1 files changed, 319 insertions, 106 deletions

diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 6da18316d209..f495fdb39151 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -24,8 +24,7 @@
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/mount.h>
-
-#include <linux/uaccess.h>
+#include <linux/bug.h>
 
 #include "internal.h"
 
@@ -33,21 +32,27 @@ static void proc_evict_inode(struct inode *inode)
 {
 	struct proc_dir_entry *de;
 	struct ctl_table_header *head;
+	struct proc_inode *ei = PROC_I(inode);
 
 	truncate_inode_pages_final(&inode->i_data);
 	clear_inode(inode);
 
 	/* Stop tracking associated processes */
-	put_pid(PROC_I(inode)->pid);
+	if (ei->pid) {
+		proc_pid_evict_inode(ei);
+		ei->pid = NULL;
+	}
 
 	/* Let go of any associated proc directory entry */
-	de = PDE(inode);
-	if (de)
+	de = ei->pde;
+	if (de) {
 		pde_put(de);
+		ei->pde = NULL;
+	}
 
-	head = PROC_I(inode)->sysctl;
+	head = ei->sysctl;
 	if (head) {
-		RCU_INIT_POINTER(PROC_I(inode)->sysctl, NULL);
+		RCU_INIT_POINTER(ei->sysctl, NULL);
 		proc_sys_evict_inode(inode, head);
 	}
 }
@@ -59,7 +64,7 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
 {
 	struct proc_inode *ei;
 
-	ei = kmem_cache_alloc(proc_inode_cachep, GFP_KERNEL);
+	ei = alloc_inode_sb(sb, proc_inode_cachep, GFP_KERNEL);
 	if (!ei)
 		return NULL;
 	ei->pid = NULL;
@@ -68,6 +73,7 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
 	ei->pde = NULL;
 	ei->sysctl = NULL;
 	ei->sysctl_entry = NULL;
+	INIT_HLIST_NODE(&ei->sibling_inodes);
 	ei->ns_ops = NULL;
 	return &ei->vfs_inode;
 }
@@ -102,15 +108,84 @@ void __init proc_init_kmemcache(void)
 	BUILD_BUG_ON(sizeof(struct proc_dir_entry) >= SIZEOF_PDE);
 }
 
+void proc_invalidate_siblings_dcache(struct hlist_head *inodes, spinlock_t *lock)
+{
+	struct inode *inode;
+	struct proc_inode *ei;
+	struct hlist_node *node;
+	struct super_block *old_sb = NULL;
+
+	rcu_read_lock();
+	for (;;) {
+		struct super_block *sb;
+		node = hlist_first_rcu(inodes);
+		if (!node)
+			break;
+		ei = hlist_entry(node, struct proc_inode, sibling_inodes);
+		spin_lock(lock);
+		hlist_del_init_rcu(&ei->sibling_inodes);
+		spin_unlock(lock);
+
+		inode = &ei->vfs_inode;
+		sb = inode->i_sb;
+		if ((sb != old_sb) && !atomic_inc_not_zero(&sb->s_active))
+			continue;
+		inode = igrab(inode);
+		rcu_read_unlock();
+		if (sb != old_sb) {
+			if (old_sb)
+				deactivate_super(old_sb);
+			old_sb = sb;
+		}
+		if (unlikely(!inode)) {
+			rcu_read_lock();
+			continue;
+		}
+
+		if (S_ISDIR(inode->i_mode)) {
+			struct dentry *dir = d_find_any_alias(inode);
+			if (dir) {
+				d_invalidate(dir);
+				dput(dir);
+			}
+		} else {
+			struct dentry *dentry;
+			while ((dentry = d_find_alias(inode))) {
+				d_invalidate(dentry);
+				dput(dentry);
+			}
+		}
+		iput(inode);
+
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+	if (old_sb)
+		deactivate_super(old_sb);
+}
+
+static inline const char *hidepid2str(enum proc_hidepid v)
+{
+	switch (v) {
+		case HIDEPID_OFF: return "off";
+		case HIDEPID_NO_ACCESS: return "noaccess";
+		case HIDEPID_INVISIBLE: return "invisible";
+		case HIDEPID_NOT_PTRACEABLE: return "ptraceable";
+	}
+	WARN_ONCE(1, "bad hide_pid value: %d\n", v);
+	return "unknown";
+}
+
 static int proc_show_options(struct seq_file *seq, struct dentry *root)
 {
-	struct super_block *sb = root->d_sb;
-	struct pid_namespace *pid = sb->s_fs_info;
+	struct proc_fs_info *fs_info = proc_sb_info(root->d_sb);
 
-	if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID))
-		seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid));
-	if (pid->hide_pid != HIDEPID_OFF)
-		seq_printf(seq, ",hidepid=%u", pid->hide_pid);
+	if (!gid_eq(fs_info->pid_gid, GLOBAL_ROOT_GID))
+		seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, fs_info->pid_gid));
+	if (fs_info->hide_pid != HIDEPID_OFF)
+		seq_printf(seq, ",hidepid=%s", hidepid2str(fs_info->hide_pid));
+	if (fs_info->pidonly != PROC_PIDONLY_OFF)
+		seq_printf(seq, ",subset=pid");
 
 	return 0;
 }
@@ -137,8 +212,17 @@ static void unuse_pde(struct proc_dir_entry *pde)
 		complete(pde->pde_unload_completion);
 }
 
-/* pde is locked on entry, unlocked on exit */
+/*
+ * At most 2 contexts can enter this function: the one doing the last
+ * close on the descriptor and whoever is deleting PDE itself.
+ *
+ * First to enter calls ->proc_release hook and signals its completion
+ * to the second one which waits and then does nothing.
+ *
+ * PDE is locked on entry, unlocked on exit.
+ */
 static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
+	__releases(&pde->pde_unload_lock)
 {
 	/*
 	 * close() (proc_reg_release()) can't delete an entry and proceed:
@@ -146,9 +230,6 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
 	 *
 	 * rmmod (remove_proc_entry() et al) can't delete an entry and proceed:
 	 * "struct file" needs to be available at the right moment.
-	 *
-	 * Therefore, first process to enter this function does ->release() and
-	 * signals its completion to the other process which does nothing.
 	 */
 	if (pdeo->closing) {
 		/* somebody else is doing that, just wait */
@@ -162,10 +243,12 @@ static void close_pdeo(struct proc_dir_entry *pde, struct pde_opener *pdeo)
 
 		pdeo->closing = true;
 		spin_unlock(&pde->pde_unload_lock);
+
 		file = pdeo->file;
 		pde->proc_ops->proc_release(file_inode(file), file);
+
 		spin_lock(&pde->pde_unload_lock);
-		/* After ->release. */
+		/* Strictly after ->proc_release, see above. */
 		list_del(&pdeo->lh);
 		c = pdeo->c;
 		spin_unlock(&pde->pde_unload_lock);
@@ -199,131 +282,205 @@ static loff_t proc_reg_llseek(struct file *file, loff_t offset, int whence)
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	loff_t rv = -EINVAL;
-	if (use_pde(pde)) {
-		typeof_member(struct proc_ops, proc_lseek) lseek;
 
-		lseek = pde->proc_ops->proc_lseek;
-		if (!lseek)
-			lseek = default_llseek;
-		rv = lseek(file, offset, whence);
+	if (pde_is_permanent(pde)) {
+		return pde->proc_ops->proc_lseek(file, offset, whence);
+	} else if (use_pde(pde)) {
+		rv = pde->proc_ops->proc_lseek(file, offset, whence);
 		unuse_pde(pde);
 	}
 	return rv;
 }
 
+static ssize_t proc_reg_read_iter(struct kiocb *iocb, struct iov_iter *iter)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(iocb->ki_filp));
+	ssize_t ret;
+
+	if (pde_is_permanent(pde))
+		return pde->proc_ops->proc_read_iter(iocb, iter);
+
+	if (!use_pde(pde))
+		return -EIO;
+	ret = pde->proc_ops->proc_read_iter(iocb, iter);
+	unuse_pde(pde);
+	return ret;
+}
+
+static ssize_t pde_read(struct proc_dir_entry *pde, struct file *file, char __user *buf, size_t count, loff_t *ppos)
+{
+	typeof_member(struct proc_ops, proc_read) read;
+
+	read = pde->proc_ops->proc_read;
+	if (read)
+		return read(file, buf, count, ppos);
+	return -EIO;
+}
+
 static ssize_t proc_reg_read(struct file *file, char __user *buf, size_t count, loff_t *ppos)
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	ssize_t rv = -EIO;
-	if (use_pde(pde)) {
-		typeof_member(struct proc_ops, proc_read) read;
 
-		read = pde->proc_ops->proc_read;
-		if (read)
-			rv = read(file, buf, count, ppos);
+	if (pde_is_permanent(pde)) {
+		return pde_read(pde, file, buf, count, ppos);
+	} else if (use_pde(pde)) {
+		rv = pde_read(pde, file, buf, count, ppos);
 		unuse_pde(pde);
 	}
 	return rv;
 }
 
+static ssize_t pde_write(struct proc_dir_entry *pde, struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+{
+	typeof_member(struct proc_ops, proc_write) write;
+
+	write = pde->proc_ops->proc_write;
+	if (write)
+		return write(file, buf, count, ppos);
+	return -EIO;
+}
+
 static ssize_t proc_reg_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	ssize_t rv = -EIO;
-	if (use_pde(pde)) {
-		typeof_member(struct proc_ops, proc_write) write;
 
-		write = pde->proc_ops->proc_write;
-		if (write)
-			rv = write(file, buf, count, ppos);
+	if (pde_is_permanent(pde)) {
+		return pde_write(pde, file, buf, count, ppos);
+	} else if (use_pde(pde)) {
+		rv = pde_write(pde, file, buf, count, ppos);
 		unuse_pde(pde);
 	}
 	return rv;
 }
 
+static __poll_t pde_poll(struct proc_dir_entry *pde, struct file *file, struct poll_table_struct *pts)
+{
+	typeof_member(struct proc_ops, proc_poll) poll;
+
+	poll = pde->proc_ops->proc_poll;
+	if (poll)
+		return poll(file, pts);
+	return DEFAULT_POLLMASK;
+}
+
 static __poll_t proc_reg_poll(struct file *file, struct poll_table_struct *pts)
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	__poll_t rv = DEFAULT_POLLMASK;
-	if (use_pde(pde)) {
-		typeof_member(struct proc_ops, proc_poll) poll;
 
-		poll = pde->proc_ops->proc_poll;
-		if (poll)
-			rv = poll(file, pts);
+	if (pde_is_permanent(pde)) {
+		return pde_poll(pde, file, pts);
+	} else if (use_pde(pde)) {
+		rv = pde_poll(pde, file, pts);
 		unuse_pde(pde);
 	}
 	return rv;
 }
 
+static long pde_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg)
+{
+	typeof_member(struct proc_ops, proc_ioctl) ioctl;
+
+	ioctl = pde->proc_ops->proc_ioctl;
+	if (ioctl)
+		return ioctl(file, cmd, arg);
+	return -ENOTTY;
+}
+
 static long proc_reg_unlocked_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	long rv = -ENOTTY;
-	if (use_pde(pde)) {
-		typeof_member(struct proc_ops, proc_ioctl) ioctl;
 
-		ioctl = pde->proc_ops->proc_ioctl;
-		if (ioctl)
-			rv = ioctl(file, cmd, arg);
+	if (pde_is_permanent(pde)) {
+		return pde_ioctl(pde, file, cmd, arg);
+	} else if (use_pde(pde)) {
+		rv = pde_ioctl(pde, file, cmd, arg);
 		unuse_pde(pde);
 	}
 	return rv;
 }
 
 #ifdef CONFIG_COMPAT
+static long pde_compat_ioctl(struct proc_dir_entry *pde, struct file *file, unsigned int cmd, unsigned long arg)
+{
+	typeof_member(struct proc_ops, proc_compat_ioctl) compat_ioctl;
+
+	compat_ioctl = pde->proc_ops->proc_compat_ioctl;
+	if (compat_ioctl)
+		return compat_ioctl(file, cmd, arg);
+	return -ENOTTY;
+}
+
 static long proc_reg_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	long rv = -ENOTTY;
-	if (use_pde(pde)) {
-		typeof_member(struct proc_ops, proc_compat_ioctl) compat_ioctl;
-
-		compat_ioctl = pde->proc_ops->proc_compat_ioctl;
-		if (compat_ioctl)
-			rv = compat_ioctl(file, cmd, arg);
+	if (pde_is_permanent(pde)) {
+		return pde_compat_ioctl(pde, file, cmd, arg);
+	} else if (use_pde(pde)) {
+		rv = pde_compat_ioctl(pde, file, cmd, arg);
 		unuse_pde(pde);
 	}
 	return rv;
 }
 #endif
 
+static int pde_mmap(struct proc_dir_entry *pde, struct file *file, struct vm_area_struct *vma)
+{
+	typeof_member(struct proc_ops, proc_mmap) mmap;
+
+	mmap = pde->proc_ops->proc_mmap;
+	if (mmap)
+		return mmap(file, vma);
+	return -EIO;
+}
+
 static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct proc_dir_entry *pde = PDE(file_inode(file));
 	int rv = -EIO;
-	if (use_pde(pde)) {
-		typeof_member(struct proc_ops, proc_mmap) mmap;
 
-		mmap = pde->proc_ops->proc_mmap;
-		if (mmap)
-			rv = mmap(file, vma);
+	if (pde_is_permanent(pde)) {
+		return pde_mmap(pde, file, vma);
+	} else if (use_pde(pde)) {
+		rv = pde_mmap(pde, file, vma);
 		unuse_pde(pde);
 	}
 	return rv;
 }
 
 static unsigned long
-proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
+pde_get_unmapped_area(struct proc_dir_entry *pde, struct file *file, unsigned long orig_addr,
 			   unsigned long len, unsigned long pgoff,
 			   unsigned long flags)
 {
-	struct proc_dir_entry *pde = PDE(file_inode(file));
-	unsigned long rv = -EIO;
+	typeof_member(struct proc_ops, proc_get_unmapped_area) get_area;
 
-	if (use_pde(pde)) {
-		typeof_member(struct proc_ops, proc_get_unmapped_area) get_area;
-
-		get_area = pde->proc_ops->proc_get_unmapped_area;
+	get_area = pde->proc_ops->proc_get_unmapped_area;
 #ifdef CONFIG_MMU
-		if (!get_area)
-			get_area = current->mm->get_unmapped_area;
+	if (!get_area)
+		get_area = current->mm->get_unmapped_area;
 #endif
+	if (get_area)
+		return get_area(file, orig_addr, len, pgoff, flags);
+	return orig_addr;
+}
 
-		if (get_area)
-			rv = get_area(file, orig_addr, len, pgoff, flags);
-		else
-			rv = orig_addr;
+static unsigned long
+proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
+			   unsigned long len, unsigned long pgoff,
+			   unsigned long flags)
+{
+	struct proc_dir_entry *pde = PDE(file_inode(file));
+	unsigned long rv = -EIO;
+
+	if (pde_is_permanent(pde)) {
+		return pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags);
+	} else if (use_pde(pde)) {
+		rv = pde_get_unmapped_area(pde, file, orig_addr, len, pgoff, flags);
 		unuse_pde(pde);
 	}
 	return rv;
@@ -337,6 +494,16 @@ static int proc_reg_open(struct inode *inode, struct file *file)
 	typeof_member(struct proc_ops, proc_release) release;
 	struct pde_opener *pdeo;
 
+	if (!pde->proc_ops->proc_lseek)
+		file->f_mode &= ~FMODE_LSEEK;
+
+	if (pde_is_permanent(pde)) {
+		open = pde->proc_ops->proc_open;
+		if (open)
+			rv = open(inode, file);
+		return rv;
+	}
+
 	/*
 	 * Ensure that
 	 * 1) PDE's ->release hook will be called no matter what
@@ -386,6 +553,17 @@ static int proc_reg_release(struct inode *inode, struct file *file)
 {
 	struct proc_dir_entry *pde = PDE(inode);
 	struct pde_opener *pdeo;
+
+	if (pde_is_permanent(pde)) {
+		typeof_member(struct proc_ops, proc_release) release;
+
+		release = pde->proc_ops->proc_release;
+		if (release) {
+			return release(inode, file);
+		}
+		return 0;
+	}
+
 	spin_lock(&pde->pde_unload_lock);
 	list_for_each_entry(pdeo, &pde->pde_openers, lh) {
 		if (pdeo->file == file) {
@@ -403,9 +581,19 @@ static const struct file_operations proc_reg_file_ops = {
 	.write		= proc_reg_write,
 	.poll		= proc_reg_poll,
 	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= proc_reg_compat_ioctl,
-#endif
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+static const struct file_operations proc_iter_file_ops = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.write		= proc_reg_write,
+	.splice_read	= generic_file_splice_read,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
 	.mmap		= proc_reg_mmap,
 	.get_unmapped_area = proc_reg_get_unmapped_area,
 	.open		= proc_reg_open,
@@ -413,12 +601,27 @@ static const struct file_operations proc_reg_file_ops = {
 };
 
 #ifdef CONFIG_COMPAT
-static const struct file_operations proc_reg_file_ops_no_compat = {
+static const struct file_operations proc_reg_file_ops_compat = {
 	.llseek		= proc_reg_llseek,
 	.read		= proc_reg_read,
 	.write		= proc_reg_write,
 	.poll		= proc_reg_poll,
 	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.compat_ioctl	= proc_reg_compat_ioctl,
+	.mmap		= proc_reg_mmap,
+	.get_unmapped_area = proc_reg_get_unmapped_area,
+	.open		= proc_reg_open,
+	.release	= proc_reg_release,
+};
+
+static const struct file_operations proc_iter_file_ops_compat = {
+	.llseek		= proc_reg_llseek,
+	.read_iter	= proc_reg_read_iter,
+	.splice_read	= generic_file_splice_read,
+	.write		= proc_reg_write,
+	.poll		= proc_reg_poll,
+	.unlocked_ioctl	= proc_reg_unlocked_ioctl,
+	.compat_ioctl	= proc_reg_compat_ioctl,
 	.mmap		= proc_reg_mmap,
 	.get_unmapped_area = proc_reg_get_unmapped_area,
 	.open		= proc_reg_open,
@@ -448,44 +651,54 @@ const struct inode_operations proc_link_inode_operations = {
 
 struct inode *proc_get_inode(struct super_block *sb, struct proc_dir_entry *de)
 {
-	struct inode *inode = new_inode_pseudo(sb);
+	struct inode *inode = new_inode(sb);
 
-	if (inode) {
-		inode->i_ino = de->low_ino;
-		inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
-		PROC_I(inode)->pde = de;
+	if (!inode) {
+		pde_put(de);
+		return NULL;
+	}
 
-		if (is_empty_pde(de)) {
-			make_empty_dir_inode(inode);
-			return inode;
-		}
-		if (de->mode) {
-			inode->i_mode = de->mode;
-			inode->i_uid = de->uid;
-			inode->i_gid = de->gid;
-		}
-		if (de->size)
-			inode->i_size = de->size;
-		if (de->nlink)
-			set_nlink(inode, de->nlink);
+	inode->i_private = de->data;
+	inode->i_ino = de->low_ino;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
+	PROC_I(inode)->pde = de;
+	if (is_empty_pde(de)) {
+		make_empty_dir_inode(inode);
+		return inode;
+	}
 
-		if (S_ISREG(inode->i_mode)) {
-			inode->i_op = de->proc_iops;
+	if (de->mode) {
+		inode->i_mode = de->mode;
+		inode->i_uid = de->uid;
+		inode->i_gid = de->gid;
+	}
+	if (de->size)
+		inode->i_size = de->size;
+	if (de->nlink)
+		set_nlink(inode, de->nlink);
+
+	if (S_ISREG(inode->i_mode)) {
+		inode->i_op = de->proc_iops;
+		if (de->proc_ops->proc_read_iter)
+			inode->i_fop = &proc_iter_file_ops;
+		else
 			inode->i_fop = &proc_reg_file_ops;
 #ifdef CONFIG_COMPAT
-			if (!de->proc_ops->proc_compat_ioctl) {
-				inode->i_fop = &proc_reg_file_ops_no_compat;
-			}
+		if (de->proc_ops->proc_compat_ioctl) {
+			if (de->proc_ops->proc_read_iter)
+				inode->i_fop = &proc_iter_file_ops_compat;
+			else
+				inode->i_fop = &proc_reg_file_ops_compat;
+		}
 #endif
-		} else if (S_ISDIR(inode->i_mode)) {
-			inode->i_op = de->proc_iops;
-			inode->i_fop = de->proc_dir_ops;
-		} else if (S_ISLNK(inode->i_mode)) {
-			inode->i_op = de->proc_iops;
-			inode->i_fop = NULL;
-		} else
-			BUG();
-	} else
-	       pde_put(de);
+	} else if (S_ISDIR(inode->i_mode)) {
+		inode->i_op = de->proc_iops;
+		inode->i_fop = de->proc_dir_ops;
+	} else if (S_ISLNK(inode->i_mode)) {
+		inode->i_op = de->proc_iops;
+		inode->i_fop = NULL;
+	} else {
+		BUG();
+	}
 	return inode;
 }