy Kulikov)

v8:
 - Kirill A. Shutemov spotted a parasite semicolon
   which ruined the ptrace_check call, fixed.

v9: (feedback by Andrew Morton)
 - find_exact_vma moved into include/linux/mm.h as
   an inline helper
 - proc_map_files_setattr uses either kmalloc or
   vmalloc depending on how many ojects are to be
   allocated
 - no more map_name_to_addr but dname_to_vma_addr
   introduced instead and it uses sscanf
 - because in one case the find_exact_vma() is used
   only to confirm existence of vma area the
   boolean flag is used
 - fancy justification dropped
 - still the proc_map_files_get/setattr leaved untouched
   until additional fd/ patches applied first.

Signed-off-by: Pavel Emelyanov <xemul@parallels.com>
Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
CC: Tejun Heo <tj@kernel.org>
CC: Vasiliy Kulikov <segoon@openwall.com>
CC: "Kirill A. Shutemov" <kirill@shutemov.name>
CC: Alexey Dobriyan <adobriyan@gmail.com>
CC: Al Viro <viro@ZenIV.linux.org.uk>
CC: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/base.c     |  353 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mm.h |   12 +
 2 files changed, 365 insertions(+)

Index: linux-2.6.git/fs/proc/base.c
===================================================================
--- linux-2.6.git.orig/fs/proc/base.c
+++ linux-2.6.git/fs/proc/base.c
@@ -2171,6 +2171,358 @@ static const struct file_operations proc
 };
 
 /*
+ * 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;
+	struct task_struct *task;
+	const struct cred *cred;
+	struct mm_struct *mm;
+	struct inode *inode;
+
+	bool exact_vma_exists = false;
+
+	if (nd && nd->flags & LOOKUP_RCU)
+		return -ECHILD;
+
+	inode = dentry->d_inode;
+	task = get_proc_task(inode);
+	if (!task)
+		goto out;
+
+	mm = get_task_mm(task);
+	put_task_struct(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);
+		return 1;
+	}
+out:
+	d_drop(dentry);
+	return 0;
+}
+
+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 = -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 | S_IXUSR;
+	if (file->f_mode & FMODE_WRITE)
+		inode->i_mode |= S_IWUSR | S_IXUSR;
+
+	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 task_struct *task;
+	struct vm_area_struct *vma;
+	struct mm_struct *mm;
+	struct dentry *result;
+
+	result = ERR_PTR(-ENOENT);
+	task = get_proc_task(dir);
+	if (!task)
+		goto out_no_task;
+
+	result = ERR_PTR(-EPERM);
+	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+		goto out_no_mm;
+
+	result = ERR_PTR(-ENOENT);
+	if (dname_to_vma_addr(dentry, &vm_start, &vm_end))
+		goto out_no_mm;
+
+	mm = get_task_mm(task);
+	if (!mm)
+		goto out_no_mm;
+
+	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_no_mm:
+	put_task_struct(task);
+out_no_task:
+	return result;
+}
+
+static int proc_map_files_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	struct inode *inode = dentry->d_inode;
+	struct task_struct *task;
+	int ret = -EACCES;
+
+	task = get_proc_task(inode);
+	if (!task)
+		return -ESRCH;
+
+	if (!lock_trace(task)) {
+		ret = proc_setattr(dentry, attr);
+		unlock_trace(task);
+	}
+
+	put_task_struct(task);
+	return ret;
+}
+
+static int proc_map_files_getattr(struct vfsmount *mnt, struct dentry *dentry,
+				  struct kstat *stat)
+{
+	struct inode *inode = dentry->d_inode;
+	struct task_struct *task;
+	int ret = -EACCES;
+
+	task = get_proc_task(inode);
+	if (!task)
+		return -ESRCH;
+
+	if (!lock_trace(task)) {
+		generic_fillattr(inode, stat);
+		unlock_trace(task);
+		ret = 0;
+	}
+
+	put_task_struct(task);
+	return ret;
+}
+
+static const struct inode_operations proc_map_files_inode_operations = {
+	.lookup		= proc_map_files_lookup,
+	.setattr	= proc_map_files_setattr,
+	.getattr	= proc_map_files_getattr,
+};
+
+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 = -ENOENT;
+	task = get_proc_task(inode);
+	if (!task)
+		goto out_no_task;
+
+	ret = -EPERM;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ))
+		goto out;
+
+	ret = 0;
+	switch (filp->f_pos) {
+	case 0:
+		ino = inode->i_ino;
+		if (filldir(dirent, ".", 1, 0, 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:
+	{
+		struct map_files_info *info = NULL;
+		unsigned long nr_files, used, pos, i;
+		unsigned long mem_size = 0;
+
+		mm = get_task_mm(task);
+		if (!mm)
+			goto out;
+		down_read(&mm->mmap_sem);
+
+		nr_files = 0;
+		used = 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; vma; vma = vma->vm_next) {
+			if (vma->vm_file)
+				nr_files++;
+		}
+
+		if (nr_files) {
+			mem_size = nr_files * sizeof(*info);
+			if (mem_size <= KMALLOC_MAX_SIZE)
+				info = kmalloc(mem_size, GFP_KERNEL);
+			else
+				info = vmalloc(mem_size);
+			if (!info)
+				ret = -ENOMEM;
+			for (vma = mm->mmap, pos = 2; vma && info; vma = vma->vm_next) {
+				if (!vma->vm_file)
+					continue;
+				if (++pos <= filp->f_pos)
+					continue;
+
+				get_file(vma->vm_file);
+				info[used].file	= vma->vm_file;
+				info[used].len	= snprintf(info[used].name,
+							   sizeof(info[used].name),
+							   "%lx-%lx",
+							   vma->vm_start,
+							   vma->vm_end);
+				used++;
+			}
+		}
+
+		up_read(&mm->mmap_sem);
+
+		for (i = 0; i < used; i++) {
+			ret = proc_fill_cache(filp, dirent, filldir,
+					      info[i].name, info[i].len,
+					      proc_map_files_instantiate,
+					      task, info[i].file);
+			if (ret)
+				break;
+			filp->f_pos++;
+			put_filp(info[i].file);
+		}
+
+		for (; i < used; i++)
+			put_filp(info[i].file);
+
+		if (mem_size <= KMALLOC_MAX_SIZE)
+			kfree(info);
+		else
+			vfree(info);
+		mmput(mm);
+	}
+	}
+
+out:
+	put_task_struct(task);
+out_no_task:
+	return ret;
+}
+
+static const struct file_operations proc_map_files_operations = {
+	.read		= generic_read_dir,
+	.readdir	= proc_map_files_readdir,
+	.llseek		= default_llseek,
+};
+
+/*
  * /proc/pid/fd needs a special permission handler so that a process can still
  * access /proc/self/fd after it has executed a setuid().
  */
@@ -2785,6 +3137,7 @@ static const struct inode_operations pro
 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),
+	DIR("map_files",  S_IRUSR|S_IXUSR, proc_map_files_inode_operations, proc_map_files_operations),
 	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
Index: linux-2.6.git/include/linux/mm.h
===================================================================
--- linux-2.6.git.orig/include/linux/mm.h
+++ linux-2.6.git/include/linux/mm.h
@@ -1491,6 +1491,18 @@ static inline unsigned long vma_pages(st
 	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