Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull vfs update from Al Viro:

 - big one - consolidation of descriptor-related logics; almost all of
   that is moved to fs/file.c

   (BTW, I'm seriously tempted to rename the result to fd.c.  As it is,
   we have a situation when file_table.c is about handling of struct
   file and file.c is about handling of descriptor tables; the reasons
   are historical - file_table.c used to be about a static array of
   struct file we used to have way back).

   A lot of stray ends got cleaned up and converted to saner primitives,
   disgusting mess in android/binder.c is still disgusting, but at least
   doesn't poke so much in descriptor table guts anymore.  A bunch of
   relatively minor races got fixed in process, plus an ext4 struct file
   leak.

 - related thing - fget_light() partially unuglified; see fdget() in
   there (and yes, it generates the code as good as we used to have).

 - also related - bits of Cyrill's procfs stuff that got entangled into
   that work; _not_ all of it, just the initial move to fs/proc/fd.c and
   switch of fdinfo to seq_file.

 - Alex's fs/coredump.c spiltoff - the same story, had been easier to
   take that commit than mess with conflicts.  The rest is a separate
   pile, this was just a mechanical code movement.

 - a few misc patches all over the place.  Not all for this cycle,
   there'll be more (and quite a few currently sit in akpm's tree)."

Fix up trivial conflicts in the android binder driver, and some fairly
simple conflicts due to two different changes to the sock_alloc_file()
interface ("take descriptor handling from sock_alloc_file() to callers"
vs "net: Providing protocol type via system.sockprotoname xattr of
/proc/PID/fd entries" adding a dentry name to the socket)

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (72 commits)
  MAX_LFS_FILESIZE should be a loff_t
  compat: fs: Generic compat_sys_sendfile implementation
  fs: push rcu_barrier() from deactivate_locked_super() to filesystems
  btrfs: reada_extent doesn't need kref for refcount
  coredump: move core dump functionality into its own file
  coredump: prevent double-free on an error path in core dumper
  usb/gadget: fix misannotations
  fcntl: fix misannotations
  ceph: don't abuse d_delete() on failure exits
  hypfs: ->d_parent is never NULL or negative
  vfs: delete surplus inode NULL check
  switch simple cases of fget_light to fdget
  new helpers: fdget()/fdput()
  switch o2hb_region_dev_write() to fget_light()
  proc_map_files_readdir(): don't bother with grabbing files
  make get_file() return its argument
  vhost_set_vring(): turn pollstart/pollstop into bool
  switch prctl_set_mm_exe_file() to fget_light()
  switch xfs_find_handle() to fget_light()
  switch xfs_swapext() to fget_light()
  ...
This commit is contained in:
Linus Torvalds
2012-10-02 20:25:04 -07:00
142 changed files with 2914 additions and 2876 deletions

View File

@@ -90,6 +90,7 @@
#endif
#include <trace/events/oom.h>
#include "internal.h"
#include "fd.h"
/* NOTE:
* Implementing inode permission operations in /proc is almost
@@ -136,8 +137,6 @@ 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.
@@ -1500,7 +1499,7 @@ out:
return error;
}
static const struct inode_operations proc_pid_link_inode_operations = {
const struct inode_operations proc_pid_link_inode_operations = {
.readlink = proc_pid_readlink,
.follow_link = proc_pid_follow_link,
.setattr = proc_setattr,
@@ -1509,21 +1508,6 @@ static const struct inode_operations proc_pid_link_inode_operations = {
/* building an inode */
static int task_dumpable(struct task_struct *task)
{
int dumpable = 0;
struct mm_struct *mm;
task_lock(task);
mm = task->mm;
if (mm)
dumpable = get_dumpable(mm);
task_unlock(task);
if(dumpable == 1)
return 1;
return 0;
}
struct inode *proc_pid_make_inode(struct super_block * sb, struct task_struct *task)
{
struct inode * inode;
@@ -1649,15 +1633,6 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags)
return 0;
}
static int pid_delete_dentry(const struct dentry * dentry)
{
/* Is the task we represent dead?
* If so, then don't put the dentry on the lru list,
* kill it immediately.
*/
return !proc_pid(dentry->d_inode)->tasks[PIDTYPE_PID].first;
}
const struct dentry_operations pid_dentry_operations =
{
.d_revalidate = pid_revalidate,
@@ -1720,289 +1695,6 @@ end_instantiate:
return filldir(dirent, name, len, filp->f_pos, ino, type);
}
static unsigned name_to_int(struct dentry *dentry)
{
const char *name = dentry->d_name.name;
int len = dentry->d_name.len;
unsigned n = 0;
if (len > 1 && *name == '0')
goto out;
while (len-- > 0) {
unsigned c = *name++ - '0';
if (c > 9)
goto out;
if (n >= (~0U-9)/10)
goto out;
n *= 10;
n += c;
}
return n;
out:
return ~0U;
}
#define PROC_FDINFO_MAX 64
static int proc_fd_info(struct inode *inode, struct path *path, char *info)
{
struct task_struct *task = get_proc_task(inode);
struct files_struct *files = NULL;
struct file *file;
int fd = proc_fd(inode);
if (task) {
files = get_files_struct(task);
put_task_struct(task);
}
if (files) {
/*
* We are not taking a ref to the file structure, so we must
* hold ->file_lock.
*/
spin_lock(&files->file_lock);
file = fcheck_files(files, fd);
if (file) {
unsigned int f_flags;
struct fdtable *fdt;
fdt = files_fdtable(files);
f_flags = file->f_flags & ~O_CLOEXEC;
if (close_on_exec(fd, fdt))
f_flags |= O_CLOEXEC;
if (path) {
*path = file->f_path;
path_get(&file->f_path);
}
if (info)
snprintf(info, PROC_FDINFO_MAX,
"pos:\t%lli\n"
"flags:\t0%o\n",
(long long) file->f_pos,
f_flags);
spin_unlock(&files->file_lock);
put_files_struct(files);
return 0;
}
spin_unlock(&files->file_lock);
put_files_struct(files);
}
return -ENOENT;
}
static int proc_fd_link(struct dentry *dentry, struct path *path)
{
return proc_fd_info(dentry->d_inode, path, NULL);
}
static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct task_struct *task;
int fd;
struct files_struct *files;
const struct cred *cred;
if (flags & LOOKUP_RCU)
return -ECHILD;
inode = dentry->d_inode;
task = get_proc_task(inode);
fd = proc_fd(inode);
if (task) {
files = get_files_struct(task);
if (files) {
struct file *file;
rcu_read_lock();
file = fcheck_files(files, fd);
if (file) {
unsigned f_mode = file->f_mode;
rcu_read_unlock();
put_files_struct(files);
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 = GLOBAL_ROOT_UID;
inode->i_gid = GLOBAL_ROOT_GID;
}
if (S_ISLNK(inode->i_mode)) {
unsigned i_mode = S_IFLNK;
if (f_mode & FMODE_READ)
i_mode |= S_IRUSR | S_IXUSR;
if (f_mode & FMODE_WRITE)
i_mode |= S_IWUSR | S_IXUSR;
inode->i_mode = i_mode;
}
security_task_to_inode(task, inode);
put_task_struct(task);
return 1;
}
rcu_read_unlock();
put_files_struct(files);
}
put_task_struct(task);
}
d_drop(dentry);
return 0;
}
static const struct dentry_operations tid_fd_dentry_operations =
{
.d_revalidate = tid_fd_revalidate,
.d_delete = pid_delete_dentry,
};
static struct dentry *proc_fd_instantiate(struct inode *dir,
struct dentry *dentry, struct task_struct *task, const void *ptr)
{
unsigned fd = (unsigned long)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)
goto out;
ei = PROC_I(inode);
ei->fd = fd;
inode->i_mode = S_IFLNK;
inode->i_op = &proc_pid_link_inode_operations;
inode->i_size = 64;
ei->op.proc_get_link = proc_fd_link;
d_set_d_op(dentry, &tid_fd_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
if (tid_fd_revalidate(dentry, 0))
error = NULL;
out:
return error;
}
static struct dentry *proc_lookupfd_common(struct inode *dir,
struct dentry *dentry,
instantiate_t instantiate)
{
struct task_struct *task = get_proc_task(dir);
unsigned fd = name_to_int(dentry);
struct dentry *result = ERR_PTR(-ENOENT);
if (!task)
goto out_no_task;
if (fd == ~0U)
goto out;
result = instantiate(dir, dentry, task, (void *)(unsigned long)fd);
out:
put_task_struct(task);
out_no_task:
return result;
}
static int proc_readfd_common(struct file * filp, void * dirent,
filldir_t filldir, instantiate_t instantiate)
{
struct dentry *dentry = filp->f_path.dentry;
struct inode *inode = dentry->d_inode;
struct task_struct *p = get_proc_task(inode);
unsigned int fd, ino;
int retval;
struct files_struct * files;
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();
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);
}
out:
put_task_struct(p);
out_no_task:
return retval;
}
static struct dentry *proc_lookupfd(struct inode *dir, struct dentry *dentry,
unsigned int flags)
{
return proc_lookupfd_common(dir, dentry, proc_fd_instantiate);
}
static int proc_readfd(struct file *filp, void *dirent, filldir_t filldir)
{
return proc_readfd_common(filp, dirent, filldir, proc_fd_instantiate);
}
static ssize_t proc_fdinfo_read(struct file *file, char __user *buf,
size_t len, loff_t *ppos)
{
char tmp[PROC_FDINFO_MAX];
int err = proc_fd_info(file->f_path.dentry->d_inode, NULL, tmp);
if (!err)
err = simple_read_from_buffer(buf, len, ppos, tmp, strlen(tmp));
return err;
}
static const struct file_operations proc_fdinfo_file_operations = {
.open = nonseekable_open,
.read = proc_fdinfo_read,
.llseek = no_llseek,
};
static const struct file_operations proc_fd_operations = {
.read = generic_read_dir,
.readdir = proc_readfd,
.llseek = default_llseek,
};
#ifdef CONFIG_CHECKPOINT_RESTORE
/*
@@ -2121,7 +1813,7 @@ out:
}
struct map_files_info {
struct file *file;
fmode_t mode;
unsigned long len;
unsigned char name[4*sizeof(long)+2]; /* max: %lx-%lx\0 */
};
@@ -2130,13 +1822,10 @@ 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;
fmode_t mode = (fmode_t)(unsigned long)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);
@@ -2148,9 +1837,9 @@ proc_map_files_instantiate(struct inode *dir, struct dentry *dentry,
inode->i_size = 64;
inode->i_mode = S_IFLNK;
if (file->f_mode & FMODE_READ)
if (mode & FMODE_READ)
inode->i_mode |= S_IRUSR;
if (file->f_mode & FMODE_WRITE)
if (mode & FMODE_WRITE)
inode->i_mode |= S_IWUSR;
d_set_d_op(dentry, &tid_map_files_dentry_operations);
@@ -2194,7 +1883,8 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
if (!vma)
goto out_no_vma;
result = proc_map_files_instantiate(dir, dentry, task, vma->vm_file);
result = proc_map_files_instantiate(dir, dentry, task,
(void *)(unsigned long)vma->vm_file->f_mode);
out_no_vma:
up_read(&mm->mmap_sem);
@@ -2295,8 +1985,7 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir)
if (++pos <= filp->f_pos)
continue;
get_file(vma->vm_file);
info.file = vma->vm_file;
info.mode = vma->vm_file->f_mode;
info.len = snprintf(info.name,
sizeof(info.name), "%lx-%lx",
vma->vm_start, vma->vm_end);
@@ -2311,19 +2000,11 @@ proc_map_files_readdir(struct file *filp, void *dirent, filldir_t filldir)
ret = proc_fill_cache(filp, dirent, filldir,
p->name, p->len,
proc_map_files_instantiate,
task, p->file);
task,
(void *)(unsigned long)p->mode);
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);
@@ -2345,82 +2026,6 @@ static const struct file_operations proc_map_files_operations = {
#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().
*/
static int proc_fd_permission(struct inode *inode, int mask)
{
int rv = generic_permission(inode, mask);
if (rv == 0)
return 0;
if (task_pid(current) == proc_pid(inode))
rv = 0;
return rv;
}
/*
* proc directories can do almost nothing..
*/
static const struct inode_operations proc_fd_inode_operations = {
.lookup = proc_lookupfd,
.permission = proc_fd_permission,
.setattr = proc_setattr,
};
static struct dentry *proc_fdinfo_instantiate(struct inode *dir,
struct dentry *dentry, struct task_struct *task, const void *ptr)
{
unsigned fd = (unsigned long)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)
goto out;
ei = PROC_I(inode);
ei->fd = fd;
inode->i_mode = S_IFREG | S_IRUSR;
inode->i_fop = &proc_fdinfo_file_operations;
d_set_d_op(dentry, &tid_fd_dentry_operations);
d_add(dentry, inode);
/* Close the race of the process dying before we return the dentry */
if (tid_fd_revalidate(dentry, 0))
error = NULL;
out:
return error;
}
static struct dentry *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)
{
return proc_readfd_common(filp, dirent, filldir,
proc_fdinfo_instantiate);
}
static const struct file_operations proc_fdinfo_operations = {
.read = generic_read_dir,
.readdir = proc_readfdinfo,
.llseek = default_llseek,
};
/*
* proc directories can do almost nothing..
*/
static const struct inode_operations proc_fdinfo_inode_operations = {
.lookup = proc_lookupfdinfo,
.setattr = proc_setattr,
};
static struct dentry *proc_pident_instantiate(struct inode *dir,
struct dentry *dentry, struct task_struct *task, const void *ptr)
{