[patch 3/7] procfs: Add ability to plug in auxiliary fdinfo providers

[Cyrill Gorcunov <gorcunov@openvz.org>]

[-- Attachment #1: seq-fdinfo-seq-ops-helpers-6 --]
[-- Type: text/plain, Size: 7841 bytes --]

This patch brings ability to plug in auxiliary fdinfo providers.
For example in further patches eventfd, evenpoll and fsnotify
will print out information associated with files.

This feature is CONFIG_CHECKPOINT_RESTORE guarded to eliminate
overhead for those who don't need it at all (this
unfortunately makes patch bigger than I wanted).

The basic usage rule is the following

 - fdinfo provider should register own "show" method
   via proc_register_fdinfo_driver call, where "show"
   methods are rather well known seq-file operations

 - once the kernel opens /proc/$pid/fdinfo/$fd file
   it calls for ->probe() method in registered fdinfo
   drivers, and if probe success, then seq-file "show"
   operations will be called to provide out additional
   infomation

Initially we considered to inject some "show" metod to
file_operations but since there really a number of
file_operations declared inside kernel (and in real the
further patches cover onle eventfd/epoll/inotify) the
waste of memory space will be inacceptable I think.

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
CC: Al Viro <viro@ZenIV.linux.org.uk>
CC: Alexey Dobriyan <adobriyan@gmail.com>
CC: Andrew Morton <akpm@linux-foundation.org>
CC: Pavel Emelyanov <xemul@parallels.com>
CC: James Bottomley <jbottomley@parallels.com>
---
 fs/proc/fd.c            |  200 ++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/proc_fs.h |   26 ++++++
 2 files changed, 226 insertions(+)

Index: linux-2.6.git/fs/proc/fd.c
===================================================================
--- linux-2.6.git.orig/fs/proc/fd.c
+++ linux-2.6.git/fs/proc/fd.c
@@ -8,12 +8,210 @@
 #include <linux/security.h>
 #include <linux/file.h>
 #include <linux/seq_file.h>
+#include <linux/spinlock.h>
 
 #include <linux/proc_fs.h>
 
 #include "internal.h"
 #include "fd.h"
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+
+static LIST_HEAD(fdinfo_drivers);
+static DECLARE_RWSEM(fdinfo_drivers_sem);
+
+int proc_register_fdinfo_driver(struct proc_fdinfo_driver *s)
+{
+	struct proc_fdinfo_driver *i;
+	int ret = 0;
+
+	if (!s->ops || !s->probe)
+		return -EINVAL;
+
+	down_write(&fdinfo_drivers_sem);
+	list_for_each_entry(i, &fdinfo_drivers, list) {
+		if (i == s) {
+			WARN_ONCE("Trying reassign fdinfo driver `%s'\n",
+				  i->name);
+			ret = -EINVAL;
+			break;
+		}
+	}
+	if (!ret)
+		list_add(&s->list, &fdinfo_drivers);
+	up_write(&fdinfo_drivers_sem);
+
+	return ret;
+}
+
+void proc_unregister_fdinfo_driver(struct proc_fdinfo_driver *s)
+{
+	struct proc_fdinfo_driver *i, *tmp;
+
+	down_write(&fdinfo_drivers_sem);
+	list_for_each_entry_safe(i, tmp, &fdinfo_drivers, list) {
+		if (i == s) {
+			list_del(&i->list);
+			break;
+		}
+	}
+	up_write(&fdinfo_drivers_sem);
+}
+
+static int prep_fdinfo_driver(struct proc_fdinfo_extra *extra)
+{
+	struct proc_fdinfo_driver *s;
+
+	down_read(&fdinfo_drivers_sem);
+	list_for_each_entry(s, &fdinfo_drivers, list) {
+		if (s->probe(extra->f_file)) {
+			extra->driver = s;
+			break;
+		}
+	}
+	up_read(&fdinfo_drivers_sem);
+
+	return 0;
+}
+
+static void *seq_start(struct seq_file *m, loff_t *pos)
+{
+	struct proc_fdinfo_extra *extra = m->private;
+
+	down_read(&fdinfo_drivers_sem);
+	extra->pos = *pos;
+
+	return *pos == 0 ? extra :
+		(extra->driver ? extra->driver->ops->start(m, pos) : NULL);
+}
+
+static void seq_stop(struct seq_file *m, void *v)
+{
+	struct proc_fdinfo_extra *extra = m->private;
+
+	if (extra->driver && extra->pos > 0)
+		extra->driver->ops->stop(m, v);
+	up_read(&fdinfo_drivers_sem);
+}
+
+static void *seq_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	struct proc_fdinfo_extra *extra = m->private;
+	void *v = NULL;
+
+	if (extra->driver) {
+		int ret = 0;
+
+		if (*pos == 0) {
+			v = extra->driver->ops->start(m, pos);
+			if (v) {
+				ret = extra->driver->ops->show(m, v);
+				p = v;
+			} else
+				ret = -1;
+		}
+
+		if (!ret)
+			v = extra->driver->ops->next(m, p, pos);
+	} else
+		++*pos;
+
+	extra->pos = *pos;
+	return v;
+}
+
+static int seq_show(struct seq_file *m, void *v)
+{
+	struct proc_fdinfo_extra *extra = m->private;
+
+	if (extra->driver && extra->pos > 0)
+		return extra->driver->ops->show(m, v);
+
+	seq_printf(m, "pos:\t%lli\nflags:\t0%o\n",
+		   (long long)extra->f_file->f_pos,
+		   extra->f_flags);
+	return 0;
+}
+
+static const struct seq_operations fdinfo_seq_ops = {
+	.start	= seq_start,
+	.next	= seq_next,
+	.stop	= seq_stop,
+	.show	= seq_show,
+};
+
+static int seq_fdinfo_open(struct inode *inode, struct file *file)
+{
+	struct files_struct *files = NULL;
+	struct proc_fdinfo_extra *extra;
+	struct task_struct *task;
+	struct seq_file *m;
+	int ret;
+
+	extra = kzalloc(sizeof(*extra), GFP_KERNEL);
+	if (!extra)
+		return -ENOMEM;
+
+	ret = seq_open(file, &fdinfo_seq_ops);
+	if (!ret) {
+		ret = -ENOENT;
+		m = file->private_data;
+		m->private = extra;
+
+		task = get_proc_task(inode);
+		if (task) {
+			files = get_files_struct(task);
+			put_task_struct(task);
+		}
+
+		if (files) {
+			int fd = proc_fd(inode);
+
+			spin_lock(&files->file_lock);
+			extra->f_file = fcheck_files(files, fd);
+			if (extra->f_file) {
+				struct fdtable *fdt = files_fdtable(files);
+
+				extra->f_flags = extra->f_file->f_flags & ~O_CLOEXEC;
+				if (close_on_exec(fd, fdt))
+					extra->f_flags |= O_CLOEXEC;
+				get_file(extra->f_file);
+			}
+			spin_unlock(&files->file_lock);
+			put_files_struct(files);
+
+			ret = prep_fdinfo_driver(extra);
+		}
+	}
+
+	if (ret) {
+		if (extra->f_file)
+			put_filp(extra->f_file);
+		kfree(extra);
+	}
+	return ret;
+}
+
+static int seq_fdinfo_release(struct inode *inode, struct file *file)
+{
+	struct seq_file *m = file->private_data;
+	struct proc_fdinfo_extra *extra = m->private;
+
+	put_filp(extra->f_file);
+	kfree(m->private);
+
+	return seq_release(inode, file);
+}
+
+static const struct file_operations proc_fdinfo_file_operations = {
+	.open		= seq_fdinfo_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_fdinfo_release,
+};
+
+#else /* CONFIG_CHECKPOINT_RESTORE */
+
 struct proc_fdinfo {
 	loff_t	f_pos;
 	int	f_flags;
@@ -90,6 +288,8 @@ static const struct file_operations proc
 	.release	= seq_fdinfo_release,
 };
 
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+
 static int tid_fd_revalidate(struct dentry *dentry, struct nameidata *nd)
 {
 	struct files_struct *files;
Index: linux-2.6.git/include/linux/proc_fs.h
===================================================================
--- linux-2.6.git.orig/include/linux/proc_fs.h
+++ linux-2.6.git/include/linux/proc_fs.h
@@ -100,6 +100,24 @@ struct vmcore {
 	loff_t offset;
 };
 
+struct seq_operations;
+
+/* fdinfo auxiliary information drivers */
+struct proc_fdinfo_driver {
+	struct list_head		list;
+	const char			*name;
+	const struct seq_operations	*ops;
+	int				(*probe)(struct file *file);
+};
+
+/* auxiliary data allocated per fdinfo reader */
+struct proc_fdinfo_extra {
+	struct proc_fdinfo_driver	*driver;
+	loff_t				pos;
+	struct file			*f_file;
+	unsigned int			f_flags;
+};
+
 #ifdef CONFIG_PROC_FS
 
 extern void proc_root_init(void);
@@ -175,6 +193,11 @@ extern struct proc_dir_entry *proc_net_m
 
 extern struct file *proc_ns_fget(int fd);
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+extern int proc_register_fdinfo_driver(struct proc_fdinfo_driver *s);
+extern void proc_unregister_fdinfo_driver(struct proc_fdinfo_driver *s);
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+
 #else
 
 #define proc_net_fops_create(net, name, mode, fops)  ({ (void)(mode), NULL; })
@@ -229,6 +252,9 @@ static inline struct file *proc_ns_fget(
 	return ERR_PTR(-EINVAL);
 }
 
+static inline int proc_register_fdinfo_driver(struct proc_fdinfo_driver *s) { return -EINVAL; }
+static inline void proc_unregister_fdinfo_driver(struct proc_fdinfo_driver *s) { }
+
 #endif /* CONFIG_PROC_FS */
 
 #if !defined(CONFIG_PROC_KCORE)