diff --git a/fs/Kconfig b/fs/Kconfig
index 4bc7dd420874aa979d325d5bc620d4425f0e04db..ea2f77446080ef9f22ed4f4e860b77b2f4ce8167 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -173,13 +173,6 @@ source "fs/proc/Kconfig"
source "fs/kernfs/Kconfig"
source "fs/sysfs/Kconfig"
-config FS_PID
- bool "Pseudo filesystem for process file descriptors"
- depends on 64BIT
- default y
- help
- Pidfs implements advanced features for process file descriptors.
-
config TMPFS
bool "Tmpfs virtual memory file system support (former shm fs)"
depends on SHMEM
diff --git a/fs/internal.h b/fs/internal.h
index 49c1fcfee4b35a8f8f653ad916ec4a4459f1ed34..7ca738904e34a24074c26dd277e2800a40895cf5 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -313,8 +313,8 @@ struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap);
void mnt_idmap_put(struct mnt_idmap *idmap);
struct stashed_operations {
void (*put_data)(void *data);
- void (*init_inode)(struct inode *inode, void *data);
+ int (*init_inode)(struct inode *inode, void *data);
};
-int path_from_stashed(struct dentry **stashed, unsigned long ino,
- struct vfsmount *mnt, void *data, struct path *path);
+int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data,
+ struct path *path);
void stashed_dentry_prune(struct dentry *dentry);
diff --git a/fs/libfs.c b/fs/libfs.c
index 0d14ae808fcfdb314af5b95ccabec10f1dac8c15..3a6f2cb364f8cbcc9fa78d6a0a45519ad6fcd696 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -2001,34 +2001,40 @@ static inline struct dentry *get_stashed_dentry(struct dentry *stashed)
}
static struct dentry *prepare_anon_dentry(struct dentry **stashed,
- unsigned long ino,
struct super_block *sb,
void *data)
{
struct dentry *dentry;
struct inode *inode;
const struct stashed_operations *sops = sb->s_fs_info;
-
- dentry = d_alloc_anon(sb);
- if (!dentry)
- return ERR_PTR(-ENOMEM);
+ int ret;
inode = new_inode_pseudo(sb);
if (!inode) {
- dput(dentry);
+ sops->put_data(data);
return ERR_PTR(-ENOMEM);
}
- inode->i_ino = ino;
inode->i_flags |= S_IMMUTABLE;
inode->i_mode = S_IFREG;
simple_inode_init_ts(inode);
- sops->init_inode(inode, data);
+
+ ret = sops->init_inode(inode, data);
+ if (ret < 0) {
+ iput(inode);
+ return ERR_PTR(ret);
+ }
/* Notice when this is changed. */
WARN_ON_ONCE(!S_ISREG(inode->i_mode));
WARN_ON_ONCE(!IS_IMMUTABLE(inode));
+ dentry = d_alloc_anon(sb);
+ if (!dentry) {
+ iput(inode);
+ return ERR_PTR(-ENOMEM);
+ }
+
/* Store address of location where dentry's supposed to be stashed. */
dentry->d_fsdata = stashed;
@@ -2062,7 +2068,6 @@ static struct dentry *stash_dentry(struct dentry **stashed,
/**
* path_from_stashed - create path from stashed or new dentry
* @stashed: where to retrieve or stash dentry
- * @ino: inode number to use
* @mnt: mnt of the filesystems to use
* @data: data to store in inode->i_private
* @path: path to create
@@ -2077,8 +2082,8 @@ static struct dentry *stash_dentry(struct dentry **stashed,
*
* Return: On success zero and on failure a negative error is returned.
*/
-int path_from_stashed(struct dentry **stashed, unsigned long ino,
- struct vfsmount *mnt, void *data, struct path *path)
+int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data,
+ struct path *path)
{
struct dentry *dentry;
const struct stashed_operations *sops = mnt->mnt_sb->s_fs_info;
@@ -2091,11 +2096,9 @@ int path_from_stashed(struct dentry **stashed, unsigned long ino,
}
/* Allocate a new dentry. */
- dentry = prepare_anon_dentry(stashed, ino, mnt->mnt_sb, data);
- if (IS_ERR(dentry)) {
- sops->put_data(data);
+ dentry = prepare_anon_dentry(stashed, mnt->mnt_sb, data);
+ if (IS_ERR(dentry))
return PTR_ERR(dentry);
- }
/* Added a new dentry. @data is now owned by the filesystem. */
path->dentry = stash_dentry(stashed, dentry);
diff --git a/fs/nsfs.c b/fs/nsfs.c
index 7aaafb5cb9fc9f7792c7d7198b49f561ee14be0b..07e22a15ef02bb606e355765de0ff024131b2ef5 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -56,7 +56,7 @@ int ns_get_path_cb(struct path *path, ns_get_path_helper_t *ns_get_cb,
if (!ns)
return -ENOENT;
- return path_from_stashed(&ns->stashed, ns->inum, nsfs_mnt, ns, path);
+ return path_from_stashed(&ns->stashed, nsfs_mnt, ns, path);
}
struct ns_get_path_task_args {
@@ -101,8 +101,7 @@ int open_related_ns(struct ns_common *ns,
return PTR_ERR(relative);
}
- err = path_from_stashed(&relative->stashed, relative->inum, nsfs_mnt,
- relative, &path);
+ err = path_from_stashed(&relative->stashed, nsfs_mnt, relative, &path);
if (err < 0) {
put_unused_fd(fd);
return err;
@@ -199,11 +198,15 @@ static const struct super_operations nsfs_ops = {
.show_path = nsfs_show_path,
};
-static void nsfs_init_inode(struct inode *inode, void *data)
+static int nsfs_init_inode(struct inode *inode, void *data)
{
+ struct ns_common *ns = data;
+
inode->i_private = data;
inode->i_mode |= S_IRUGO;
inode->i_fop = &ns_file_operations;
+ inode->i_ino = ns->inum;
+ return 0;
}
static void nsfs_put_data(void *data)
diff --git a/fs/pidfs.c b/fs/pidfs.c
index 8fd71a00be9c0cbfca51b2e717db2293710e6ac4..a63d5d24aa02687586a05c358828a58b24d7c622 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -16,17 +16,6 @@
#include "internal.h"
-static int pidfd_release(struct inode *inode, struct file *file)
-{
-#ifndef CONFIG_FS_PID
- struct pid *pid = file->private_data;
-
- file->private_data = NULL;
- put_pid(pid);
-#endif
- return 0;
-}
-
#ifdef CONFIG_PROC_FS
/**
* pidfd_show_fdinfo - print information about a pidfd
@@ -120,7 +109,6 @@ static __poll_t pidfd_poll(struct file *file, struct poll_table_struct *pts)
}
static const struct file_operations pidfs_file_operations = {
- .release = pidfd_release,
.poll = pidfd_poll,
#ifdef CONFIG_PROC_FS
.show_fdinfo = pidfd_show_fdinfo,
@@ -131,16 +119,45 @@ struct pid *pidfd_pid(const struct file *file)
{
if (file->f_op != &pidfs_file_operations)
return ERR_PTR(-EBADF);
-#ifdef CONFIG_FS_PID
return file_inode(file)->i_private;
-#else
- return file->private_data;
-#endif
}
-#ifdef CONFIG_FS_PID
static struct vfsmount *pidfs_mnt __ro_after_init;
+#if BITS_PER_LONG == 32
+/*
+ * Provide a fallback mechanism for 32-bit systems so processes remain
+ * reliably comparable by inode number even on those systems.
+ */
+static DEFINE_IDA(pidfd_inum_ida);
+
+static int pidfs_inum(struct pid *pid, unsigned long *ino)
+{
+ int ret;
+
+ ret = ida_alloc_range(&pidfd_inum_ida, RESERVED_PIDS + 1,
+ UINT_MAX, GFP_ATOMIC);
+ if (ret < 0)
+ return -ENOSPC;
+
+ *ino = ret;
+ return 0;
+}
+
+static inline void pidfs_free_inum(unsigned long ino)
+{
+ if (ino > 0)
+ ida_free(&pidfd_inum_ida, ino);
+}
+#else
+static inline int pidfs_inum(struct pid *pid, unsigned long *ino)
+{
+ *ino = pid->ino;
+ return 0;
+}
+#define pidfs_free_inum(ino) ((void)(ino))
+#endif
+
/*
* The vfs falls back to simple_setattr() if i_op->setattr() isn't
* implemented. Let's reject it completely until we have a clean
@@ -173,6 +190,7 @@ static void pidfs_evict_inode(struct inode *inode)
clear_inode(inode);
put_pid(pid);
+ pidfs_free_inum(inode->i_ino);
}
static const struct super_operations pidfs_sops = {
@@ -183,8 +201,10 @@ static const struct super_operations pidfs_sops = {
static char *pidfs_dname(struct dentry *dentry, char *buffer, int buflen)
{
- return dynamic_dname(buffer, buflen, "pidfd:[%lu]",
- d_inode(dentry)->i_ino);
+ struct inode *inode = d_inode(dentry);
+ struct pid *pid = inode->i_private;
+
+ return dynamic_dname(buffer, buflen, "pidfd:[%llu]", pid->ino);
}
static const struct dentry_operations pidfs_dentry_operations = {
@@ -193,13 +213,19 @@ static const struct dentry_operations pidfs_dentry_operations = {
.d_prune = stashed_dentry_prune,
};
-static void pidfs_init_inode(struct inode *inode, void *data)
+static int pidfs_init_inode(struct inode *inode, void *data)
{
inode->i_private = data;
inode->i_flags |= S_PRIVATE;
inode->i_mode |= S_IRWXU;
inode->i_op = &pidfs_inode_operations;
inode->i_fop = &pidfs_file_operations;
+ /*
+ * Inode numbering for pidfs start at RESERVED_PIDS + 1. This
+ * avoids collisions with the root inode which is 1 for pseudo
+ * filesystems.
+ */
+ return pidfs_inum(data, &inode->i_ino);
}
static void pidfs_put_data(void *data)
@@ -240,13 +266,7 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags)
struct path path;
int ret;
- /*
- * Inode numbering for pidfs start at RESERVED_PIDS + 1.
- * This avoids collisions with the root inode which is 1
- * for pseudo filesystems.
- */
- ret = path_from_stashed(&pid->stashed, pid->ino, pidfs_mnt,
- get_pid(pid), &path);
+ ret = path_from_stashed(&pid->stashed, pidfs_mnt, get_pid(pid), &path);
if (ret < 0)
return ERR_PTR(ret);
@@ -261,30 +281,3 @@ void __init pidfs_init(void)
if (IS_ERR(pidfs_mnt))
panic("Failed to mount pidfs pseudo filesystem");
}
-
-bool is_pidfs_sb(const struct super_block *sb)
-{
- return sb == pidfs_mnt->mnt_sb;
-}
-
-#else /* !CONFIG_FS_PID */
-
-struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags)
-{
- struct file *pidfd_file;
-
- pidfd_file = anon_inode_getfile("[pidfd]", &pidfs_file_operations, pid,
- flags | O_RDWR);
- if (IS_ERR(pidfd_file))
- return pidfd_file;
-
- get_pid(pid);
- return pidfd_file;
-}
-
-void __init pidfs_init(void) { }
-bool is_pidfs_sb(const struct super_block *sb)
-{
- return false;
-}
-#endif
diff --git a/include/linux/pid.h b/include/linux/pid.h
index c79a0efd02586b1b9147895272c0d0fd46c354f1..a3aad9b4074cb09b12ec1cb98c8148250c506e0a 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -45,6 +45,8 @@
* find_pid_ns() using the int nr and struct pid_namespace *ns.
*/
+#define RESERVED_PIDS 300
+
struct upid {
int nr;
struct pid_namespace *ns;
@@ -55,10 +57,8 @@ struct pid
refcount_t count;
unsigned int level;
spinlock_t lock;
-#ifdef CONFIG_FS_PID
struct dentry *stashed;
- unsigned long ino;
-#endif
+ u64 ino;
/* lists of tasks that use this pid */
struct hlist_head tasks[PIDTYPE_MAX];
struct hlist_head inodes;
diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h
index 40dd325a32a634153778bebdd818f7028aa8e4df..75bdf9807802a5d1a9699c99aa42648c2bd34170 100644
--- a/include/linux/pidfs.h
+++ b/include/linux/pidfs.h
@@ -4,6 +4,5 @@
struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags);
void __init pidfs_init(void);
-bool is_pidfs_sb(const struct super_block *sb);
#endif /* _LINUX_PID_FS_H */
diff --git a/kernel/pid.c b/kernel/pid.c
index 99a0c5eb24b8d61df9b4fa2d171ddf71b54f3a92..da76ed1873f7070b85ff129d28f7eb2ab19d3d2e 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -62,17 +62,13 @@ struct pid init_struct_pid = {
int pid_max = PID_MAX_DEFAULT;
-#define RESERVED_PIDS 300
-
int pid_max_min = RESERVED_PIDS + 1;
int pid_max_max = PID_MAX_LIMIT;
-#ifdef CONFIG_FS_PID
/*
* Pseudo filesystems start inode numbering after one. We use Reserved
* PIDs as a natural offset.
*/
static u64 pidfs_ino = RESERVED_PIDS;
-#endif
/*
* PID-map pages start out as NULL, they get allocated upon
@@ -280,10 +276,8 @@ struct pid *alloc_pid(struct pid_namespace *ns, pid_t *set_tid,
spin_lock_irq(&pidmap_lock);
if (!(ns->pid_allocated & PIDNS_ADDING))
goto out_unlock;
-#ifdef CONFIG_FS_PID
pid->stashed = NULL;
pid->ino = ++pidfs_ino;
-#endif
for ( ; upid >= pid->numbers; --upid) {
/* Make the PID visible to find_pid_ns. */
idr_replace(&upid->ns->idr, pid, upid->nr);